Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 870 files from 1 769 authors, of which 62 217 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Expert Teaching Assistant with deep knowledge of classroom management, differentiated instruction, student assessment, learning objective design, and educational technology integration
Expert Teaching Secretary with 10+ years managing academic scheduling, student records, examination administration, and faculty coordination. Specializes in academic calendar management, enrollment processing, and institutional compliance. Use when: education, scheduling, academic-records, administration, coordination.
Expert Test Prep Instructor specializing in SAT, ACT, GRE, GMAT, LSAT, and professional certification exam preparation. Expert in test-taking strategies, content review, performance analytics, and score improvement methodologies. Use when: test-prep, sat, act, gre, gmat, lsat, exam-prep, test-strategies, score-improvement.
Expert Training Class Advisor with 10+ years managing K12 and adult training classes. Specializes in student progress tracking, parent communication, classroom management, and student psychological development
Expert Training Manager specializing in corporate learning, talent development, training program design, and organizational capability building. Expert in needs assessment, training delivery, learning technologies, and measuring training effectiveness. Use when: training-management, corporate-learning, talent-development, training-design, organizational-development, learning-and-development.
Expert Training Marketing specialist with 10+ years driving enrollment for K12 tutoring, professional certification, and skill training programs. Specializes in digital marketing, conversion optimization, and education brand building. Use when: education, marketing, lead-generation, brand-promotion, enrollment.
Expert Training School Principal with deep knowledge of educational operations, business development, instructor management, curriculum oversight, and regulatory compliance for private training institutions
Expert-level Subject Tutor with deep knowledge of K-12 and higher education pedagogy, differentiated instruction, assessment design, learning psychology, and exam preparation strategies
Expert Tutoring Center Manager specializing in educational business operations, tutor recruitment and training, student enrollment, and quality assurance. Expert in curriculum delivery, customer service, and learning outcome optimization. Use when: tutoring-center, education-business, tutor-management, student-enrollment, learning-outcomes, educational-operations.
Expert University Administrator with deep knowledge of higher education policy, accreditation, enrollment management, financial aid, academic affairs, and institutional compliance
Expert Vocational Trainer with deep knowledge of competency-based education, industry certifications, workforce development, and career coaching
Battery engineer specializing in electrochemistry, cell design, battery management systems, and energy storage system integration.
A distinguished university professor specializing in higher education pedagogy, research methodology, academic writing, grant development, and doctoral supervision. Expert in evidence-based teaching, scholarly publication, and academic leadership. Use when: higher-education, university-teaching, research, academic-writing, grant-proposals, doctoral-supervision.
Senior battery R&D engineer specializing in lithium-ion cell development, electrochemistry, and next-generation energy storage
Senior carbon management consultant specializing in emissions accounting, carbon trading strategies, CCUS project development, and decarbonization roadmaps
A world-class energy storage system engineer specializing in grid-scale storage, battery management systems, and safety-critical energy infrastructure
Senior gas engineer specializing in natural gas distribution system design, pipeline engineering, pressure regulation, and gas safety
Senior hydrogen fuel cell engineer specializing in PEMFC stack design, membrane electrode assembly development, and hydrogen system integration
Power grid engineer specializing in electrical power systems, transmission planning, grid modernization, and integration of renewable energy sources.
Petroleum engineer specializing in reservoir engineering, drilling operations, production optimization, and enhanced oil recovery for oil and gas development.
Expert-level Nuclear Operator skill with deep knowledge of reactor operations, nuclear safety protocols, radiation protection standards, emergency response procedures, and regulatory compliance
Senior power system engineer specializing in electrical grid design, renewable energy integration, and grid modernization. Use when designing transmission networks, analyzing grid stability, sizing transformers, or developing interconnection studies. Use when: power-grid, electrical-engineering, renewable-integration, grid-stability, smart-grid.
Solar energy engineer specializing in photovoltaic system design, solar farm development, and grid integration for utility-scale renewable energy projects.
A world-class solid-state battery engineer specializing in next-generation all-solid-state batteries. Use when designing solid-state cells, selecting electrolytes, solving interface problems, or developing solid-state battery manufacturing processes. Use when: solid-state-battery, solid-electrolyte, lithium-metal, battery-rd, electrochemistry.
Expert-level Virtual Power Plant (VPP) Operator skill with deep knowledge of distributed energy resource aggregation, demand response programs, wholesale power markets, grid integration, and advanced energy management systems. Use when: virtual-power-plant, distributed-energy, demand-response, energy-trading, aggregator.
Expert-level Water Treatment Engineer skill with deep knowledge of water purification, wastewater treatment, desalination, membrane technology, chemical treatment, and environmental compliance
Expert skill for AbbVie Enterprise Intelligence
Wind energy engineer specializing in wind turbine design, wind farm development, and power curve optimization for onshore and offshore wind projects.
Adidas sportswear and lifestyle expert specializing in Three Stripes brand strategy, product innovation, sustainability initiatives, DTC transformation, and retail excellence. Use when: analyzing sportswear market positioning, developing product strategies, optimizing retail operations, or implementing sustainability frameworks in apparel.
Expert skill for Adobe
Use when emulating Airbnb's engineering methodology for two-sided marketplace design. Implements design-led development with host-guest marketplace optimization, trust & safety systems, and pricing algorithms. Triggers: "Airbnb style", "belong anywhere", "marketplace matching", "host-guest optimization".
Expert skill for Airbus
DEPRECATED: Use /skills/enterprise/alibaba/SKILL.md instead. This file is kept for backward compatibility.
> AI creative director with recursive self-assessment. Generates concepts using world-class methodologies (SIT, TRIZ, Lateral Thinking, bisociation), scores against 6 weighted criteria with Cannes/D&AD/HumanKind calibration, and recursively refines until the 9+ threshold is reached. Accepts briefs in any format — text, voice transcript, PDF, or raw notes. Use when the user asks to generate creative concepts, brainstorm campaign ideas, develop a Big Idea or campaign platform, evaluate or critique existing creative work, find consumer insights, or shares a brief for ideation — including activations, PR-stunts, brand utility, experiential, and non-advertising ideas. Calibrates against a library of 569 legendary campaigns (P01-P18 pattern map) to detect saturation and ensure originality. Do not use for media planning, production budgeting, brand identity/logo design, copywriting final drafts, or market research data collection.
> Autonomous GDPR compliance auditor that scans a codebase to identify PII collection, storage, and sharing, then produces an article-by-article gap analysis, a pre-filled Data Processing Agreement (DPA), and a ROPA (Record of Processing Activities) starter kit — all exported as downloadable files (.docx recommended). Use this skill whenever the user mentions GDPR, data privacy audit, DPA, ROPA, EU compliance, PII scan, data protection, ICO, CNIL, or asks whether their codebase or product is compliant with data protection law. Trigger even for casual phrasings like "are we GDPR compliant?", "I need to check our data privacy", or "help me get audit-ready." The skill runs autonomously — it reads the codebase, researches third-party processors, and produces final deliverables without the user needing to provide structured input.
> Proactive PII add-on — augments the main response with PII guidance. Auto-trigger on any form, schema, migration, model, API route, GraphQL webhooks, workers, seed/fixture/factory files, delete/export/purge/anonymize functions, cron jobs, HTTP clients, controllers, services, resolvers. I include", "how should I design the schema", "POC / lead / contact / user / customer information", "store / save / persist X", "sign up / login / auth / registration", "share thoughts on how to build". token, secret, api_key, health, biometric, ip_address, salary, session, device_id, notes, metadata (on user-facing models).
Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP server. Cloud-only — connects to the hosted service, not a local ComfyUI install. Use for any "generate/edit an image", "make a video", "text to 3D", or ComfyUI workflow task.
Use when the user is addressing pull request review comments locally and asks for help evaluating, implementing, or drafting responses to reviewer feedback - requires technical rigor and verification, not performative agreement or blind implementation
Use this skill when categorizing code review findings into severity levels. Apply when determining which emoji and label to use for PR comments, deciding if an issue should be flagged at all, or classifying findings as CRITICAL, IMPORTANT, DEBT, SUGGESTED, or QUESTION.
Use when the user provides a single Jira issue key and asks whether it is still relevant, still applicable, still pending, still a bug, has been fixed, or can be closed. Trigger phrases include "Is [TICKET] still relevant?", "Is this still an issue?", "Is PM-123 still pending?", "Has this been fixed?", "Can we close this?", "Is this ticket still valid?", "Is this still applicable?", "Does this bug still exist?". Fetches the ticket and verifies the described problem against the current codebase to return a verdict with evidence. This skill assesses a single ticket at a time; invoke it iteratively for multiple tickets.
Use this skill when posting inline comments to GitHub pull requests. Apply when formatting comments following Bitwarden engineering standards with severity emojis, clear explanations, and actionable suggestions. Use after findings are classified and ready to post. DO NOT USE when posting summary comments.
Perform a rigorous, multi-agent code review with architecture-compliance, parallel quality/security analysis, finding validation, and severity audit. Use when the user asks for a structured, deep, thorough, multi-pass, or multi-agent code review — or a review that includes architecture/pattern compliance, confidence-scored findings, or a severity audit. Use when the user asks for a code review across a commit range, time window, or N most recent commits in a locally checked-out repo.
Use this skill when posting the final summary comment after all inline comments are posted. Apply as the LAST step of code review after all findings are classified and inline comments are complete. Detects context (agent mode sticky comment, GitHub Actions MCP tool, or local file) and routes output accordingly.
Use this skill to validate findings during a code review. For each finding, run the rejection criteria and verification checks. If a finding fails any check, drop it.
Use whenever the user mentions a Jira issue key and wants more than a surface-level lookup — "Read PROJ-123", "What's PROJ-123 about?", "Give me context on PROJ-123", "Deep dive PROJ-123", "What's blocking PROJ-123?", "Summarize PROJ-123 and its dependencies", "I need to work on PROJ-123, what should I know?", or any request to understand an issue's purpose, scope, or requirements. Thoroughly researches and synthesizes a Jira issue including all linked issues, sub-tasks, blocked dependencies, and supporting Confluence documentation.
Use this skill when a PR diff contains changes to dependency manifest files (package.json, .csproj, Cargo.toml, go.mod, requirements.txt, etc.) or when reviewing Renovate/Dependabot bot PRs. Evaluates new dependencies for AppSec approval process compliance, major version bump significance, lock file hygiene, and dependency removal completeness. Does NOT perform deep security or license analysis — that is handled by the bitwarden-security-engineer plugin's reviewing-dependencies skill.
Architecting solutions at the team level while staying coherent with Bitwarden's holistic architecture. Covers security mindset, architectural judgment, Bitwarden-specific constraints, and working with the architecture group. Use when designing or planning a solution, reviewing architecture within a team's scope, assessing change impact, evaluating trade-offs in different implementations, or deciding whether a choice needs architecture group input.
Decompose a breakdown Plan into a tasks.md document with one entry per future Jira work item. Also handles resumption against a partly-drafted task list. Triggers: "decompose into tasks", "draft the tasks section", "break this into stories", "split into Jira tickets", "fill in the tasks table", "continue task decomposition".
Git commit conventions and workflow for Bitwarden repositories. Use when committing code, writing commit messages, or preparing changes for commit. Triggered by "commit", "git commit", "commit message", "prepare commit", "stage changes".
Open a pull request from a branch in a Bitwarden repository — pick the conventional commit type prefix that drives the t: label, fill in the repo's PR template, choose an ai-review label, and confirm a full submission preview before running gh pr create.
Develop the Plan section of a Bitwarden Tech Breakdown after the Specification is filled — technical architecture, per-layer impact, in-flight collision scan, cross-team impact mapping, and self-review. Supports resumption against a partly-developed Plan. Triggers: "develop the plan", "draft the implementation plan", "map per-layer impact", "scan for in-flight work", "identify cross-team impacts", "continue planning", "plan the breakdown".
Apply one intent across many targets at once — a fleet of repositories across the Bitwarden ecosystem, or many projects inside a monorepo — as N consistent, idempotent, reviewable draft PRs.
Resolve open design questions, then capture what's being built into the Specification section of a Bitwarden Tech Breakdown. Use after a breakdown document has been created in its empty state or resuming a partly-resolved specification. Triggered by phrasings such as "understand the work", "define breakdown scope", "write the breakdown spec", "develop the specification", "continue the breakdown spec".
Conventional commit type keywords for PR titles and commit messages. Use when determining the change type for commits or PRs. Triggered by "what type", "label", "change type", "conventional commit", "t: label".
Quality gate checklist to run before committing or creating a PR. Use when finishing implementation, checking work quality, or preparing to commit. Triggered by "preflight", "self review", "ready to commit", "check my work", "quality gate".
Phase-by-phase guidance for participating in Bitwarden's Software Initiative Funnel. Covers ownership boundaries between shepherd and tech lead at each phase, how to run an epic breakdown after handoff, sizing and estimation, cross-team dependency tracking, and the escalation paths that protect team autonomy. Use when a team is about to receive an initiative epic, when participating in an Architectural Assessment or PoC, when preparing a team breakdown, or when surfacing concerns back to the shepherd or engineering leadership.
Apply Bitwarden brand standards — logo usage, color palette, typography, iconography, and capitalization rules — grounded in bitwarden.com/brand and the bitwarden/brand repository.
Six-phase playbook for running ownership transitions in either direction — receiving work from another team (initiative handoffs from shepherds, frameworks from Platform, operational responsibilities from SRE), or originating a transition (handing off a built framework, transitioning a shepherded initiative, or moving operational responsibilities). Applies Bitwarden's Work Transition Playbook from whichever side a team is on. Use when a team is about to take on or hand off transferred work, when preparing materials or sessions, when the support period is underway, or when running a pulse check or retrospective on a handoff.
Sets up a new Bitwarden Tech Breakdown in the bitwarden/tech-breakdowns repo. Creates a per-breakdown folder (`<team>/<JIRA-KEY>-<short-slug>/`) containing `breakdown.md` from the template, so the future `tasks.md` and any specification artifacts can live alongside it. Use when a team is creating a new breakdown — triggered by phrasings such as "start a tech breakdown", "create a new breakdown for X", "set up the breakdown file", "spin up a breakdown".
Bitwarden's product content style guide for end-user-facing GUI copy — voice, tone, AP-style-with-exceptions grammar, sentence case in UI, and accessibility-first language at a U.S. 7th-grade reading level.
Claude Skills — questions
Answers built from the skills we actually parsed.