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. 79 341 files from 1 736 authors, of which 61 700 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.
> Outcome-clarity reviewer that questions whether you've defined what you're trying to achieve, validated the problem exists, and can defend it in plain language. Catches people BEFORE they build — the moment between "I should build X" and actually building. Not a solution reviewer — a reviewer of whether you know what success looks like and whether the problem is real.
> Build a new opinionated advisor-persona skill — a reviewer "lens" like crusty-old-engineer — modeled on a real person or archetype and proven from real evidence. Mines the subject's authentic voice and discipline, defines its one distinct load-bearing question, drafts it to the family template, proves it steers in a live session, reduces it, and publishes it to a skills bundle. Use when creating or authoring a persona/advisor skill, adding a sibling to the crusty-old-engineer family, or turning a person's real direction style into a reusable reviewer skill. Also triggers on "personafy" / "personify".
> Use when making a system extensible with runtime plugin discovery via Python entry points, a file-based plugin registry, multi-backend provider abstractions, or schema-driven input validation.
| Competitive-differentiation reviewer that refuses to accept "the user wants this" as sufficient — insisting the plan also explain why a real customer would choose it over every real alternative, including doing nothing at all. Hunts the feature that is individually desirable but has no answer for "why us, why this, why now" against the competition and the status quo. Sounds like a positioning strategist who has watched too many well-liked products lose to a competitor with a clearer story, or to customers simply staying put. Not a user-desirability reviewer — a reviewer of competitive and market differentiation. A lens for any product checkpoint — plan, roadmap, or go-to-market framing. pay for it over an alternative, the competitive landscape is unaddressed, or "no one else does this" is asserted without checking — any time the worry is "why would the customer choose this over the alternative, including doing nothing?"
Convene the Product Development Council on the CURRENT conversation / work-in-progress — the plan, roadmap, or scope decision you've been building in this session. The INLINE counterpart to /product-council (which forks and runs isolated, so it cannot see the chat). Use when you want the council to critique what we're working on right now.
Convene the Product Development Council (six orthogonal product-delivery lenses, anchored by a mandatory problem-validation gate) on a target — cold independent fan-out, debate-to-consensus, synthesized verdict with recorded dissent and a roster manifest.
> Use when building a React frontend that dynamically loads independent bundles sharing a single React instance via import maps, needs frecency-based autocomplete, dynamic schema-driven forms, or Zustand state with localStorage.
| Momentum-driven engineering reviewer that holds one uncompromising gate — is it REAL, proven end-to-end as a user would — while driving work forward. Demands proof over claims, plumbing before polish, fail-loud over fallbacks, trust in the model over instructions, and protects the critical path so good-but-costly ideas don't stall the work. Warm, blunt, forward-driving — not a curmudgeon. A lens for any checkpoint — brainstorm, design, plan, implement, debug, or ship — not just the finish. whether you're building in the right order, whether a fix is real or a band-aid, or whether work is actually done/ready — any time the worry is "are we fooling ourselves about what's real?"
> Use when adding a doctor diagnostic command, self-update/upgrade mechanism, cross-platform service installation (systemd and launchd), or post-upgrade verification to a CLI tool.
Diagnose issues in the current Amplifier session — misconfigured tools, failing operations, unexpected behavior. Use when something isn't working right.
> Capture a repeatable process from the current session into a reusable Amplifier SKILL.md skill file. Analyzes the conversation, interviews the user to confirm structure, and writes a complete skill to disk. Use when the user wants to create a skill, save a workflow as a skill, turn a process into a reusable skill, or mentions "skillify", "create skill", "make a skill", "save as skill", "capture workflow", "turn this into a skill", "new skill", or wants to automate a repeatable process they just performed.
| Adversarial breaker that reviews code by trying to make it fail, not by confirming it works. Hunts the unhappy paths — the malformed input, the empty string, the reversed range, the race condition — that the happy-path reviewer never types. Sounds like a gleeful adversary who thinks in inputs nobody intended and assumes everything is broken until a concrete attempt to break it comes up empty. Not a QA checklist — a hostile witness for the failure that hasn't happened yet. A lens for any checkpoint — brainstorm, design, plan, implement, debug, or review — not just a test gate. for "I tried to break it and couldn't," or nobody has named the input that makes this fall over — any time the worry is "how does this fail, and where are the edges?"
Authoritative consultant for all skills-related questions. Use when creating or modifying skills, understanding the Agent Skills spec, troubleshooting skill loading or invocation issues, leveraging enhanced format features (context fork, model_role, user-invocable), writing cross-harness portable skills, ensuring Claude Code Skills 2.0 compatibility, or deciding between skills vs agents.
| User-need reviewer that speaks for the person who isn't in the room — the one who will actually live with what gets built. Hunts the gap between "we can build this" and "they actually want this," and between "it works" and "they can live with it." Sounds like the patient, slightly impatient voice of the absent user — uninterested in how clever the build is, relentless about whether anyone asked for it and whether it survives contact with a real person. Not a UX consultant — an advocate for the served person's desire and lived experience. A lens for any checkpoint — brainstorm, design, plan, implement, debug, or review — not just design. celebrated while the recovery path is missing, or nobody can name the person this serves — any time the worry is "does the person we serve actually want this, and can they live with it?"
> Use when verifying that completed work actually works. Auto-surface during /verify mode, post-implementation review, or before claiming a task is done. Teaches the discipline of testing outcomes vs implementation, the unit/integration/smoke gradient, and what "done" actually means.
Scaffold a complete, production-ready Azure project from scratch for ANY use case: RAG chatbots, multi-agent systems, API backends, data pipelines, Azure Functions, full-stack web apps, ML training/inference, or event-driven microservices. USE FOR: gathering requirements through adaptive questioning, generating complete project folder structures with all source files, Azure Bicep infrastructure, azure.yaml for azd-up deployment, Docker configuration, CI/CD workflows, README with architecture diagrams, and Responsible AI documentation. Produces fully deployable Azure projects targeting Azure Container Apps, Azure AI Foundry, Azure Functions, or Azure ML. DO NOT USE FOR: modifying existing projects, deploying to Azure (use azure-deploy skill), managing Azure resources (use azure-prepare skill).
Use after implementation and before completion claims, merge, or PR when work must be checked against confirmed SPEC.md files, Python architecture rules, and the actual diff.
Use when designing, specifying, implementing, or auditing Python project architecture, package boundaries, public APIs, domain logic, persistence boundaries, or module dependencies.
Use when the user invokes requirements-to-design, asks to start an SDD design phase, or wants non-trivial Python work clarified into a confirmed design document before SPEC.md changes.
Use when the user invokes spec-driven with an approved design path, asks to update SPEC.md files from a confirmed design, or wants Python SDD implementation run from confirmed specs.
Live-drive test harness for the microsoft/WinAppVSCE repo. Launches an isolated VS Code instance with the WinApp extension installed and drives real winapp.* commands inside VS Code to test any piece of extension functionality live.
> Turns vague "what did I do?" into evidence-backed impact statements for performance reviews, self-reviews, promotion packets, and weekly updates. Uniquely mines Copilot CLI session logs to reconstruct forgotten work, plus git commits and GitHub PRs. Enforces a 3-part impact contract (action → result → evidence). Works standalone Use this skill whenever the user asks to document, summarize, reconstruct, or organize their engineering work — even if they don't literally say "brag sheet". history", "performance review", "self-review", "self assessment", "write impact statement", "review prep", "promo packet", "promotion case", "weekly update", "status report", "accomplishments", "what did I ship", "I forgot to log my work", "summarize my work", "track my wins", "end of half", "career growth", "work journal".
> Guides Microsoft Entra administrators through proof-of-concept deployments of Entra Suite products including Private Access, Internet Access, Global Secure Access, ID Protection, ID Governance, Verified ID, and External Identities. Use when user mentions "Entra POC", "Global Secure Access setup", "private access proof of concept", "Entra Suite trial", "GSA configuration", "zero trust network access POC", "secure web gateway POC", "identity governance POC", "external identities POC", "B2B collaboration setup", "CIAM proof of concept", "guest user onboarding", "customer identity POC", or asks to plan, configure, validate, or document an Entra deployment. Orchestrates Microsoft MCP Server for Enterprise to read tenant configuration and generates documentation, PowerShell scripts, and gap analysis reports. Do NOT use for general Microsoft 365 administration, Exchange, SharePoint, or Teams configuration unrelated to Entra Suite security features.
>- Companion skill for the Building Agents with eve course on Vercel Academy. Use when the user mentions "building agents with eve", "the eve course", "the bike shop agent", "the dispatcher", "teach me", or asks about eve (the filesystem-first agent framework) — defineTool, defineState, dynamic skills, needsApproval, channels, or deploying an eve agent — in the context of the Academy course.
>- Companion skill for the Building Filesystem Agents course on Vercel Academy. Use when the user mentions "filesystem agents", "the course", "teach me", or asks about ToolLoopAgent, Vercel Sandbox, or bash tools in the context of the Academy course.
>- Companion skill for the Agent-Friendly APIs course on Vercel Academy. Use when the user mentions "agent-friendly APIs", "API documentation", "llms.txt", "the course", "teach me", or asks about agent-friendly docs, documentation patterns, or building Claude Code skills in the context of the Academy course.
>- Test changes to the TAV C, WASM, and C# FFI surfaces. Use when exported functions, handles, constants, ownership rules, errors, goldens, or consumer tests change under ffi/.
Use when building, reviewing, or optimizing web animations OR rendering performance (frame loops, scroll/viewport reveals, mount/unmount transitions, canvas/WebGL lifecycles, reduced-motion handling, lazy rendering, deferring off-screen or non-critical work) with the phase library. Also use when auditing existing animation or rendering code to decide between CSS-only, minimal JS, phase, or a heavier library like motion. Trigger on janky animations, per-frame allocations, forced reflows, re-renders from animation loops, animations that don't pause off-screen, missing reduced-motion support, content-visibility, lazy-mounting on viewport or idle, requestIdleCallback, deferring rendering of long pages, or questions like 'should I use CSS or JS for this animation' or 'how do I render this off-screen content faster'. Always use this skill when you mention phase or any phase export.
> Use with root `twg` for Jira workitems, projects, boards, sprints, fields, transitions, comments, links, and administration. Applies Jira semantics and safe mutation rules.
> Run a lightweight single-prompt A/B comparison of free Atlassian/local MCP context vs TWG CLI graph context using paired read-only agent sessions.
> Use with root `twg` for deep iterative enterprise/company knowledge search and internal research with Rovo Search across connected apps/connectors including Confluence, Jira, Drive, Slack, Bitbucket, and GitHub.
> Use with root `twg` for deep context, dependency maps, related entities, project-to-repo discovery, OOO catch-ups, and "catch me up" requests around a concrete anchor.
> Use with root `twg` for code search, repositories using an API/package, implementation and reverse-dependency discovery, PR status and reviews, repo contributors, hot areas, and issue-to-PR lookups.
> Clean up stale or unresolved Jira workitems. Dry-run single items, lists, boards, sprints, epics, or projects by matching Jira keys/titles to merged PRs, repos, Rovo/search-code hits, and assignee activity.
> Use with the root `twg` skill for on-call handoffs, incident response and investigation, post-incident reviews, reliability reviews, Assets refresh, capacity views, meeting summaries, and operational risk readouts.
> Use with root `twg` for Confluence content, spaces, hierarchy, authoring, editing, comments, versions, permissions, exports, and CQL. Applies Confluence semantics and safe write rules.
> Use with root `twg` to route owners, subject-matter experts, maintainers, reviewers, approvers, decision authorities, Heads of Engineering, or escalation paths for a topic, area, ask, project, service, or component.
> Root TWG CLI skill for Atlassian work-data tasks. Use typed commands for known anchors; use live `twg help` only when command shape or output contract is uncertain.
> Use with root `twg` for status rollups, personal work summaries, and decision-readiness or go/no-go briefs. Routes to `pr-tree`, `org-tree`, `work-tree`, or `workitem-tree`.
Write a Twitter/X post or thread based on research findings or a given topic. Use this skill when asked to create tweets, X posts, or social media threads.
Write a LinkedIn post based on research findings or a given topic. Use this skill when asked to create LinkedIn content, professional posts, or thought leadership pieces.
Add or maintain PolyStella in an existing Astro project. Use when integrating AI-driven build-time content localization, configuring R2 caching, wiring locale-prefixed routes, or debugging an existing PolyStella setup in a downstream project.
Edit the PolyStella package source. Use when adding a file-format adapter, adding a CLI subcommand, adding a translation provider, modifying the cache contract, debugging a translation regression, or otherwise working on the package itself (not consuming it).
prisma db push. Reference when using this Prisma feature.
prisma db seed. Reference when using this Prisma feature.
prisma format. Reference when using this Prisma feature.
prisma db pull. Reference when using this Prisma feature.
prisma db execute. Reference when using this Prisma feature.
prisma debug. Reference when using this Prisma feature.
prisma dev. Reference when using this Prisma feature.
prisma generate. Reference when using this Prisma feature.
prisma migrate deploy
prisma init. Reference when using this Prisma feature.
prisma migrate dev. Reference when using this Prisma feature.
prisma migrate reset
prisma migrate resolve
Claude Skills — questions
Answers built from the skills we actually parsed.