feat: computer-vision-engineer skill package v0.1.0

2026-08-14 17:28:44 +02:00
commit 9b21178015
9 changed files with 775 additions and 0 deletions
--- a/PROVENANCE.md
+++ b/PROVENANCE.md
@@ -0,0 +1,31 @@
+# Data provenance — computer-vision-engineer
+
+Where the content of this skill package comes from, counted by
+content items (tasks, competences, tools, evidence entries, curated
+knowledge). Rendered live by Gitea:
+
+```mermaid
+%%{init: {'theme':'base','themeVariables':{'pie1':'#f9a825','pie2':'#1e88e5','pie3':'#ff355e','pie4':'#d97757','pie5':'#8e24aa','pieOuterStrokeWidth':'0px','pieSectionTextColor':'#fff'}}}%%
+pie showData
+    title Content sources — computer-vision-engineer
+    "ESCO (occupation & competences)" : 53
+    "O*NET (tasks & tools)" : 120
+    "Job boards (market evidence)" : 106
+    "Anthropic official Claude skills" : 9
+    "External AI skill packs (mapped)" : 99
+```
+
+| Source | Items | Share | Files |
+|---|---|---|---|
+| ESCO (occupation & competences) | 53 | 13.7 % | references/profile.md, references/skills.md |
+| O*NET (tasks & tools) | 120 | 31.0 % | references/tasks.md, references/tools.md |
+| Job boards (market evidence) | 106 | 27.4 % | references/market.md (full report) + "Market evidence" headline sections |
+| Wikipedia & AI expert curation | 0 | 0.0 % | glossary, literature, usecases, intake, quality, evals/ |
+| Anthropic official Claude skills | 9 | 2.3 % | references/ai-skills.md, section "anthropics/skills" (official Claude Code skills) |
+| External AI skill packs (mapped) | 99 | 25.6 % | references/ai-skills.md (per-source attribution inside) |
+| Stack Exchange practitioner Q&A (CC-BY-SA) | 0 | 0.0 % | references/practitioner-qa.md (per-entry attribution inside) |
+
+Licensing: O*NET (USDOL/ETA, CC BY 4.0) · ESCO (© European Union) ·
+job-ad evidence via official APIs (JSearch/Adzuna) · Wikipedia content
+paraphrased with source URLs — never copied · external AI skills are
+linked, not copied (Apache-2.0/MIT/source-available, see ai-skills.md).
--- a/SKILL.md
+++ b/SKILL.md
@@ -0,0 +1,61 @@
+---
+name: computer-vision-engineer
+description: "Occupational skill for the role 'computer vision engineer' (also: computer vision applied scientist, computer vision expert, computer vision specialist, computer vision project engineer, smart technics computer vision engineer). Use when the user asks for typical computer vision engineer work such as: Analyze, manipulate, or process large sets of data using statistical software.; Apply feature selection algorithms to models predicting outcomes of interest, such as sales, attrition, and healthcare use.; Apply sampling techniques to determine groups to be surveyed or use complete enumeration methods."
+---
+
+# Computer Vision Engineer
+
+Computer vision engineers research, design, develop, and train artificial intelligence algorithms and machine learning primitives that understand the content of digital images based on a large amount of data. They apply this understanding to solve different real-world problems such as security, autonomous driving, robotic manufacturing, digital image classification, medical image processing and diagnosis, etc.
+
+## Core workflow
+
+1. Analyze, manipulate, or process large sets of data using statistical software.
+2. Apply feature selection algorithms to models predicting outcomes of interest, such as sales, attrition, and healthcare use.
+3. Apply sampling techniques to determine groups to be surveyed or use complete enumeration methods.
+4. Clean and manipulate raw data using statistical software.
+5. Compare models using statistical performance metrics, such as loss functions or proportion of explained variance.
+6. Create graphs, charts, or other visualizations to convey the results of data analysis using specialized software.
+7. Deliver oral or written presentations of the results of mathematical modeling and data analysis to management or other end users.
+8. Design surveys, opinion polls, or other instruments to collect data.
+
+## How to use this skill
+
+- Read [references/profile.md](references/profile.md) for the occupation profile and scope.
+- Consult [references/tasks.md](references/tasks.md) for the full task and activity inventory.
+- Check [references/skills.md](references/skills.md) for essential vs. optional competences.
+- Check [references/tools.md](references/tools.md) for the software commonly used in this role.
+- See [references/ai-skills.md](references/ai-skills.md) — matched external AI agent skills (per-source attribution).
+
+## Key competences (essential)
+
+- apply statistical analysis techniques
+- computer programming
+- computer simulation
+- conduct literature research
+- data engineering
+- data science
+- define technical requirements
+- deliver visual presentation of data
+- develop computer vision system
+- develop data processing applications
+- develop software prototype
+- digital image processing
+- digital twin technology
+- establish data processes
+- execute analytical mathematical calculations
+
+## Hot technologies
+
+- IBM SPSS Statistics
+- SAS
+- TensorFlow
+- The MathWorks MATLAB
+- Docker
+- GitHub
+- Kubernetes
+- Alteryx software
+- Apache Spark
+- Google Looker Analytics
+
+---
+*Sources: ESCO v1.2.1 (http://data.europa.eu/esco/occupation/1c5a45b9-440e-4726-b565-16a952abd341), O*NET 30.3 (15-2051.00). See manifest.json for licensing/attribution.*
--- a/manifest.json
+++ b/manifest.json
@@ -0,0 +1,118 @@
+{
+  "name": "computer-vision-engineer",
+  "title": "computer vision engineer",
+  "version": "0.1.0",
+  "layer": "core",
+  "language": "en",
+  "generated": "2026-07-07",
+  "ids": {
+    "esco_uri": "http://data.europa.eu/esco/occupation/1c5a45b9-440e-4726-b565-16a952abd341",
+    "esco_code": "2511.2",
+    "isco_group": "2511",
+    "onet_soc": "15-2051.00",
+    "crosswalk_match": "closeMatch"
+  },
+  "sources": [
+    {
+      "name": "ESCO",
+      "version": "1.2.1",
+      "url": "https://esco.ec.europa.eu/"
+    },
+    {
+      "name": "O*NET",
+      "version": "30.3",
+      "url": "https://www.onetcenter.org/",
+      "license": "CC BY 4.0"
+    }
+  ],
+  "attribution": "This package includes information from the O*NET Database (v30.3) by the U.S. Department of Labor, Employment and Training Administration (USDOL/ETA), CC BY 4.0. skillfactor is not endorsed by USDOL/ETA. ESCO data (v1.2.1) (c) European Union, used per the ESCO download conditions: https://esco.ec.europa.eu/en/use-esco/download",
+  "counts": {
+    "tasks": 16,
+    "dwas": 16,
+    "skills_essential": 32,
+    "skills_optional": 20,
+    "software": 87
+  },
+  "enrichment_ai_skills": {
+    "generated": "2026-07-14",
+    "method": "deterministic mapping (ISCO prefix + title/competence keywords)",
+    "sources": {
+      "anthropics/skills": {
+        "repo": "https://github.com/anthropics/skills",
+        "commit": "f6656c1",
+        "license": "Apache-2.0; the document skills (docx/pdf/pptx/xlsx) are source-available \u2014 see the LICENSE.txt in the upstream skill folder",
+        "skills": 6
+      },
+      "obra/superpowers": {
+        "repo": "https://github.com/obra/superpowers",
+        "commit": "d884ae0",
+        "license": "MIT (c) Jesse Vincent",
+        "skills": 12
+      },
+      "wshobson/agents": {
+        "repo": "https://github.com/wshobson/agents",
+        "commit": "6fd3247",
+        "license": "MIT (c) Seth Hobson",
+        "skills": 12
+      },
+      "NVIDIA/skills": {
+        "repo": "https://github.com/NVIDIA/skills",
+        "commit": "153b14b",
+        "license": "CC-BY-4.0 (skills/docs), Apache-2.0 (code)",
+        "skills": 12
+      },
+      "veniceai/skills": {
+        "repo": "https://github.com/veniceai/skills",
+        "commit": "de089fa",
+        "license": "MIT",
+        "skills": 9
+      },
+      "google/skills": {
+        "repo": "https://github.com/google/skills",
+        "commit": "b15f327",
+        "license": "Apache-2.0",
+        "skills": 12
+      },
+      "phuryn/pm-skills": {
+        "repo": "https://github.com/phuryn/pm-skills",
+        "commit": "18468a9",
+        "license": "MIT",
+        "skills": 9
+      },
+      "czlonkowski/n8n-skills": {
+        "repo": "https://github.com/czlonkowski/n8n-skills",
+        "commit": "9ea3aa5",
+        "license": "MIT",
+        "skills": 12
+      }
+    },
+    "total_skills": 84,
+    "tiers": {
+      "core": 34,
+      "adjacent": 50
+    }
+  },
+  "provenance": {
+    "items": {
+      "esco": 53,
+      "onet": 120,
+      "jobads": 106,
+      "wiki_ai": 0,
+      "anthropic": 9,
+      "ai_skills": 99,
+      "stackx": 0
+    },
+    "share_percent": {
+      "esco": 13.7,
+      "onet": 31.0,
+      "jobads": 27.4,
+      "wiki_ai": 0.0,
+      "anthropic": 2.3,
+      "ai_skills": 25.6,
+      "stackx": 0.0
+    },
+    "method": "content items per source category"
+  },
+  "collar": "white",
+  "computer_work": true
+}
--- a/references/ai-skills.md
+++ b/references/ai-skills.md
@@ -0,0 +1,166 @@
+# External AI agent skills — computer-vision-engineer
+
+Proven, publicly available AI agent skills mapped to this occupation.
+Nothing is copied from the sources: every entry is a name, a one-line
+summary and a link to the upstream skill package. Each section names
+its source repository, commit, license and retrieval date.
+
+**Tiers:** `core` = the skill directly exercises a top market hard
+skill, tool or method (from gated job-ad evidence) or an essential
+ESCO competence of this occupation; `adjacent` =
+plausibly useful, secondary. Entries are capped at 12 per source
+and 80 in total per occupation (core first,
+strongest matches survive); everything beyond the caps is excluded
+and logged in the pipeline audit trail, not in this package.
+
+_Matched deterministically (ISCO group + title/competence keywords,
+tiered against market evidence + ESCO essentials) by
+`pipeline/p5_enrich_ai_skills.py` on 2026-07-14._
+
+## Source: anthropics/skills
+
+- Repository: [https://github.com/anthropics/skills](https://github.com/anthropics/skills) (commit `f6656c1`, retrieved 2026-07-14)
+- License: Apache-2.0; the document skills (docx/pdf/pptx/xlsx) are source-available — see the LICENSE.txt in the upstream skill folder
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `mcp-builder` | core | Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python … | [source](https://github.com/anthropics/skills/tree/main/skills/mcp-builder) |
+| `claude-api` | adjacent | Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a … | [source](https://github.com/anthropics/skills/tree/main/skills/claude-api) |
+| `webapp-testing` | adjacent | Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. | [source](https://github.com/anthropics/skills/tree/main/skills/webapp-testing) |
+| `docx` | adjacent | Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to … | [source](https://github.com/anthropics/skills/tree/main/skills/docx) |
+| `pdf` | adjacent | Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating … | [source](https://github.com/anthropics/skills/tree/main/skills/pdf) |
+| `skill-creator` | adjacent | Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with … | [source](https://github.com/anthropics/skills/tree/main/skills/skill-creator) |
+
+## Source: obra/superpowers
+
+- Repository: [https://github.com/obra/superpowers](https://github.com/obra/superpowers) (commit `d884ae0`, retrieved 2026-07-14)
+- License: MIT (c) Jesse Vincent
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `brainstorming` | adjacent | You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. | [source](https://github.com/obra/superpowers/tree/main/skills/brainstorming) |
+| `subagent-driven-development` | adjacent | Use when executing implementation plans with independent tasks in the current session | [source](https://github.com/obra/superpowers/tree/main/skills/subagent-driven-development) |
+| `finishing-a-development-branch` | adjacent | Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup | [source](https://github.com/obra/superpowers/tree/main/skills/finishing-a-development-branch) |
+| `test-driven-development` | adjacent | Use when implementing any feature or bugfix, before writing implementation code | [source](https://github.com/obra/superpowers/tree/main/skills/test-driven-development) |
+| `using-git-worktrees` | adjacent | Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | [source](https://github.com/obra/superpowers/tree/main/skills/using-git-worktrees) |
+| `executing-plans` | adjacent | Use when you have a written implementation plan to execute in a separate session with review checkpoints | [source](https://github.com/obra/superpowers/tree/main/skills/executing-plans) |
+| `receiving-code-review` | adjacent | Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | [source](https://github.com/obra/superpowers/tree/main/skills/receiving-code-review) |
+| `requesting-code-review` | adjacent | Use when completing tasks, implementing major features, or before merging to verify work meets requirements | [source](https://github.com/obra/superpowers/tree/main/skills/requesting-code-review) |
+| `writing-plans` | adjacent | Use when you have a spec or requirements for a multi-step task, before touching code | [source](https://github.com/obra/superpowers/tree/main/skills/writing-plans) |
+| `writing-skills` | adjacent | Use when creating new skills, editing existing skills, or verifying skills work before deployment | [source](https://github.com/obra/superpowers/tree/main/skills/writing-skills) |
+| `dispatching-parallel-agents` | adjacent | Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | [source](https://github.com/obra/superpowers/tree/main/skills/dispatching-parallel-agents) |
+| `systematic-debugging` | adjacent | Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes | [source](https://github.com/obra/superpowers/tree/main/skills/systematic-debugging) |
+
+## Source: wshobson/agents
+
+- Repository: [https://github.com/wshobson/agents](https://github.com/wshobson/agents) (commit `6fd3247`, retrieved 2026-07-14)
+- License: MIT (c) Seth Hobson
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `recsys-pipeline-architect` | core | Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced X For You algorithm. Use when building any system that picks … | [source](https://github.com/wshobson/agents/tree/main/plugins/machine-learning-ops/skills/recsys-pipeline-architect) |
+| `prompt-engineering-patterns` | core | This skill should be used when the user asks to "optimize a prompt", "improve prompt performance", "design a prompt template", "write better prompts", "debug prompt issues", "use chain-of-thought", "structured prompting", "few-shot … | [source](https://github.com/wshobson/agents/tree/main/plugins/llm-application-dev/skills/prompt-engineering-patterns) |
+| `code-documentation-docs-architect (agent)` | core | Creates comprehensive technical documentation from existing codebases. Analyzes architecture, design patterns, and implementation details to produce long-form technical manuals and ebooks. Use PROACTIVELY for system documentation, … | [source](https://github.com/wshobson/agents/tree/main/plugins/code-documentation/agents/docs-architect.md) |
+| `codebase-cleanup-test-automator (agent)` | core | Master AI-powered test automation with modern frameworks, self-healing tests, and comprehensive quality engineering. Build scalable testing strategies with advanced CI/CD integration. Use PROACTIVELY for testing automation or quality … | [source](https://github.com/wshobson/agents/tree/main/plugins/codebase-cleanup/agents/test-automator.md) |
+| `dbt-transformation-patterns` | core | Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best … | [source](https://github.com/wshobson/agents/tree/main/plugins/data-engineering/skills/dbt-transformation-patterns) |
+| `debugging-strategies` | core | Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior. | [source](https://github.com/wshobson/agents/tree/main/plugins/developer-essentials/skills/debugging-strategies) |
+| `python-design-patterns` | core | Python design patterns including KISS, Separation of Concerns, Single Responsibility, and composition over inheritance. Use this skill when designing a new service or component from scratch and choosing how to layer responsibilities, when … | [source](https://github.com/wshobson/agents/tree/main/plugins/python-development/skills/python-design-patterns) |
+| `python-testing-patterns` | core | Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices. | [source](https://github.com/wshobson/agents/tree/main/plugins/python-development/skills/python-testing-patterns) |
+| `unit-testing-test-automator (agent)` | core | Master AI-powered test automation with modern frameworks, self-healing tests, and comprehensive quality engineering. Build scalable testing strategies with advanced CI/CD integration. Use PROACTIVELY for testing automation or quality … | [source](https://github.com/wshobson/agents/tree/main/plugins/unit-testing/agents/test-automator.md) |
+| `async-python-patterns` | core | Master Python asyncio, concurrent programming, and async/await patterns for high-performance applications. Use when building async APIs, concurrent systems, or I/O-bound applications requiring non-blocking operations. | [source](https://github.com/wshobson/agents/tree/main/plugins/python-development/skills/async-python-patterns) |
+| `python-background-jobs` | core | Python background job patterns including task queues, workers, and event-driven architecture. Use when implementing async task processing, job queues, long-running operations, or decoupling work from request/response cycles. | [source](https://github.com/wshobson/agents/tree/main/plugins/python-development/skills/python-background-jobs) |
+| `python-error-handling` | core | Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust … | [source](https://github.com/wshobson/agents/tree/main/plugins/python-development/skills/python-error-handling) |
+
+## Source: google/skills
+
+- Repository: [https://github.com/google/skills](https://github.com/google/skills) (commit `b15f327`, retrieved 2026-07-14)
+- License: Apache-2.0
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `bigquery-ai-ml` | core | Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, detect outliers, find key drivers, or leverage generative AI … | [source](https://github.com/google/skills/tree/b15f327/skills/cloud/bigquery-ai-ml) |
+| `agent-platform-eval-flywheel` | core | Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing … | [source](https://github.com/google/skills/tree/b15f327/skills/cloud/agent-platform-eval-flywheel) |
+| `bigtable-basics` | core | Assists in provisioning instances/tables, designing performant schemas, and querying data in Bigtable. Use when designing Bigtable row keys, configuring column families, writing SQL queries or client library code (Java, Go, Python) for … | [source](https://github.com/google/skills/tree/b15f327/skills/cloud/bigtable-basics) |
+| `cloud-sql-basics` | core | This file generates or explains Cloud SQL resources. Use this file when the user asks to create a Cloud SQL instance or database for MySQL, PostgreSQL, or SQL Server. Cloud SQL manages third-party MySQL, PostgreSQL, and SQL Server … | [source](https://github.com/google/skills/tree/b15f327/skills/cloud/cloud-sql-basics) |
+| `bigquery-basics` | adjacent | Manages datasets, tables, and jobs in BigQuery. Use when you need to interact with BigQuery, run SQL queries, manage BigQuery resources (datasets, tables, views), or perform basic data ingestion and analysis. | [source](https://github.com/google/skills/tree/b15f327/skills/cloud/bigquery-basics) |
+| `datalineage-bigquery-asset-impact-analysis` | adjacent | Analyzes the downstream impact (blast radius) when a BigQuery table or view is broken, stale, or modified. Identifies all downstream tables, dashboards, and processes that will be affected. Use when: - Performing a blast radius or impact … | [source](https://github.com/google/skills/tree/b15f327/skills/cloud/datalineage-bigquery-asset-impact-analysis) |
+| `alloydb-basics` | adjacent | Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB model context protocol (MCP) tools for automated database operations. | [source](https://github.com/google/skills/tree/b15f327/skills/cloud/alloydb-basics) |
+| `agent-platform-alert-configuration` | adjacent | Configures best-practice alerting policies for Google Cloud Vertex AI / Agent Platform agents on Agent Runtime. Use when analyzing, writing, or deploying alerting policies to monitor agent latency, error rates, and quality metrics … | [source](https://github.com/google/skills/tree/b15f327/skills/cloud/agent-platform-alert-configuration) |
+| `gke-observability` | adjacent | Configures GKE observability, including Cloud Logging, Cloud Monitoring, and managed Prometheus. Use when configuring GKE monitoring, setting up GKE logging, or configuring Prometheus metrics collection. Don't use to configure local … | [source](https://github.com/google/skills/tree/b15f327/skills/cloud/gke-observability) |
+| `google-analytics-admin-api-basics` | adjacent | Manages Google Analytics account and property settings, enables the Analytics Admin API via the Cloud CLI, lists accounts and properties, and manages data streams, custom dimensions, conversion events, and integrations. Use when you need … | [source](https://github.com/google/skills/tree/b15f327/skills/analytics/google-analytics-admin-api-basics) |
+| `google-analytics-data-api-basics` | adjacent | Manages Google Analytics reporting data, enables the Analytics Data API via the Cloud CLI, and creates reports using the Google Analytics Data API (v1beta). Use when you need to interact with Google Analytics properties, run customized … | [source](https://github.com/google/skills/tree/b15f327/skills/analytics/google-analytics-data-api-basics) |
+| `google-cloud-networking-observability` | adjacent | Investigates Google Cloud networking issues by analyzing logs, metrics, and diagnostics. Use when investigating VPC Flow Logs (including cost estimation), NAT, firewall, or threat logs, querying latency and throughput metrics, or running … | [source](https://github.com/google/skills/tree/b15f327/skills/cloud/google-cloud-networking-observability) |
+
+## Source: czlonkowski/n8n-skills
+
+- Repository: [https://github.com/czlonkowski/n8n-skills](https://github.com/czlonkowski/n8n-skills) (commit `9ea3aa5`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `n8n-code-python` | core | Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes. Use this skill when the user specifically … | [source](https://github.com/czlonkowski/n8n-skills/tree/9ea3aa5/skills/n8n-code-python) |
+| `n8n-code-tool` | core | Write JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will … | [source](https://github.com/czlonkowski/n8n-skills/tree/9ea3aa5/skills/n8n-code-tool) |
+| `n8n-node-configuration` | adjacent | Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between get_node detail levels, or learning common configuration patterns by node type. … | [source](https://github.com/czlonkowski/n8n-skills/tree/9ea3aa5/skills/n8n-node-configuration) |
+| `n8n-agents` | adjacent | Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain.* AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool … | [source](https://github.com/czlonkowski/n8n-skills/tree/9ea3aa5/skills/n8n-agents) |
+| `n8n-binary-and-data` | adjacent | Handle files and binary data in n8n correctly. Use when working with files, images, PDFs, attachments, uploads or downloads, base64, vision/multimodal input, or when an AI agent needs a file as tool input or output — and whenever the user … | [source](https://github.com/czlonkowski/n8n-skills/tree/9ea3aa5/skills/n8n-binary-and-data) |
+| `n8n-workflow-patterns` | adjacent | Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API … | [source](https://github.com/czlonkowski/n8n-skills/tree/9ea3aa5/skills/n8n-workflow-patterns) |
+| `n8n-validation-expert` | adjacent | Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about … | [source](https://github.com/czlonkowski/n8n-skills/tree/9ea3aa5/skills/n8n-validation-expert) |
+| `n8n-mcp-tools-expert` | adjacent | Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, managing credentials, auditing instance security, or using any n8n-mcp tool. Provides … | [source](https://github.com/czlonkowski/n8n-skills/tree/9ea3aa5/skills/n8n-mcp-tools-expert) |
+| `n8n-subworkflows` | adjacent | Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over ~10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, … | [source](https://github.com/czlonkowski/n8n-skills/tree/9ea3aa5/skills/n8n-subworkflows) |
+| `n8n-code-javascript` | adjacent | Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with this.helpers / the $helpers global, working with dates using DateTime, troubleshooting Code node … | [source](https://github.com/czlonkowski/n8n-skills/tree/9ea3aa5/skills/n8n-code-javascript) |
+| `n8n-error-handling` | adjacent | Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the … | [source](https://github.com/czlonkowski/n8n-skills/tree/9ea3aa5/skills/n8n-error-handling) |
+| `n8n-expression-syntax` | adjacent | Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, mapping data between nodes, or referencing webhook data in … | [source](https://github.com/czlonkowski/n8n-skills/tree/9ea3aa5/skills/n8n-expression-syntax) |
+
+## Source: NVIDIA/skills
+
+- Repository: [https://github.com/NVIDIA/skills](https://github.com/NVIDIA/skills) (commit `153b14b`, retrieved 2026-07-14)
+- License: CC-BY-4.0 (skills/docs), Apache-2.0 (code)
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `deepstream-dev` | core | NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker … | [source](https://github.com/NVIDIA/skills/tree/153b14b/skills/deepstream-dev) |
+| `tao-finetune-clip` | core | CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot classification, computing image embeddings, … | [source](https://github.com/NVIDIA/skills/tree/153b14b/skills/tao-finetune-clip) |
+| `tao-port-huggingface-model` | core | Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline). Use when the user asks to "integrate a HuggingFace model into TAO", "add an HF model … | [source](https://github.com/NVIDIA/skills/tree/153b14b/skills/tao-port-huggingface-model) |
+| `tao-train-visual-changenet` | core | Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluating, exporting, or running inference for PCB defect detection or visual inspection, comparing image pairs for PASS/NO_PASS … | [source](https://github.com/NVIDIA/skills/tree/153b14b/skills/tao-train-visual-changenet) |
+| `deepstream-generate-pipeline` | core | Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming — including natural phrases like 'pipeline to infer on image', 'run inference on … | [source](https://github.com/NVIDIA/skills/tree/153b14b/skills/deepstream-generate-pipeline) |
+| `tao-train-mask2former` | core | Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with masked attention for high-quality segmentation results. Use when training, evaluating, exporting, quantizing, or running inference for … | [source](https://github.com/NVIDIA/skills/tree/153b14b/skills/tao-train-mask2former) |
+| `tao-train-pointpillars` | core | PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a pillar-based representation, then applies 2D detection — used in autonomous driving and robotics. Use when training, evaluating, … | [source](https://github.com/NVIDIA/skills/tree/153b14b/skills/tao-train-pointpillars) |
+| `tilegym-cutile-python` | core | Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks. | [source](https://github.com/NVIDIA/skills/tree/153b14b/skills/tilegym-cutile-python) |
+| `tao-train-deformable-detr` | core | Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing, lighter than DINO with competitive accuracy. Use when training, evaluating, exporting, quantizing, or running inference for a … | [source](https://github.com/NVIDIA/skills/tree/153b14b/skills/tao-train-deformable-detr) |
+| `tao-finetune-huggingface-model` | core | Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container. Use when the user wants to fine-tune a HuggingFace model (full or LoRA), train a vision / VLM / LLM model end-to-end, generate a … | [source](https://github.com/NVIDIA/skills/tree/153b14b/skills/tao-finetune-huggingface-model) |
+| `tao-train-oneformer` | core | OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned queries. Use when training, evaluating, exporting, quantizing, or running inference for a … | [source](https://github.com/NVIDIA/skills/tree/153b14b/skills/tao-train-oneformer) |
+| `dynamo-recipe-runner` | core | Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments. | [source](https://github.com/NVIDIA/skills/tree/153b14b/skills/dynamo-recipe-runner) |
+
+## Source: phuryn/pm-skills
+
+- Repository: [https://github.com/phuryn/pm-skills](https://github.com/phuryn/pm-skills) (commit `18468a9`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `ab-test-analysis` | core | Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split … | [source](https://github.com/phuryn/pm-skills/tree/18468a9/pm-data-analytics/skills/ab-test-analysis) |
+| `dummy-dataset` | core | Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and … | [source](https://github.com/phuryn/pm-skills/tree/18468a9/pm-execution/skills/dummy-dataset) |
+| `sql-queries` | core | Generate SQL queries from natural language descriptions. Supports BigQuery, PostgreSQL, MySQL, and other dialects. Reads database schemas from uploaded diagrams or documentation. Use when writing SQL, building data reports, exploring … | [source](https://github.com/phuryn/pm-skills/tree/18468a9/pm-data-analytics/skills/sql-queries) |
+| `cohort-analysis` | adjacent | Perform cohort analysis on user engagement data — retention curves, feature adoption trends, and segment-level insights. Use when analyzing user retention by cohort, studying feature adoption over time, investigating churn patterns, or … | [source](https://github.com/phuryn/pm-skills/tree/18468a9/pm-data-analytics/skills/cohort-analysis) |
+| `metrics-dashboard` | adjacent | Define and design a product metrics dashboard with key metrics, data sources, visualization types, and alert thresholds. Use when creating a metrics dashboard, defining KPIs, setting up product analytics, or building a data monitoring plan. | [source](https://github.com/phuryn/pm-skills/tree/18468a9/pm-product-discovery/skills/metrics-dashboard) |
+| `lean-canvas` | adjacent | Generate a Lean Canvas with problem, solution, metrics, cost structure, UVP, unfair advantage, channels, segments, and revenue. Use when exploring a lean startup canvas, testing a business hypothesis, or modeling a new venture. | [source](https://github.com/phuryn/pm-skills/tree/18468a9/pm-product-strategy/skills/lean-canvas) |
+| `north-star-metric` | adjacent | Define a North Star Metric and 3-5 supporting input metrics that form a metrics constellation. Classify the business game (Attention, Transaction, Productivity) and validate against 7 criteria for an effective North Star. Use when choosing … | [source](https://github.com/phuryn/pm-skills/tree/18468a9/pm-marketing-growth/skills/north-star-metric) |
+| `product-strategy` | adjacent | Create a comprehensive product strategy using the 9-section Product Strategy Canvas — vision, segments, costs, value propositions, trade-offs, metrics, growth, capabilities, and defensibility. Use when building a product strategy, creating … | [source](https://github.com/phuryn/pm-skills/tree/18468a9/pm-product-strategy/skills/product-strategy) |
+| `gtm-strategy` | adjacent | Create a go-to-market strategy covering marketing channels, messaging, success metrics, and launch timeline. Use when planning a product launch, creating a GTM plan from scratch, or defining a launch strategy for a new market. | [source](https://github.com/phuryn/pm-skills/tree/18468a9/pm-go-to-market/skills/gtm-strategy) |
+
+## Source: veniceai/skills
+
+- Repository: [https://github.com/veniceai/skills](https://github.com/veniceai/skills) (commit `de089fa`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `venice-characters` | adjacent | Discover and use Venice public characters (persona-driven system prompts with a bound model). Covers GET /characters (search/filter/sort), /characters/{slug}, /characters/{slug}/reviews, the Character schema, and how to apply a character … | [source](https://github.com/veniceai/skills/tree/de089fa/skills/venice-characters) |
+| `venice-image-edit` | adjacent | Transform existing images with Venice. Covers POST /image/edit (prompt-driven single-image edit), /image/multi-edit (compose 1-3 images), /image/upscale (2-4x upscale + enhance), and /image/background-remove. Accepts base64, file upload, … | [source](https://github.com/veniceai/skills/tree/de089fa/skills/venice-image-edit) |
+| `venice-image-generate` | adjacent | Generate images with Venice. Covers POST /image/generate (Venice-native), POST /images/generations (OpenAI-compatible), GET /image/styles (style presets), request fields (prompt, dimensions, cfg_scale, seed, variants, style_preset, … | [source](https://github.com/veniceai/skills/tree/de089fa/skills/venice-image-generate) |
+| `venice-api-overview` | adjacent | High-level map of the Venice.ai API - base URL, authentication modes, endpoint categories, response headers, pricing model, error shape, and versioning. Load this first when starting any Venice integration. | [source](https://github.com/veniceai/skills/tree/de089fa/skills/venice-api-overview) |
+| `venice-embeddings` | adjacent | Call POST /embeddings on Venice. Covers request shape (input, model, encoding_format, dimensions, user), OpenAI compatibility, response compression (gzip/br), and practical usage for retrieval, clustering, and RAG. | [source](https://github.com/veniceai/skills/tree/de089fa/skills/venice-embeddings) |
+| `venice-api-keys` | adjacent | Manage Venice API keys. Covers GET/POST/PATCH/DELETE /api_keys, GET /api_keys/{id}, GET /api_keys/rate_limits, GET /api_keys/rate_limits/log, the two-step /api_keys/generate_web3_key wallet flow, INFERENCE vs ADMIN key types, and per-key … | [source](https://github.com/veniceai/skills/tree/de089fa/skills/venice-api-keys) |
+| `venice-errors` | adjacent | Handle Venice API errors correctly. Covers the StandardError / DetailedError / ContentViolationError / X402InferencePaymentRequired body shapes, every meaningful status code (400, 401, 402, 403, 415, 422, 429, 500, 503, 504), the 402 … | [source](https://github.com/veniceai/skills/tree/de089fa/skills/venice-errors) |
+| `venice-auth` | adjacent | Authenticate to the Venice API with a Bearer API key or with an x402 / SIWE wallet. Covers header formats, the SIWE message fields, TTL and nonce rules, the venice-x402-client SDK, and how to choose between the two modes. | [source](https://github.com/veniceai/skills/tree/de089fa/skills/venice-auth) |
+| `venice-responses` | adjacent | Use Venice's Alpha POST /responses endpoint - an OpenAI-compatible Responses API with typed output blocks (reasoning, message, function_call, web_search_call). Covers request shape, streaming, differences from /chat/completions, supported … | [source](https://github.com/veniceai/skills/tree/de089fa/skills/venice-responses) |
--- a/references/market.md
+++ b/references/market.md
@@ -0,0 +1,63 @@
+# Market evidence report — computer-vision-engineer
+
+Source: **5 real job ads** (JSearch API, countries: us 5), extracted into the MSSQL evidence store; as of 2026-07-10.
+This report contains extracted, aggregated facts only — no ad text is
+reproduced (copyright / platform terms).
+
+## Seniority distribution
+
+| Seniority | Ads | Share |
+|---|---|---|
+| mid | 4 | 80 % |
+| lead | 1 | 20 % |
+
+## Tools — full market ranking
+
+| # | Item | Ads | Share |
+|---|---|---|---|
+| 1 | Python | 3 | 60 % |
+
+## Hard skills — full market ranking
+
+| # | Item | Ads | Share |
+|---|---|---|---|
+| 1 | computer vision | 5 | 100 % |
+
+## Methods — full market ranking
+
+| # | Item | Ads | Share |
+|---|---|---|---|
+
+## Responsibilities — full market ranking
+
+| # | Item | Ads | Share |
+|---|---|---|---|
+
+## Regional breakdown
+
+> **Corpus note:** 5 relevant ads in total — below the 100-ad target for a fully reliable ranking. Percentages above should be read as indicative.
+
+### US (us)
+
+**Insufficient evidence** — 5 ads (minimum for a regional ranking: 30). No ranking is reported for this region.
+
+### UK (gb)
+
+**Insufficient evidence** — 0 ads (minimum for a regional ranking: 30). No ranking is reported for this region.
+
+### EU/DACH (de, at, ch, nl)
+
+**Insufficient evidence** — 0 ads (minimum for a regional ranking: 30). No ranking is reported for this region.
+
+
+## Job title variants in the market
+
+| Title | Ads |
+|---|---|
+| Applied Computer Vision Engineer ML, AI 🏆 | 1 |
+| Cleared Computer Vision Scientist | 1 |
+| Computer Vision AI Engineer | 1 |
+| Lead Software Engineer – Computer Vision & Automation (Transportation) | 1 |
+| Space Computer Vision Engineer — AI-Driven Autonomy | 1 |
+
+Methodology: entities extracted per ad ({hard_skills, tools, methods, responsibilities, seniority}), normalized, counted as DISTINCT ads per entity; report threshold ≥ 3 ads. Headline sections in skills.md/tools.md use the stricter ≥ 20 % threshold.
--- a/references/profile.md
+++ b/references/profile.md
@@ -0,0 +1,22 @@
+# Occupation profile — computer vision engineer
+
+- **ESCO URI:** http://data.europa.eu/esco/occupation/1c5a45b9-440e-4726-b565-16a952abd341
+- **ESCO code:** 2511.2
+- **ISCO-08 group:** 2511 — Systems analysts
+- **O*NET-SOC:** 15-2051.00 — Data Scientists (match: closeMatch)
+
+## Description (ESCO)
+
+Computer vision engineers research, design, develop, and train artificial intelligence algorithms and machine learning primitives that understand the content of digital images based on a large amount of data. They apply this understanding to solve different real-world problems such as security, autonomous driving, robotic manufacturing, digital image classification, medical image processing and diagnosis, etc.
+
+## Definition
+
+nan
+
+## Alternative labels
+
+- computer vision applied scientist
+- computer vision expert
+- computer vision specialist
+- computer vision project engineer
+- smart technics computer vision engineer
--- a/references/skills.md
+++ b/references/skills.md
@@ -0,0 +1,137 @@
+# Competences — computer vision engineer
+
+Source: ESCO v1.2.1 occupation-skill relations (http://data.europa.eu/esco/occupation/1c5a45b9-440e-4726-b565-16a952abd341).
+
+## Essential
+
+- **apply statistical analysis techniques** (skill/competence)
+- **computer programming** (knowledge)
+- **computer simulation** (knowledge)
+- **conduct literature research** (skill/competence)
+- **data engineering** (knowledge)
+- **data science** (knowledge)
+- **define technical requirements** (skill/competence)
+- **deliver visual presentation of data** (skill/competence)
+- **develop computer vision system** (skill/competence)
+- **develop data processing applications** (skill/competence)
+- **develop software prototype** (skill/competence)
+- **digital image processing** (knowledge)
+- **digital twin technology** (knowledge)
+- **establish data processes** (skill/competence)
+- **execute analytical mathematical calculations** (skill/competence)
+- **handle data samples** (skill/competence)
+- **image recognition** (knowledge)
+- **implement data quality processes** (skill/competence)
+- **integrated development environment software** (knowledge)
+- **interpret current data** (skill/competence)
+- **machine learning** (knowledge)
+- **manage data collection systems** (skill/competence)
+- **normalise data** (skill/competence)
+- **perform data cleansing** (skill/competence)
+- **perform dimensionality reduction** (skill/competence)
+- **principles of artificial intelligence** (knowledge)
+- **Python (computer programming)** (knowledge)
+- **report analysis results** (skill/competence)
+- **scientific computing** (knowledge)
+- **statistics** (knowledge)
+- **use software libraries** (skill/competence)
+- **utilise computer-aided software engineering tools** (skill/competence)
+
+## Optional
+
+- cognitive computing (knowledge)
+- computer graphics (knowledge)
+- conduct qualitative research (skill/competence)
+- conduct quantitative research (skill/competence)
+- conduct scholarly research (skill/competence)
+- create data models (skill/competence)
+- debug software (skill/competence)
+- deep learning (knowledge)
+- define data quality criteria (skill/competence)
+- design user interface (skill/competence)
+- digital systems (knowledge)
+- image formation (knowledge)
+- mathematical modelling (knowledge)
+- perform data mining (skill/competence)
+- quantum computing (knowledge)
+- query languages (knowledge)
+- resource description framework query language (knowledge)
+- signal processing (knowledge)
+- state estimation (knowledge)
+- use markup languages (skill/competence)
+
+<!-- market-evidence -->
+
+## Market evidence (job-ad analysis, 5 ads, as of 2026-07-10)
+
+Share of analyzed job ads mentioning the item (threshold ≥ 20 %). Source: JSearch/Adzuna APIs.
+
+### Hard skills
+
+- computer vision — **100 %**
+- algorithm development — **40 %**
+- deep learning — **40 %**
+- image processing — **40 %**
+- geospatial analysis — **20 %**
+- data engineering — **20 %**
+- data preprocessing — **20 %**
+- data science — **20 %**
+- algorithm optimization — **20 %**
+- automation — **20 %**
+- business development — **20 %**
+- algorithm design — **20 %**
+- machine learning — **20 %**
+- machine learning engineering — **20 %**
+- machine learning pipelines — **20 %**
+- model deployment — **20 %**
+- model evaluation — **20 %**
+- object recognition — **20 %**
+- predictive modeling — **20 %**
+- sensor fusion — **20 %**
+- target tracking — **20 %**
+- system design — **20 %**
+
+### Methods
+
+- tracking — **20 %**
+- transformer models — **20 %**
+- transformers — **20 %**
+- object detection — **20 %**
+- scrum — **20 %**
+- micro-service design — **20 %**
+- machine learning — **20 %**
+- agile methodologies — **20 %**
+- CNNs — **20 %**
+- CI/CD — **20 %**
+- classification — **20 %**
+- deep learning — **20 %**
+- image segmentation — **20 %**
+
+### Responsibilities
+
+- model deployment — **40 %**
+- model training — **40 %**
+- pipeline design — **20 %**
+- proposal writing — **20 %**
+- requirements breakdown — **20 %**
+- software delivery — **20 %**
+- model development — **20 %**
+- model experimentation — **20 %**
+- model testing — **20 %**
+- innovation application — **20 %**
+- engineer mentoring — **20 %**
+- experimentation — **20 %**
+- documentation maintenance — **20 %**
+- data analysis — **20 %**
+- data conversion — **20 %**
+- client engagement — **20 %**
+- code documentation — **20 %**
+- cost estimation — **20 %**
+- technical leadership — **20 %**
+- technical solution development — **20 %**
+- technology support — **20 %**
+- system design — **20 %**
+- system implementation — **20 %**
+- status briefing — **20 %**
+
+<!-- market-evidence -->
--- a/references/tasks.md
+++ b/references/tasks.md
@@ -0,0 +1,41 @@
+# Tasks & work activities — computer vision engineer
+
+Source: O*NET 30.3, occupation 15-2051.00 (Data Scientists).
+
+## Task statements
+
+- **[nan]** Analyze, manipulate, or process large sets of data using statistical software.
+- **[nan]** Apply feature selection algorithms to models predicting outcomes of interest, such as sales, attrition, and healthcare use.
+- **[nan]** Apply sampling techniques to determine groups to be surveyed or use complete enumeration methods.
+- **[nan]** Clean and manipulate raw data using statistical software.
+- **[nan]** Compare models using statistical performance metrics, such as loss functions or proportion of explained variance.
+- **[nan]** Create graphs, charts, or other visualizations to convey the results of data analysis using specialized software.
+- **[nan]** Deliver oral or written presentations of the results of mathematical modeling and data analysis to management or other end users.
+- **[nan]** Design surveys, opinion polls, or other instruments to collect data.
+- **[nan]** Identify business problems or management objectives that can be addressed through data analysis.
+- **[nan]** Identify relationships and trends or any factors that could affect the results of research.
+- **[nan]** Identify solutions to business problems, such as budgeting, staffing, and marketing decisions, using the results of data analysis.
+- **[nan]** Propose solutions in engineering, the sciences, and other fields using mathematical theories and techniques.
+- **[nan]** Read scientific articles, conference papers, or other sources of research to identify emerging analytic trends and technologies.
+- **[nan]** Recommend data-driven solutions to key stakeholders.
+- **[nan]** Test, validate, and reformulate models to ensure accurate prediction of outcomes of interest.
+- **[nan]** Write new functions or applications in programming languages to conduct analyses.
+
+## Detailed work activities
+
+- Advise others on analytical techniques.
+- Analyze business or financial data.
+- Analyze data to identify or resolve operational problems.
+- Analyze data to identify trends or relationships among variables.
+- Analyze data to inform operational decisions or activities.
+- Apply mathematical principles or statistical approaches to solve problems in scientific or applied fields.
+- Determine appropriate methods for data analysis.
+- Develop procedures to evaluate organizational activities.
+- Develop scientific or mathematical models.
+- Prepare analytical reports.
+- Prepare data for analysis.
+- Prepare graphics or other visual representations of information.
+- Present research results to others.
+- Select resources needed to accomplish tasks.
+- Update technical knowledge.
+- Write computer programming code.
--- a/references/tools.md
+++ b/references/tools.md
@@ -0,0 +1,136 @@
+# Tools & technology — computer vision engineer
+
+Source: O*NET 30.3 'Software Skills' for 15-2051.00.
+
+| Software | Category | Hot technology |
+|---|---|---|
+| IBM SPSS Statistics | Analytical or scientific software | yes |
+| SAS | Analytical or scientific software | yes |
+| TensorFlow | Analytical or scientific software | yes |
+| The MathWorks MATLAB | Analytical or scientific software | yes |
+| Docker | Application server software | yes |
+| GitHub | Application server software | yes |
+| Kubernetes | Application server software | yes |
+| Alteryx software | Business intelligence and data analysis software | yes |
+| Apache Spark | Business intelligence and data analysis software | yes |
+| Google Looker Analytics | Business intelligence and data analysis software | yes |
+| Microsoft Power BI | Business intelligence and data analysis software | yes |
+| Tableau | Business intelligence and data analysis software | yes |
+| Atlassian JIRA | Content workflow software | yes |
+| Apache Cassandra | Data base management system software | yes |
+| Apache Hadoop | Data base management system software | yes |
+| Apache Hive | Data base management system software | yes |
+| Elasticsearch | Data base management system software | yes |
+| MongoDB | Data base management system software | yes |
+| NoSQL | Data base management system software | yes |
+| Teradata Database | Data base management system software | yes |
+| Amazon Elastic Compute Cloud EC2 | Data base user interface and query software | yes |
+| Amazon Redshift | Data base user interface and query software | yes |
+| Amazon Web Services AWS software | Data base user interface and query software | yes |
+| Microsoft Access | Data base user interface and query software | yes |
+| Microsoft SQL Server | Data base user interface and query software | yes |
+| PyTorch | Data base user interface and query software | yes |
+| Structured query language SQL | Data base user interface and query software | yes |
+| Snowflake | Data mining software | yes |
+| Apache Kafka | Development environment software | yes |
+| C | Development environment software | yes |
+| Go | Development environment software | yes |
+| Microsoft Azure software | Development environment software | yes |
+| Ruby | Development environment software | yes |
+| Jenkins CI | Enterprise application integration software | yes |
+| Splunk Enterprise | Enterprise system management software | yes |
+| Git | File versioning software | yes |
+| C# | Object or component oriented development software | yes |
+| C++ | Object or component oriented development software | yes |
+| Oracle Java | Object or component oriented development software | yes |
+| Perl | Object or component oriented development software | yes |
+| Python | Object or component oriented development software | yes |
+| R | Object or component oriented development software | yes |
+| Scala | Object or component oriented development software | yes |
+| PostgreSQL | Object oriented data base management software | yes |
+| Microsoft Office software | Office suite software | yes |
+| Bash | Operating system software | yes |
+| Linux | Operating system software | yes |
+| Shell script | Operating system software | yes |
+| UNIX | Operating system software | yes |
+| Microsoft PowerPoint | Presentation software | yes |
+| Apache Airflow | Procedure management software | yes |
+| Atlassian Confluence | Project management software | yes |
+| Microsoft Excel | Spreadsheet software | yes |
+| JavaScript | Web platform development software | yes |
+| JavaScript Object Notation JSON | Web platform development software | yes |
+| Kubeflow | Analytical or scientific software |  |
+| Mathematical software | Analytical or scientific software |  |
+| Mlflow | Analytical or scientific software |  |
+| StataCorp Stata | Analytical or scientific software |  |
+| Statistical software | Analytical or scientific software |  |
+| Business intelligence software | Business intelligence and data analysis software |  |
+| MapReduce big data software | Business intelligence and data analysis software |  |
+| Qlik Tech QlikView | Business intelligence and data analysis software |  |
+| Amazon Web Services AWS SageMaker | Cloud-based management software |  |
+| Google Cloud software | Cloud-based management software |  |
+| Apache Pig | Data base management system software |  |
+| Reporting software | Data base reporting software |  |
+| BigQuery | Data base user interface and query software |  |
+| Neo4j | Data base user interface and query software |  |
+| NumPy | Data base user interface and query software |  |
+| pandas | Data base user interface and query software |  |
+| PySpark | Data base user interface and query software |  |
+| Flask | Development environment software |  |
+| Julia | Development environment software |  |
+| OpenAI ChatGPT | Development environment software |  |
+| Scikit-learn | Development environment software |  |
+| XGBoost | Development environment software |  |
+| Management information systems MIS | Enterprise resource planning ERP software |  |
+| Geographic information system GIS systems | Geographic information system |  |
+| Apache MXNet | Industrial control software |  |
+| Jupyter software | Object or component oriented development software |  |
+| SciPy | Object or component oriented development software |  |
+| Shiny | Object or component oriented development software |  |
+| spaCy | Object or component oriented development software |  |
+| Keras | Operating system software |  |
+| Amazon Simple Storage Service S3 | Storage networking software |  |
+| RESTful API | Web platform development software |  |
+
+<!-- market-evidence -->
+
+## Market evidence (job-ad analysis, 5 ads, as of 2026-07-10)
+
+Share of analyzed job ads mentioning the item (threshold ≥ 20 %). Source: JSearch/Adzuna APIs.
+
+### Tools
+
+- Python — **60 %**
+- PyTorch — **40 %**
+- OpenCV — **40 %**
+- Kubernetes — **40 %**
+- C++ — **40 %**
+- TensorFlow — **40 %**
+- WandB — **20 %**
+- Airflow — **20 %**
+- AWS — **20 %**
+- Azure — **20 %**
+- Bitbucket”, “Confluence”] — **20 %**
+- CUDA — **20 %**
+- Cloud Foundry — **20 %**
+- DVC — **20 %**
+- Docker — **20 %**
+- gdal”, “geopandas”, “shapely” — **20 %**
+- Gitlab CI — **20 %**
+- Java — **20 %**
+- Jira — **20 %**
+- Kubeflow — **20 %**
+- MLFlow — **20 %**
+- matplotlib — **20 %**
+- OpenShift — **20 %**
+- Oracle — **20 %**
+- pandas — **20 %**
+- RAPIDs — **20 %**
+- PostgreSQL — **20 %**
+- MySQL — **20 %**
+- numpy — **20 %**
+- SQL Server — **20 %**
+- sklearn — **20 %**
+- Rust — **20 %**
+
+<!-- market-evidence -->