38 KiB
External AI agent skills — corporate-training-manager
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 (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 |
|---|---|---|---|
internal-comms |
adjacent | A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership … | source |
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 |
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 |
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 |
pptx |
adjacent | Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even … | source |
slack-gif-creator |
adjacent | Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack. | source |
Source: wshobson/agents
- Repository: https://github.com/wshobson/agents (commit
6fd3247, retrieved 2026-07-14) - License: MIT (c) Seth Hobson
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
gdpr-data-handling |
core | Implement GDPR-compliant data handling with consent management, data subject rights, and privacy by design. Use when building systems that process EU personal data, implementing privacy controls, or conducting GDPR compliance reviews. | source |
employment-contract-templates |
core | Create employment contracts, offer letters, and HR policy documents following legal best practices. Use when drafting employment agreements, creating HR policies, or standardizing employment documentation. | source |
team-collaboration-dx-optimizer (agent) |
adjacent | Developer Experience specialist. Improves tooling, setup, and workflows. Use PROACTIVELY when setting up new projects, after team feedback, or when development friction is noticed. | source |
Source: a5c-ai/babysitter
- Repository: https://github.com/a5c-ai/babysitter (commit
44a5d58b, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
learning-needs-analysis |
core | Conduct comprehensive learner audience analysis, identify performance gaps, and determine instructional requirements using surveys, interviews, and data analysis | source |
media-training-simulation |
core | Media interview preparation and crisis simulation tools for executive readiness and spokesperson development | source |
translation-management |
core | Integration with translation management systems and i18n workflows. Connect with Crowdin, Transifex, Weblate, manage translation memory, synchronize glossaries, and automate localization pipelines. | source |
ats-integration |
core | Integration with Applicant Tracking Systems and automated recruitment workflow management | source |
context-engineering |
core | Context window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200k tokens. Provides warnings at thresholds, context-aware summarization triggers, and wave-level budget planning. | source |
opex-program-designer |
core | Operational Excellence program design skill with governance structure, methodology deployment, and capability building | source |
Competitive Intelligence |
core | Deep competitive analysis and market monitoring capabilities for product strategy | source |
exit-analysis |
core | Analyze exit interview data and identify retention insights and patterns | source |
Source: aaron-he-zhu/aaron-marketing-skills
- Repository: https://github.com/aaron-he-zhu/aaron-marketing-skills (commit
b7b0b9f, retrieved 2026-07-14) - License: Apache-2.0
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
memory-management |
core | Use when the user asks to "remember project context", review saved findings, initialize runtime memory, archive stale work, reconcile notes, or erase a subject; manages authorized HOT/WARM/COLD working memory across all disciplines while … | source |
advocacy-program-designer |
core | Use when the user asks to "design an employee advocacy program", "set up founder-led sharing", or "build a share kit for the team"; produces an advocacy program blueprint in two modes — participation-driven opt-in (default) or top-down … | source |
Source: affaan-m/everything-claude-code
- Repository: https://github.com/affaan-m/everything-claude-code (commit
ed38744, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
agentic-os |
core | Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. | source |
Source: alirezarezvani/claude-skills
- Repository: https://github.com/alirezarezvani/claude-skills (commit
0241f43, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
ceo-advisor |
core | Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Use when planning strategy, preparing board presentations, managing investors, developing organizational culture, making … | source |
founder-coach |
core | Personal leadership development for founders and first-time CEOs. Covers founder archetype identification, delegation frameworks, energy management, CEO calendar audits, leadership style evolution, blind spot identification, imposter … | source |
process-mapper |
core | Use when a BizOps lead, COO, or process-improvement owner needs to document an end-to-end business process (procurement, employee onboarding, incident handoff, customer-onboarding, claims adjudication) in BPMN-style notation, measure cycle … | source |
business-investment-advisor |
core | Business investment analysis and capital allocation advisor. Use when evaluating whether to invest in equipment, real estate, a new business, hiring, technology, or any capital expenditure. Also use for ROI calculations, IRR, NPV, payback … | source |
marketing-strategy-pmm |
core | Product marketing skill for positioning, GTM strategy, competitive intelligence, and product launches. Use when the user asks about product positioning, go-to-market planning, competitive analysis, target audience definition, ICP … | source |
Source: basicmachines-co/basic-memory
- Repository: https://github.com/basicmachines-co/basic-memory (commit
53da71c, retrieved 2026-07-14) - License: custom (see upstream LICENSE)
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
memory-tasks |
core | Task management via Basic Memory schemas: create, track, and resume structured tasks that survive context compaction. Uses BM's schema system for uniform notes queryable through the knowledge graph. | source |
Source: browser-act/skills
- Repository: https://github.com/browser-act/skills (commit
51daea1, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
youtube-transcript-analysis-api-skill |
core | This skill helps users extract YouTube video transcripts and perform deep competitive analysis on the content. Agent should proactively apply this skill when users express needs like analyze YouTube video content strategy, perform … | source |
amazon-listing-competitor-analysis-skill |
core | This skill helps users analyze Amazon competitor listings by ASIN and produce structured competitive intelligence plus strategic opportunity points for their own go-to-market. The Agent should proactively apply this skill when users want … | source |
amazon-competitor-analyzer |
core | Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities. | source |
Source: brycewang-stanford/Auto-Empirical-Research-Skills
- Repository: https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills (commit
85bf545, retrieved 2026-07-14) - License: CC-BY-4.0
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
business-skills |
core | 5 business research skills. Trigger: business strategy, market analysis, competitive intelligence. Design: analytical frameworks and methods for management and innovation research. | source |
hud |
core | Diverga HUD (Heads-Up Display) management skill. Configure and manage the research project statusline display. Supports multiple presets: research, checkpoint, memory, minimal. Triggers: "hud", "statusline", "display settings | source |
Source: davepoon/buildwithclaude
- Repository: https://github.com/davepoon/buildwithclaude (commit
3c94e0c, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
outlook-calendar-automation |
core | Automate Outlook Calendar tasks via Rube MCP (Composio): create events, manage attendees, find meeting times, and handle invitations. Always search tools first for current schemas. | source |
Source: davila7/claude-code-templates
- Repository: https://github.com/davila7/claude-code-templates (commit
fa79251, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
google-cloud-onboarding |
core | Guides developers through their first steps on Google Cloud, covering account creation, billing setup, project management, CLI installation, and deploying a first resource. | source |
product-strategist |
core | Strategic product leadership toolkit for Head of Product including OKR cascade generation, market analysis, vision setting, and team scaling. Use for strategic planning, goal alignment, competitive analysis, and organizational design. | source |
agent-memory-mcp |
core | A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions). | source |
claude-code-sessions |
core | Search, analyze, and manage Claude Code session history. Use when the user wants to find past sessions, check token usage, review tool breakdowns, resume previous work, or manage tasks across sessions. Provides 11 skills and a web … | source |
code-review-excellence |
core | Transform code reviews from gatekeeping to knowledge sharing through constructive feedback, systematic analysis, and collaborative improvement. | source |
Source: Ericyoung-183/alpha-insights
- Repository: https://github.com/Ericyoung-183/alpha-insights (commit
30c1e87, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
alpha-insights |
core | Business Analyst Skill. Triggered when users ask about business analysis, industry research, competitive analysis, product analysis, business model analysis, business opportunity discovery, market entry strategy, investment decisions, … | source |
Source: ferdinandobons/startup-skill
- Repository: https://github.com/ferdinandobons/startup-skill (commit
a5f97c3, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
startup-design |
core | Design, validate, and plan a startup from scratch. Covers market research, competitive analysis, business model, brand identity, product definition, financial projections, and validation experiments. Trigger when the user has a startup … | source |
Source: gooseworks-ai/goose-skills
- Repository: https://github.com/gooseworks-ai/goose-skills (commit
94ec916, retrieved 2026-07-14) - License: no explicit license — referenced by link only
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
job-scraper |
core | Search for job postings across LinkedIn and Indeed. Use when users want to find open roles, monitor hiring signals, identify companies hiring for specific positions, or research competitor hiring activity. Returns job title, company, … | source |
company-current-gtm-analysis |
core | Comprehensive GTM analysis of any target company. Researches what a company is currently doing across all go-to-market dimensions — content/blog, founder LinkedIn activity, SEO/traffic, hiring signals, social/community presence, customer … | source |
Source: HeshamFS/materials-simulation-skills
- Repository: https://github.com/HeshamFS/materials-simulation-skills (commit
fa1ce8d, retrieved 2026-07-14) - License: Apache-2.0
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
performance-profiling |
core | Identify computational bottlenecks, analyze parallel scaling, estimate memory requirements, and generate optimization recommendations for materials simulations — parse timing logs to find dominant phases (solver, assembly, I/O), evaluate … | source |
Source: jeremylongshore/claude-code-plugins-plus-skills
- Repository: https://github.com/jeremylongshore/claude-code-plugins-plus-skills (commit
e112938a, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
windsurf-cascade-context |
core | Manage Cascade context window and memory for complex projects. Activate when users mention "cascade context", "ai memory", "context management", "large codebase navigation", or "multi-session development". Handles context optimization and … | source |
cursor-team-setup |
core | Set up Cursor for teams: plan selection, member management, shared rules, admin dashboard, and onboarding. Triggers on "cursor team", "cursor organization", "cursor business", "cursor enterprise setup", "cursor admin". | source |
buzz-community |
core | Build and manage open source community — Discord/Slack structure, contributor onboarding, ambassador program, community flywheel design, and GitHub community health. Use when asked to "build a community", "grow our Discord", "improve … | source |
apify-cost-tuning |
core | Optimize Apify platform costs through memory tuning, compute unit management, and proxy budgeting. Use when analyzing Apify billing, reducing Actor run costs, or implementing usage monitoring and budget alerts. Trigger: "apify cost", … | source |
competitor-analyst |
core | Competitive analysis and market positioning partner for Product Managers. Use when the user needs to analyze competitors, map market positioning, identify feature gaps, or prepare for competitive conversations. Triggers include … | source |
nda-generator |
core | Generates custom non-disclosure agreements with plain English annotations. Use when creating an NDA for business discussions, hiring, vendor relationships, or partnerships. Supports mutual, one-way, employee, and vendor variants. Trigger … | source |
crest-narrative |
core | Strategic narrative — write a standalone strategy memo that frames product direction, bets, and rationale for a planning horizon. Use when asked to "write a strategy doc", "product vision", "strategic narrative", "company strategy memo", … | source |
profiling-application-performance |
core | Execute this skill enables AI assistant to profile application performance, analyzing cpu usage, memory consumption, and execution time. it is triggered when the user requests performance analysis, bottleneck identification, or … | source |
Source: mohitagw15856/pm-claude-skills
- Repository: https://github.com/mohitagw15856/pm-claude-skills (commit
876fa30, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
roi-estimator |
core | Estimate the ROI, payback, and NPV of an investment, project, or purchase. Use when asked to calculate ROI, build a business case, justify a purchase/initiative, work out payback period, or compare options by return. Produces a computed … | source |
customer-success-plan |
core | Build a joint customer success plan for a specific account. Use when asked to create a success plan, joint success plan, mutual action plan, or customer onboarding plan. Produces a structured success plan with business goals, milestones, … | source |
go-to-market-planner |
core | Build a go-to-market plan for any product launch, feature release, or new market entry. Use when planning a product launch, writing a GTM strategy, defining launch tiers, or coordinating cross-functional launch activities. Produces a … | source |
Source: mukul975/Anthropic-Cybersecurity-Skills
- Repository: https://github.com/mukul975/Anthropic-Cybersecurity-Skills (commit
673da1f, retrieved 2026-07-14) - License: Apache-2.0
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
analyzing-macro-malware-in-office-documents |
core | Analyzes malicious VBA macros embedded in Microsoft Office documents (Word, Excel, PowerPoint) to identify download cradles, payload execution, persistence mechanisms, and anti-analysis techniques. Uses olevba, oledump, and VBA … | source |
analyzing-linux-kernel-rootkits |
core | Detect kernel-level rootkits in Linux memory dumps using Volatility3 linux plugins (check_syscall, lsmod, hidden_modules), rkhunter system scanning, and /proc vs /sys discrepancy analysis to identify hooked syscalls, hidden kernel modules, … | source |
Source: nexscope-ai/eCommerce-Skills
- Repository: https://github.com/nexscope-ai/eCommerce-Skills (commit
56f3288, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
tiktok-shop-affiliate-program |
core | TikTok Shop affiliate program strategy and creator collaboration. Commission structures, creator recruitment, sample management, performance tracking, and partnership optimization. Use when the user asks about TikTok Shop affiliates, … | source |
ecommerce-business-plan |
core | Create a comprehensive e-commerce business plan. Market analysis, financial projections, marketing strategy, operations planning, and milestone roadmap for new or growing e-commerce businesses. | source |
tiktok-shop-content-strategy |
core | TikTok Shop content creation strategy and planning. Trending formats, viral hooks, product showcasing, hashtag strategy, and content calendar development. Use when the user asks about TikTok content strategy, viral content creation, TikTok … | source |
price-optimization-tool |
core | Evaluate ecommerce price candidates using unit economics, historical observations, elasticity analysis, scenario modeling, and controlled experiments. Use when a seller asks what price to test, how price changes could affect contribution … | source |
Source: nextlevelbuilder/ui-ux-pro-max-skill
- Repository: https://github.com/nextlevelbuilder/ui-ux-pro-max-skill (commit
fe3f65e, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
design |
core | Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, … | source |
Source: nexu-io/open-design
- Repository: https://github.com/nexu-io/open-design (commit
4b66023, retrieved 2026-07-14) - License: Apache-2.0
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
html-ppt-zhangzara-daisy-days |
core | A customer-success workshop onboarding users to a project-management app — the first-value path and the habits that retain. Built as a decision-grade professional training deck for new customers, CS team. | source |
html-ppt-graphify-dark-graph |
core | Open Design's feature business case for the plugin marketplace: the user pain, options, tradeoffs, and the measure of success. Built as a decision-grade product management deck for PM, eng, design, leadership. | source |
ib-pitch-book |
core | Open Design's investor pitch book: market map, moat, unit economics, and the ask — analyst-grade and diligence-ready. Built as a decision-grade fundraising pitch deck for growth-equity investors. | source |
Source: Orchestra-Research/AI-research-SKILLs
- Repository: https://github.com/Orchestra-Research/AI-research-SKILLs (commit
773a529, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
pytorch-fsdp2 |
core | Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with … | source |
Source: parcadei/Continuous-Claude-v3
- Repository: https://github.com/parcadei/Continuous-Claude-v3 (commit
d07ff4b, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
remember |
core | Store a learning, pattern, or decision in the memory system for future recall | source |
Source: rampstackco/claude-skills
- Repository: https://github.com/rampstackco/claude-skills (commit
bc6d961, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
ux-research |
core | Plan and execute user research including research planning, recruiting, interview design, qualitative synthesis, and translating findings into product decisions. Use this skill whenever the user wants to plan user research, design … | source |
Source: rsmdt/the-startup
- Repository: https://github.com/rsmdt/the-startup (commit
ff6a0be, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
user-research |
core | User research and insight synthesis for interviews, usability testing, personas, journey mapping, and actionable product/design recommendations. Use when planning studies, collecting evidence, synthesizing patterns, or converting findings … | source |
Source: ruvnet/claude-code-flow
- Repository: https://github.com/ruvnet/claude-code-flow (commit
73914bd, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
Hooks Automation |
core | Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre$post task hooks, session management, Git integration, memory coordination, and neural pattern training … | source |
AgentDB Memory Patterns |
core | Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants. | source |
memory-management |
core | AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, … | source |
Source: ruvnet/ruflo
- Repository: https://github.com/ruvnet/ruflo (commit
73914bd, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
Hooks Automation |
core | Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre$post task hooks, session management, Git integration, memory coordination, and neural pattern training … | source |
AgentDB Memory Patterns |
core | Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants. | source |
memory-management |
core | AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, … | source |
Source: serejaris/personal-corp-os
- Repository: https://github.com/serejaris/personal-corp-os (commit
9d3660e, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
ceo-council |
core | Use when needing strategic project analysis from multiple independent expert perspectives. Triggers on business decisions, growth strategy, product direction, competitive analysis, or any situation where diverse C-level opinions reduce … | source |
Source: serejaris/personal-corp-skills
- Repository: https://github.com/serejaris/personal-corp-skills (commit
b517d36, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
ceo-council |
core | Use when needing strategic project analysis from multiple independent expert perspectives. Triggers on business decisions, growth strategy, product direction, competitive analysis, or any situation where diverse C-level opinions reduce … | source |
Source: ThinkInAIXYZ/deepchat
- Repository: https://github.com/ThinkInAIXYZ/deepchat (commit
f275c92, retrieved 2026-07-14) - License: Apache-2.0
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
memory-management |
core | Guide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape. | source |
Source: vibeeval/vibecosystem
- Repository: https://github.com/vibeeval/vibecosystem (commit
cea9462, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
remember |
core | Store a learning, pattern, or decision in the memory system for future recall. | source |
prd-writer |
core | Product Requirements Document writing - PRD templates, MoSCoW prioritization, user personas, competitive analysis, feature specs, acceptance criteria, risk assessment | source |
Source: wanshuiyin/Auto-claude-code-research-in-sleep
- Repository: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep (commit
eb5c9d7, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
system-profile |
core | Profile a target (script, process, GPU, memory, interconnect) for performance analysis. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis. | source |
Source: zechenzhangAGI/AI-research-SKILLs
- Repository: https://github.com/zechenzhangAGI/AI-research-SKILLs (commit
773a529, retrieved 2026-07-14) - License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
pytorch-fsdp2 |
core | Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with … | source |