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.
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG plumbing (that is `building-agents`).
Use when constitution, spec, plan and tasks all exist and you want them cross-read against each other before any code is written — the rsc-sdd pre-implementation gate. Reports coverage gaps, contradictions, duplication, ambiguity and scope drift; edits nothing. NOT the task breakdown (that is `tasks`), NOT the coding (that is `implement`), NOT the post-code test gate (that is `verify`), NOT resolving ambiguity (that is `clarify`).
Use when designing or analyzing a controlled experiment — falsifiable hypothesis, sample size from an MDE, reading significance/CI/power, CUPED, or rescuing tests that won't go significant. NOT recurring metric tracking (that is `analytics`), NOT north-star/KPI trees (that is `kpi-framework`), NOT projecting metrics forward (that is `forecasting`).
Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already did. NOT building the loop, tools, or RAG (that is `building-agents`).
Use when instrumenting product or web analytics — GA4/PostHog SDK wiring, event taxonomy, funnels, double-counted events, consent gating, PII scrubbing. NOT charting that data (that is dashboard), NOT choosing which metrics matter (that is kpi-framework), NOT experiment math (that is ab-testing), NOT cookie-policy text (that is gdpr-privacy).
Use when settling the contract of an API you expose, before implementation: resources/URLs, REST vs GraphQL, versioning, one RFC 9457 error envelope, pagination, idempotency — emitted as OpenAPI 3.1. NOT implementing the endpoints (that is `fastapi`/`nestjs`/`go`/`nodejs`), NOT auth hardening (that is `secure-coding`), NOT consuming a third-party API (that is `api-connector-builder`).
Use when writing a client for someone else's REST or GraphQL API: auth flow choice and token refresh, pagination to exhaustion, retry-with-jitter on transient failures only, rate-limit-aware throttling. NOT inbound callbacks (that is `webhooks`), NOT chaining services (that is `automation-flows`), NOT designing your own API (that is `api-design`).
Use when building a content-driven or marketing site with Astro 6: static-first pages, islands and partial hydration, content collections, server islands, per-route on-demand rendering, deploy adapters, and Astro 5→6 migration. NOT app-router React with server actions and heavy client interactivity (that is `nextjs`).
Use when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into references/, writing its evals, auditing it against the rubric. NOT building a product feature (that is `specify`) and NOT designing an agent loop (that is `building-agents`).
Use when building, refactoring, or debugging Angular (v20/21+): standalone components, signals, zoneless change detection, @if/@for/@defer control flow, inject() DI, resource()/httpResource(), RxJS interop, NgRx SignalStore, ng CLI. NOT React (that is react), NOT Next.js (that is nextjs), NOT a TypeScript language question (that is typescript).
Use when building or fixing a no-code automation on n8n, Make, or Zapier — trigger to multi-app steps with data mapping, dedup, retries and an error path — or picking the platform by billing unit (task vs credit vs execution). NOT a typed API client in code (that is api-connector-builder), NOT a webhook receiver in your own app (that is webhooks).
Use when writing one long-form article end to end — answer-first lede, question-shaped headings, plus its on-page surface (title, meta, slug, FAQ, Article/FAQPage JSON-LD) — or fixing a draft that buries the answer or reads AI-padded. NOT keyword research or topic selection (that is `seo-geo`), NOT the editorial calendar (that is `content-engine`).
Use when deciding whether a process is worth automating, sizing ROI and build-vs-buy, choosing an automation platform, or diagnosing why a fleet of automations keeps breaking — the decision layer before anyone builds. NOT building the flow (that is `automation-flows`, or `n8n` / `make` / `zapier` / `power-automate` to drive a live platform).
Use when standing up the core AWS surface a small product needs: hardening a fresh account, a private S3 bucket, encrypted RDS Postgres, ECS Fargate vs EC2, CloudFront + OAC, or scoping an IAM policy to least privilege. NOT the CI pipeline that ships the container (that is `deployment`), NOT app-code access-control review (that is `secure-coding`).
Use when writing or hardening a shell script that must survive another machine — a CI step, install script, cron job, git hook, devcontainer entrypoint: strict-mode leaks, quoting/word-splitting, arrays, trap cleanup, bash-vs-POSIX portability, ShellCheck findings. NOT CI workflow structure, runners, caching or matrix (that is `github-actions`).
Use when designing or auditing a backup-and-restore program that must survive a real disaster: setting defensible RPO/RTO targets, laying out 3-2-1-1-0 copies that are offsite and immutable, wiring point-in-time recovery, and proving restores work on a schedule. NOT tuning Postgres internals or writing the archive_command (that is `postgresdb`).
Use when a small business needs audit-ready books — a chart of accounts, posting a transaction to the right account and side, clearing an uncategorized bank feed, cash vs accrual, or a ledger that won't tie to the bank. NOT interpreting the numbers — runway, burn, P&L cadence (that is `finance-ops`), NOT issuing invoices (that is `invoicing`).
Use when a project needs its visual foundation built or consolidated into one system: logo brief, color system in HEX/RGB/CMYK/OKLCH with proven AA contrast, type system, usage rules, and an exported W3C design-tokens.json that later skills consume. NOT the applied UI pixels (that is design), NOT the words or tone (that is brand-voice).
Use whenever the user asks to make an answer or draft sound human, natural, plain-spoken or less AI-written — including a terse bro after the last response. Rewrites or drafts in the same language while preserving meaning, facts and channel. NOT a reusable brand voice (that is `brand-voice`), NOT translation (that is `translation-l10n`).
Use when defining how a brand SOUNDS as a reusable system: adjectives turned into linguistic rules, four tone dimensions as ratios, a use/avoid word bank, an AI voice-DNA block — so content stops sounding like five different writers. NOT the finished copy written against it (that is `landing-copy` / `marketing`), NOT the brand's look (`brand-identity`).
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is `postgresdb`) or service deployment (that is `deployment`).
Use when a metric (revenue, MRR, margin) needs defining once in a governed semantic layer so every dashboard, report and agent returns the same number, or when an LLM must answer data questions in plain language without hallucinating SQL. NOT chart layout (that is `dashboard`), NOT which KPIs to track (that is `kpi-framework`), NOT a hand-written query (that is `sql`).
Use when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent prices or policy, jailbreak and injection defense, the human handoff, launch metrics and kill switch. NOT the agent loop or RAG index under it (that is `building-agents`), NOT a human answering one ticket (that is `customer-support`).
Use when a product needs a booking surface — a pick-a-slot page, a Cal.com/Calendly embed, or real availability plus the confirmed meeting written to Google/Outlook — or when fixing double-booking, DST drift, or orphaned reschedule events. NOT calendar CRUD with no booking surface (that is `google-workspace`), NOT the payment (that is `stripe`).
Use when building or shipping a Manifest V3 browser extension and hitting its quirks — service worker dying and losing state, permission warnings, a Chrome Web Store rejection, content-script/worker/popup messaging, or an MV2-to-V3 migration. NOT a generic web app (that is `nextjs`), NOT a desktop shell (that is `electron`).
Use when turning one named customer's measured win into a case study, or the attributed testimonial quote that travels with it — consent-cleared, metrics-anchored proof for the next skeptical buyer. NOT the deck that sells the vision to a room (that is `pitch-deck`), NOT thought-leadership with no single named customer (that is `article-writing`).
Use when a spec exists and must be de-risked before planning — hunt its ambiguities, unstated assumptions and edge cases, ask the few build-changing questions, bake the answers back into the spec. The rsc SDD gate between `specify` (writes the spec) and `plan` (designs the build). NOT the cross-artifact consistency check (that is `analyze`).
Use when running a ClickHouse server for high-volume OLAP: choosing a MergeTree engine and ORDER BY/PARTITION BY keys, ingesting billions of event/log/metric rows, pre-aggregating with materialized views, or fixing a query that scans instead of pruning. NOT in-process file analytics (that is `duckdb`), NOT OLTP CRUD indexing (that is `postgresdb`).
Use when a deal closed or a user signed up and the first 30 days need an activation plan: sales→delivery handoff, one verifiable activation event, kickoff, and a 30/60/90 or day-0→14 plan with owners, dates and a measurable exit. NOT reactive ticket triage (that is `customer-support`), NOT renewals/churn past the onboarded gate (that is `retention`).
Use when working on Cloudflare's edge platform — wrangler.jsonc bindings, choosing between D1/KV/R2/Durable Objects/Queues, deploying a Worker or SPA via Static Assets, or designing around a Workers runtime limit. NOT generic CI/release (that is `deployment`), NOT Next.js framework wiring (that is `nextjs`), NOT DNS records (that is `domains-dns`).
Use when you land in an unfamiliar or inherited codebase and must get productive fast: a breadth-first map of entry points, request flow, module ownership, hidden side effects (cron, webhooks, workers) and churn hotspots, committed as CODEBASE-MAP.md. NOT a deep audit of one module (that is `analyze`) or chasing one failure (that is `debug`).
Use when an already-named set of rivals is watched on a cadence — pricing, features, positioning and changelog diffed into a maintained tracker plus an append-only, classified change log. NOT sizing the market or choosing who the rivals are (that is `market-research`), NOT one-off page extraction (that is `data-scraper`).
Use when writing a cold email or LinkedIn DM to a stranger and its cadence: first-touch copy under a word ceiling, 4-7 step bump sequences, per-inbox volume and warm-up limits, the compliant opt-out footer. NOT SPF/DKIM/DMARC setup (that is email-deliverability), NOT sourcing the list (that is lead-gen), NOT life after a reply (that is sales-pipeline).
Use when building or running a persistent two-way community space — Discord, Telegram, Circle: platform choice, structure, onboarding, native→bot→human moderation, rituals, growth loops, health metrics. NOT churn of paying product customers (that is `retention`), NOT broadcast email (that is `newsletter`), NOT one live event (that is `webinar`).
Use to judge a concrete diff, branch, or GitHub PR on its own merits with no rsc-SDD spec/plan chain to key off — the spec-less giving pass behind /code-review: only findings you can defend, one verdict, read-only unless --comment or --fix. NOT the SDD gate keyed to 02-DOCS/wiki/sdd/ that also processes incoming review comments (that is `review`).
Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cross-platform UI (that is flutter).
Use when scoping which regulatory frameworks bind a business — SOC 2, ISO 27001, HIPAA, PCI DSS, EU AI Act, DORA, NIS2 — building a control register with owners and evidence, or standing up the cadence that keeps it audit-ready. NOT drafting privacy-policy/ROPA/DPA or ToS text (that is gdpr-privacy, terms-conditions), NOT hardening code (that is secure-coding).
Use when setting or amending a project's non-negotiables — stack canon, quality bars, conventions, security/a11y floors — as numbered, testable rules later phases obey. First rsc-sdd phase; writes 02-DOCS/wiki/sdd/constitution.md. NOT a feature spec (that is `specify`), NOT the technical plan (that is `plan`), NOT the wiki itself (that is `harness`).
Use when a mistake, correction, or surprise taught the workspace something that must stick — a retro or postmortem, the same agent error corrected twice, a resolved bug's root cause, scattered notes-to-self — and route that lesson to the durable surface that fires next time. NOT a forward choice with alternatives (that is `decision-records`).
Use when a content operation needs a SYSTEM: a dated editorial calendar built top-down from pillars, plus the stage gates, briefs, WIP limits and 1:10 atomization plan that move each slot to publish-ready. NOT writing the pieces (that is `article-writing`), NOT publishing them (that is `social-publisher`), NOT keyword research (that is `seo-geo`).
Use when self-hosting apps and databases with Coolify on a VPS you own — install, first-admin lockdown, Git-to-deploy (Nixpacks/Dockerfile/compose), managed Postgres/Redis, scheduled S3 backups, domains + auto-SSL. NOT a PaaS someone else runs (that is `railway`), NOT sizing/hardening the box (that is `hetzner`), NOT authoring Dockerfiles (that is `docker`).
Use when metering and capping AI or cloud app spend — tokens read from the response `usage` object, priced off a dated rate table, ledgered per user/tenant/feature, with alerts and a hard cap before the bill. NOT cash runway (that is `finance-ops`), NOT cost-per-unit margin (that is `unit-economics`), NOT booking the spend (that is `bookkeeping`).
Use when drafting or reviewing business contracts and clauses in plain language — NDAs, MSAs, SOWs, contractor agreements, risk boilerplate (liability caps, indemnity, force majeure, termination, IP) — or redlining a counterparty's paper. NOT consumer Terms of Service (that is terms-conditions) and NOT the signing workflow (that is e-signature).
Use when a long-horizon task is filling the context window and you must decide what to keep, offload, drop, or hand off to a fresh window — when to compact, what the summary must preserve, and whether to isolate a read-heavy subtask in a subagent. NOT dollar spend or caps (that is cost-tracking), NOT finding context via embeddings (that is rag).
Use when turning \"I want to teach X\" into a defensible course skeleton — measurable outcomes (Bloom + ABCD), assessment that proves each one, sequenced modules, and an outcome×module×assessment matrix — for a workshop, bootcamp, cohort or onboarding track. NOT making one concept land emotionally with story or analogy (that is course-storytelling).
Use when lesson or course content is correct but forgettable and a concept has to LAND: profiles the learner, breaks the blocking false belief, then rebuilds it as epiphany story → named model → grounded analogy → proof → so-what. NOT outcomes, assessment or module order (that is `course-builder`), NOT slide visuals (that is `presentations`).
Use when writing, reviewing, testing, or shipping C# / .NET code — ASP.NET Core APIs (minimal APIs vs controllers), EF Core data access, async correctness, solution layout in .cs/.csproj/.sln. NOT a Java/Spring backend (that is spring-boot), NOT a Node/TypeScript backend (that is nestjs), NOT framework-neutral REST naming (that is api-design).
Use when writing, reviewing, modernizing, building, or debugging C++ - RAII and resource lifetime, smart-pointer ownership, move semantics and the Rule of Zero/Five, target-based CMake with FetchContent, and killing undefined behavior with ASan/UBSan/TSan plus clang-tidy. NOT borrow-checker / Result-Option / cargo memory safety (that is rust).
Use when a live support ticket needs triage (intent, P1–P4 priority, SLA clock), an on-voice reply, not a raw template, de-escalation of an angry or churn-risk customer, or escalation with a handoff packet. NOT the help-center article it links to (that is `technical-writing`), a win-back program (`retention`), or the auto-answer bot (`chatbot`).
Use when building internal data-governance machinery: a retention schedule (period, lawful basis, expiry action, system where deletion runs), an Art. 6 lawful-basis register, an Art. 30 ROPA, or a consent capture/withdrawal model. NOT the public privacy notice or DSAR handling (that is `gdpr-privacy`), NOT SOC 2 posture (that is `compliance`).
Use when building or fixing a KPI dashboard decision-makers must read in one screen: which metrics earn a tile, how each tile is framed to answer a decision, and which chart fits it. NOT defining the metrics or their targets (that is kpi-framework), wiring the data (that is analytics), or writing a narrative status report (that is reporting).
Use when data lives on a website with no usable API — listings, prices, public records — and the scrape must stay legal and not get blocked: legal gate, extraction path, durable selectors, pacing, resilience. NOT parsing bytes you already hold into fields (that is structured-extraction), NOT a documented API or key (that is api-connector-builder).
Use when a raw table is too dirty to trust — nulls, sentinels, duplicate rows, category sprawl, mixed types, bad dates — and you need a re-runnable clean() plus a schema gate that fails loud. NOT emitting .xlsx (that is spreadsheet-ops), NOT acquiring rows (that is data-scraper), NOT parsing PDF/HTML into rows (that is structured-extraction).
Use when a schema change must ship without downtime — NOT NULL, rename, type change, or backfilling millions of live rows — for the expand-contract sequence and the lock/batching discipline that keeps each step from freezing prod. NOT lock internals or EXPLAIN (that is `postgresdb`), NOT drizzle-kit mechanics (that is `drizzle-orm`), NOT PITR (that is `backups`).
Use when a hard-to-reverse choice (database, framework, vendor, auth model) must be frozen as an immutable numbered ADR — the context that forced it, the options weighed, the decision, consequences both ways — or superseded without erasing history. NOT a meeting recap (that is meeting-notes), NOT standing project principles (that is constitution).
Use when a high-impact plan, migration or architecture claim needs a bounded adversarial challenge before commitment. Isolates claims from persuasion, attacks assumptions, reconciles doubts with evidence and emits proceed/hold/stop. NOT a finished-diff review (`review`/`code-review`), NOT SDD artifact consistency (`analyze`).
Use when something is broken — a failing or flaky test, crash, wrong result or regression — and the root cause must be reproduced and proven before any fix. On-demand; callable mid-`implement`. NOT a feature to spec or build (that is `specify`/`implement`), NOT the lint/test gate (that is `verify`), NOT adversarial diff reading (that is `review`).
Use when training or debugging a neural net in PyTorch — the forward/loss/backward/step loop and its silent bugs, mixed precision (AMP), AdamW/LR schedules, DDP/FSDP/ZeRO, checkpoints and seeds. NOT LoRA/QLoRA on a pretrained LLM (that is `finetuning`), NOT tabular sklearn/XGBoost (that is `machine-learning`), NOT tokenization or NLP metrics (that is `nlp`).
Use when taking an app from source to live: choosing the deploy target from requirements (Hetzner+Coolify vs Vercel vs a third), then wiring container → CI → registry → host with build secrets, healthchecks and rollback. NOT one platform's mechanics (that is `coolify`, `vercel`, `railway`, `render`), NOT the Dockerfile alone (that is `docker`).
Use when retiring a public API, feature, integration, service or legacy path without abandoning consumers. Inventories usage, classifies advisory vs compulsory migration, ships compatibility/tooling, assigns owners and gates removal on evidence. NOT live schema expand-contract (`db-migrations`), NOT replacement API design (`api-design`).
Claude Skills — questions
Answers built from the skills we actually parsed.