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. 80 149 files from 1 774 authors, of which 62 489 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.
Add a new diagnostic code following the defineDiagnostics() conventions from nostics
Structured diagnostic code library for JavaScript/TypeScript. Turns errors and other conditions into typed, machine-readable `Diagnostic` instances with stable codes, docs URLs, and actionable fields. Use this skill whenever the project imports `nostics`, or works with `defineDiagnostics`/`defineProdDiagnostics`, the `Diagnostic` class, diagnostic code registries, or structured error handling. Also covers reporters (`createConsoleReporter`, `createFetchReporter` from nostics/reporters/fetch, `createFileReporter` from nostics/reporters/node, `createDevReporter` from nostics/reporters/dev), formatters (`formatDiagnostic`, `ansiFormatter`, `jsonFormatter`), and Vite plugins (`nosticsStrip` from @nostics/unplugin/strip-transform, `nosticsCollector` from @nostics/unplugin/dev-server-collector). Also use when migrating a library's existing `console.warn`/`console.error`/`warn()` helpers or thrown `Error`s to diagnostics: follow `references/migration.md`.
> Initialize or update CLAUDE.md coding standards for any project by auto-detecting tech stack and assembling rules from the claude-rules template library. Use when user says "init rules", "初始化规范", "生成 CLAUDE.md", or wants to set up coding standards.
Read-only investigation and analysis of GitHub issues for Shopify/shopify-app-template-react-router. Fetches issue details via gh CLI, searches for duplicates, examines the template's code for relevant context, applies version-based maintenance policy classification, and produces a structured investigation report. Use when a GitHub issue URL is provided or when asked to analyze or triage an issue.
Rank tracking without a tracker subscription — position movers between any two periods from real Search Console data. Use when asked "how are my rankings", "what moved this week/month", "track my keywords", or "did the update hit me".
SERP-driven content brief for a target keyword — what ranks, what to cover, headings, questions, internal links from your own data. Use when asked for a "content brief", "outline to rank for X", "what should this article cover", or before writing any SEO page.
Backlink profile for any domain — referring domains, authority, anchors, new/lost links, and a side-by-side vs a competitor. Use when asked "check my backlinks", "backlink profile of X", "who links to them", or "link gap vs competitor".
Measure real AI-engine visibility — traffic from ChatGPT, Perplexity, Claude, Gemini and which pages they cite — from actual GA4 referral data, not prompt sampling. Use when asked "AI visibility", "GEO/AEO check", "do LLMs cite us", "traffic from ChatGPT", or "how do we show up in AI search".
Keyword research from a seed topic — ideas, real Google volume/CPC, intent, difficulty, clustered into a plan. Use when asked to "find keywords", "keyword research for X", "what should I rank for", or "build a keyword plan".
Full SEO audit of a site from its real Search Console + GA4 data — indexation health, CTR anomalies, decaying pages, striking-distance keywords, quick wins. Use when asked to "audit my site", "SEO audit", "why is my organic traffic down", or "SEO health check".
Find money leaking between search ads and SEO — queries you pay for while already ranking organically, and paid queries with no organic coverage. Use when asked "am I paying for clicks I'd get free", "brand bidding waste", "SEO vs ads overlap", or "cut wasted ad spend with SEO".
Find keywords a competitor ranks for that the user's site doesn't — the content gap, prioritized by volume and winnability. Use when asked "what does competitor.com rank for", "keyword gap vs X", "steal competitor keywords", or "why do they outrank us".
Environment-level Dataverse administration — bulk delete, retention/archival, organization settings, OrgDB settings, recycle bin, audit, and the 37 allowlisted PPAC toggles. Use when the user wants to clean up data at scale, configure audit, change environment settings, manage retention policies, or list/cancel ERP batch jobs.
Security-role assignment, user access, application users, business units, and admin self-elevation in Dataverse environments. Use when the user wants to give someone access, grant a role, become an admin, or add a service principal.
Foundational cross-cutting context for Dataverse / Power Platform work — scope and the skill map, the tool-capability reference, the safety rules, and the safe change lifecycle. Use when the user mentions Dataverse, Dynamics 365, Power Platform, CRM, or ERP; load this first for orientation. Specialist skills self-route via their own frontmatter triggers.
One-step setup for a Dataverse environment — installs tools, authenticates, registers the MCP server, and writes `.env`. Use when starting a new project, switching environments, fixing authentication, or troubleshooting an MCP connection that won't come up.
Dataverse solution lifecycle — create, export, import, promote across environments, and validate deployments. Use when the user wants to package customizations, deploy to another environment, or move work between dev / test / prod.
Dataverse schema authoring and inspection — tables, columns, relationships, forms, and views. Use when the user wants to define, evolve, or inspect the data model — add a column, create a table, set up a lookup, customize a form, build a view, or list existing columns and relationships.
Record-level CRUD and bulk operations — create, update, delete, upsert, CSV import, multi-table foreign-key loads, AI-generated sample data. Use when the user wants to write, modify, seed, or import data records into Dataverse tables.
Bulk reads, multi-page iteration, and analytics over Dataverse data. Use when the user wants to read, list, filter, aggregate, group, join, or analyze records — including pandas DataFrame workflows and notebook exploration.
Modern tidyverse patterns for R including pipes, joins, grouping, purrr, and stringr. Use when writing tidyverse R code.
R package development guide covering dependencies, API design, testing, and documentation. Use when developing R packages.
R style guide covering naming conventions, spacing, layout, and function design best practices. Use when writing R code.
rlang metaprogramming patterns for data-masking, injection operators, and dynamic dots. Use when writing functions that use tidy evaluation.
Test-driven development workflow for R using testthat. Use when writing new features, fixing bugs, or refactoring code. Enforces test-first development with 80%+ coverage.
Patterns for Bayesian inference in R using brms, including multilevel models, DAG validation, and marginal effects. Use when performing Bayesian analysis.
R object-oriented programming guide for S7, S3, S4, and vctrs. Use when designing R classes or choosing an OOP system.
R performance best practices including profiling, benchmarking, vctrs, and optimization strategies. Use when optimizing R code.
Cut a coordinated AHP release (spec + all 5 clients) — bumps every manifest, dates the CHANGELOGs, opens the release PR with auto-merge, and walks through pushing the six per-artifact tags. Use when the user says "release AHP X.Y.Z", "publish AHP", "cut a release", "tag the release", or similar. The skill also captures the recovery procedure for tags whose publish workflow didn't fire.
>- Migrate code that talks to or implements the Agent Host Protocol to the flattened SessionState model. Use when asked to upgrade an AHP client/server/binding and you see a `summary` sub-object on `SessionState` (e.g. `state.summary.title`, `session.summary.modifiedAt`), `model` / `agent` on `SessionState` / `SessionSummary` / `ChatState` / `ChatSummary`, the `session/modelChanged` or `session/agentChanged` actions, numeric `createdAt` / `modifiedAt`, or `model` / `agent` arguments to `createSession` / `createChat`.
>- Interact with an Agent Host Protocol (AHP) server via WebSocket. Use when asked to connect to, message, or control an AHP server.
>- Migrate code that talks to or implements the Agent Host Protocol from the pre-channels model to the current channel-based model. Use when asked to `envelope` field inside `action` params, a `resource` field on subscribe/unsubscribe/snapshot results, or `session` / `terminal` / `changeset` fields on command params or action payloads.
Audits recently closed PRs in agent-host-protocol (AHP) to make sure any future work they promised has a tracking issue (filing new ones or linking PRs to existing ones), then triages every open issue into implementable-now / no-longer-relevant / blocked-on-a-dependency, closing or annotating each accordingly, and finally prioritizes and implements the ready issues. Validates every follow-up and issue against the current state of this repo — the canonical `types/`, the generated client mirrors, the conformance fixtures, and the published versioned artifacts — before acting. Use when asked to triage or groom the issue backlog, file follow-up issues from merged PRs, audit closed PRs for un-tracked work, or work through the open issues.
Review Business Central AL code changes using the BCQuality knowledge base. Use when reviewing an AL pull request, a working-tree diff, or a single AL file, and you want findings backed by BCQuality's curated, BC-specific quality rules.
Ingestion architecture and implementation principles. Use for design, review, meaningful refactoring, Azure integration, document security, testing, or operational changes.
Keeps ingestion repository and published GPT-RAG documentation aligned with shipped formats, configuration, indexing, deployment, audit, and operator behavior.
Conducts and records a verifiable ingestion architectural decision. Use when a choice alters pipeline boundaries, chunk/index contracts, identity, data, source integration, deployment, or operation with meaningful reversal cost.
Prepares and validates gpt-rag-ingestion releases. Use for release branches, VERSION, changelog entries, compatible GPT-RAG pins, tags, images, and GitHub Release notes.
Selects and runs evidence-based validation for Python ingestion, chunking, jobs, Azure AI Search contracts, deployment assets, and the operator frontend. Use whenever repository behavior or engineering assets change.
This skill should be used to generate a "prompt request" one-pager that summarizes the current session for a pull request. It produces one consolidated User block folding together every ask and decision from the session, plus one Assistant block summarizing what was built. Use it when the user asks to "generate a prompt request", recap or summarize the session for a PR, or capture what was requested. Also use it automatically when opening a pull request or writing a PR description, so the PR body includes the asks and decisions behind the change. Works on the current session only and outputs inline markdown ready to paste into a PR.
This skill should be used when the user asks questions about startups, founding decisions, co-founders, fundraising, product development, growth, hiring, or any entrepreneurial advice. It provides access to Y Combinator's complete library of 443 curated resources including essays by Paul Graham, founder interviews, and startup school lectures. Use this skill to give thorough, research-backed advice on startup decisions.
Reduce negative-constraint and session-history leakage when a discarded proposal or user correction is echoed into final artifacts as a ‘without X’ label, rejected-option explanation, or process residue. Use for 此地无银三百两式 output in prose, code, metadata, and handoffs, including later requests to finish, commit, publish, or open a PR after iterative work; not for ordinary deletion, deprecation, migration, or requirements where the exclusion itself is material.
> Discovery, download, and configuration hub for the entire aelf agent skill ecosystem. (2) install/bootstrap aelf skills into Cursor, Claude Desktop, OpenClaw, Codex, or Claude Code, (3) route an aelf-related intent to the correct skill, (4) check health or audit installed skills, (5) onboard a new skill into the aelf ecosystem. AelfScan explorer, TomorrowDAO governance, aelf node interaction.
Fixture node skill depending on fixture core.
Fixture core skill for CI gates.
Publish local HTML, Markdown, or built static web projects with Pagecast as shareable public URLs. Use whenever Codex creates or finishes an .html, .htm, .md, .markdown, or static build output that a person could share (a report, plan, doc, dashboard, or analysis) — proactively offer to publish it without being asked — and whenever the user asks to publish, share, make a public link for, or send a local report/doc/dashboard/web project from terminal, Codex CLI, or Codex desktop.
Help publish local HTML, Markdown, or built static web projects by asking whether to use Claude Code Artifacts or Pagecast/Cloudflare Pages when the user's publish request is ambiguous. Use when a report, plan, doc, dashboard, analysis, or static build output should be shared from Claude Code, especially when the user says publish, share, make a public link, or send this. If the user explicitly says Pagecast, publish with Pagecast.
Скилл для очеловечивания русскоязычного текста. Убирает признаки AI-генерации, делает текст живым. Используй ВСЕГДА, когда пользователь просит: очеловечить текст, убрать следы нейросети, сделать текст живым/естественным, переписать как человек, humanize на русском, убрать канцелярит, убрать водянистость, сделать текст менее формальным. Также используй если пользователь вставляет русскоязычный текст и говорит что-то вроде 'перепиши', 'сделай лучше', 'звучит как робот', 'слишком искусственно'. Работает ТОЛЬКО с русским языком. Для английского используй оригинальный humanizer. НЕ используй для: перевод, написание с нуля, грамматика, код.
Socratic method teaching skill that guides users to discover answers themselves through questioning, never giving direct answers. TRIGGER when: user's message contains 'socratic', 'Socrates', or '소크라테스'. Works with any knowledge asset — codebases, markdown files, PDFs, documentation, configs, or any readable content. Respond in the user's language.
Router skill for LLMQuant ETFs workflows. Use when the user needs ETF holdings, overlap, concentration, issuer snapshot, or theme exposure analysis.
Router skill for LLMQuant equities workflows. Use when the user needs stock analysis, equity comparison, research memos, merger-arb memos, or sell/take-profit work.
Router skill for LLMQuant credit workflows. Use when the user needs issuer credit review, spread regime analysis, high-yield stress monitoring, default risk, debt maturity, or covenant context.
Router skill for LLMQuant equity derivatives workflows. Use when the user needs single-stock derivative, convertible, warrant, structured payoff, or hybrid security analysis.
Router skill for LLMQuant Data primitive workflows. Use when the user needs SEC filings, 13F holders, macro snapshots, or source-grounded macro briefs.
Router skill for LLMQuant event workflows. Use when the user needs earnings event briefs, M&A tracking, regulatory risk, catalysts, event calendars, or cross-asset event impact.
Router skill for LLMQuant commodities workflows. Use when the user needs commodity spot, futures curve, inventory, roll yield, or macro linkage analysis.
Router skill for LLMQuant crypto workflows. Use when the user needs crypto market regime analysis, token research, perpetual funding, basis, leverage, liquidity, or cross-asset crypto context.
Router skill for LLMQuant investor-lens workflows. Use when the user wants an investor-style reasoning overlay grounded in LLMQuant Data evidence.
Router skill for LLMQuant macro workflows. Use when the user needs macro dashboards, Fed or central-bank previews, inflation and growth context, liquidity, or macro-to-portfolio impact analysis.
Router skill for LLMQuant market-intelligence workflows. Use when the user needs macro views, market sentiment dashboards, or event probability signals.
Claude Skills — questions
Answers built from the skills we actually parsed.