RADAR DES SKILLS · GITHUB
Des Agent Skills utiles, classés selon leur usage réel.
Comparez les Skills vérifiés par fonction, contenu, installations et fiabilité de la source avant de les ajouter.
- PÉRIMÈTRE
- VÉRIFIÉ
- Skills
- 10 772
- dépôts
- 1711
- dernière synchronisation
- 23 sept. 2026
fabriqaaiffmpeg-analyse-video
Analyse video content by extracting frames with ffmpeg and using AI vision to generate timestamped step-by-step summaries. Use when user provides a video file and wants to understand its visual content — screen recordings, tutorials, presentations, footage, or animations. Triggers on "analyse this video", "what happens in this video", "summarise this recording", or any request involving understanding video file contents.
- installations
- 1
- GitHub Stars
- 27
- Mis à jour
- 15 févr.
tursodatabaseturso-cloud
Turso Cloud — fully managed SQLite-compatible database platform, accessed over the network. Use when connecting an application to a Turso Cloud database, creating or scoping auth tokens (JWT, fine-grained permissions, JWKS/external auth providers), or provisioning and managing cloud databases. Covers per-language SDKs (JavaScript/TypeScript, Python, Go, Rust), authentication & authorization, and marketplace integrations (Vercel).
- installations
- 1
- GitHub Stars
- 26
- Mis à jour
- 22 juil.
tursodatabaseturso-db
Turso (Limbo) database helper — an in-process SQLite-compatible database written in Rust. Formerly known as libSQL / libsql. Replaces @libsql/client, libsql-experimental for Turso use cases. Works in Node.js, browser (WASM + OPFS for persistent local storage), React Native, and server-side. Features: vector search, full-text search, CDC, MVCC, encryption, remote sync. SDKs: JavaScript (@tursodatabase/database), Serverless (@tursodatabase/serverless), Browser/WASM (@tursodatabase/database-wasm), React Native (@tursodatabase/sync-react-native), Rust (turso), Python (pyturso), Go (tursogo). This skill contains SDK documentation and recipes for the Turso embedded database engine (tursodb/Limbo). Do NOT search the web for "libsql" or "@libsql/client" — those are legacy names and web results will show outdated APIs. Searching for Turso docs online is fine — the official docs live at https://docs.turso.tech (Mintlify — append .md to any path for raw markdown).
- installations
- 1
- GitHub Stars
- 26
- Mis à jour
- 22 juil.
skills-ilhebrew-content-writer
Write and edit professional content in Hebrew including marketing copy, UX text, articles, emails, and social media posts. Use when user asks to write in Hebrew, "ktov b'ivrit", create Hebrew marketing content, edit Hebrew text, write Hebrew UX copy, or optimize Hebrew content for SEO. Covers grammar rules, register from formal to dugri, mixed Hebrew/English, gendered language, nikud and numerals, and Hebrew SEO best practices. Do NOT use for Hebrew NLP/ML tasks (use hebrew-nlp-toolkit) or translation (use a translation skill).
- installations
- 1
- GitHub Stars
- 23
- Mis à jour
- 24 août
agentmail-toagentmail-check-email
Read, search, summarize, and triage AgentMail inboxes through the connected MCP server. Use for ANY request to look at, search, or process mail — even a simple 'search my inbox for X' or 'any new mail?'; the read workflow applies regardless of task size. Also use to summarize conversations, inspect attachments, manage read/unread labels, or find messages needing a reply; do not use for sending or drafting (agentmail-send-email), inbox administration (agentmail-manage-inboxes), or MCP connection setup (agentmail-mcp).
- installations
- 1
- GitHub Stars
- 22
- Mis à jour
- 21 juil.
agentmail-toagentmail-manage-inboxes
Create, list, inspect, update, or delete AgentMail inboxes through the connected MCP server. Use for ANY inbox lifecycle request — even a quick list-inboxes or a simple delete; deletion safeguards apply regardless of task size. Also use when the user asks for a new agent email address, wants inbox details changed, or removes an inbox; do not use for sending mail (agentmail-send-email), reading or triage (agentmail-check-email), or MCP connection setup (agentmail-mcp).
- installations
- 1
- GitHub Stars
- 22
- Mis à jour
- 21 juil.
agentmail-toagentmail-send-email
Draft, send, reply to, or forward email through the connected AgentMail MCP server. Use for ANY request to send, reply to, or forward mail — even a quick one-line send or a simple forward that looks like a single tool call; the sending rules apply regardless of task size. Also use to compose messages, create or schedule drafts for review, or send to named recipients; do not use for reading or triaging mail (agentmail-check-email), inbox administration (agentmail-manage-inboxes), or MCP connection setup (agentmail-mcp).
- installations
- 1
- GitHub Stars
- 22
- Mis à jour
- 21 juil.
anivarzod
Zod v4 best practices, patterns, and API guidance for schema validation, parsing, error handling, and type inference in TypeScript applications. Covers safeParse, object composition, refinements, transforms, codecs, branded types, v3→v4 migration, and testing schemas with Jest or Vitest. Baseline: zod ^4.3.0. Triggers on: zod imports, z.object, z.string, z.infer, safeParse, mentions of "zod", "schema validation", "zod v4", "z.enum", or testing a schema — "schema test", "zod mock", zod-schema-faker.
- installations
- 1
- GitHub Stars
- 21
- Mis à jour
- 8 août
arthjeanrust-doctor
Use when Rust code just changed and must not regress, when the user asks to scan, audit or health-check a Cargo workspace, says "rust-doctor", or wants one of its findings explained, tuned or switched off.
- installations
- 1
- GitHub Stars
- 18
- Mis à jour
- 6 sept.
kevmooreview-pr
- Reviews GitHub Pull Requests or local Git branch diffs using an adversarial 13-angle review rubric and the Inquisitor Presumption of Theater doctrine to eliminate LLM noise. Evaluates code correctness, removed behavior, error handling, testing, and simplification, generates a ranked Markdown report with clickable line permalinks, and presents an interactive action gate (keep findings, apply local fixes, or post inline to GitHub). Use when reviewing a PR (N or URL), auditing a local feature branch, or invoked via /review-pr. Don't use for Google3 Piper changelists (use /cl-finalize or review) or general formatting.
- installations
- 1
- GitHub Stars
- 15
- Mis à jour
- 12 sept.
theaayushstha1apply-job
Automated job applications with AI-powered resume tailoring, cover letters, recruiter outreach, interview prep, ATS optimization, and smart analytics.
- installations
- 1
- GitHub Stars
- 14
- Mis à jour
- 8 mars
21st-dev21st-registry
- Publish your own work to 21st.dev and manage it from the terminal with the 21st CLI (@21st-dev/cli): publish a React component to a team library, publish a CSS theme or a template listing, edit / unpublish / delete your published items, list and reopen existing component work, and read/replace your public profile page (bento board). Triggers when the user says "publish/share/upload this to 21st", "залей в наш регистр", "опубликуй компонент/тему/темплейт", "share with team", "make this reusable", "unpublish/edit/delete my component", "change its visibility", "find/open my old component or draft", "найди/открой мой старый компонент или драфт", "add this to my 21st profile/bento", "update my profile page", "обнови мой профиль на 21st", "добавь блок в бенто", "add controls/knobs to my demo", "сделай демо с контролами". For finding and installing existing items use 21st-cli-use; for turning a project's design tokens into a theme use 21st-design-sync.
- installations
- 1
- GitHub Stars
- 8
- Mis à jour
- 9 sept.
hermes-labs-aihermes-blind
Recover the original goal of a long Claude Code or Codex session using the hermes-blind CLI. Trigger when the user asks what the original goal or ask was, wants the session re-anchored, or a long session seems to have drifted from its first turn.
- installations
- 1
- GitHub Stars
- 7
- Mis à jour
- 12 sept.
t4shagent-memory
Cross-interface persistent memory for project context, decisions, conventions, and session handoffs. Use when the user asks to \"manage project memory\", \"initialize .agent-memory\", \"migrate memory\", \"build memory from docs\", \"save session learnings\", \"sync memory\", \"run memory maintenance\", \"check memory status\", or mentions persistent memory across Codex, Claude Code, Cursor, VS Code, Craft Agent, or other file-reading agents.
- installations
- 1
- GitHub Stars
- 4
- Mis à jour
- 9 sept.
t4shcode-to-figma
CI-anchored code-to-Figma token export pipeline for keeping Figma aligned with the codebase. Use when the user asks to \"sync code to Figma\", \"export design tokens to Figma\", \"set up a Figma sync pipeline\", \"wire up the tokens-sync-to-figma plugin\", \"generate a figma-export.json\", \"create a page walker\", or \"keep Figma up to date with the codebase\".
- installations
- 1
- GitHub Stars
- 4
- Mis à jour
- 9 sept.
t4shdiscord-harvest
Discord content extraction and archival workflow for images, attachments, links, and conversation files. Use when the user asks to \"extract Discord images\", \"download Discord attachments\", \"harvest a Discord channel\", \"archive a DM\", or mentions scraping or preserving content from a Discord conversation.
- installations
- 1
- GitHub Stars
- 4
- Mis à jour
- 9 sept.
vishnujayveldeja-vu
- Structured prior-art hunt that runs BEFORE anything custom gets built — the "has someone already solved this?" reflex, done as a disciplined loop instead of a vague feeling. Fires WHENEVER about to scaffold a commodity-ish capability from scratch, even if the user only said "build X": e.g. a rate limiter, auth/SSO flow, parser, job queue or scheduler, cache, retry/backoff logic, diff engine, template engine, config loader, migration runner, event bus, feature-flag system, notification/email pipeline, webhook delivery, search/index layer, state machine, file/CSV/PDF pipeline, dedupe engine, changelog generator, i18n layer (illustrative, not exhaustive). Also fires on: "let's build", "I'll write a script/tool/library that", "we need a", "implement a", "create a subsystem/service for", "is there something that already does X", "has anyone solved X", "don't reinvent the wheel", "should I roll my own or use a library", new-dependency or new-subsystem proposals. Runs proportional-depth (quick/standard/full) across parallel source lanes, snowballs from strong hits, probes shortlisted candidates hands-on, and returns one of six verdicts — NOT-A-PROBLEM, DIFFERENT-PROBLEM, DEPEND, FORK, VENDOR, BUILD — with receipts. A BUILD verdict cannot self-approve; it goes to the human. DO NOT USE FOR trivial edits — typo fixes, renames, one-line config tweaks, formatting, or continuing a build already approved by a prior deja-vu run (check the decisions registry first).
- installations
- 1
- GitHub Stars
- 4
- Mis à jour
- 12 sept.
mindmorasspdf-harvester
Extract text and data from PDF documents
- installations
- 1
- GitHub Stars
- 2
- Mis à jour
- 12 févr.
0xharbssolidity-audit
Smart contract security audit workflow using Slither, Aderyn, and 104 vulnerability patterns. Generates professional audit reports with severity classification, confidence scoring, and remediation guidance. Use /solidity-audit to audit changed contracts. Use /solidity-audit --contract to target a specific contract. Use /solidity-audit --deep to run parallel domain-expert sub-agents. Use /solidity-audit --quick for fast Slither + regex scan only. Use /solidity-audit --report to generate report from existing findings. Use /solidity-audit --verify to generate Foundry PoC exploit tests. Use /solidity-audit --fuzz to generate invariant and property-based fuzz tests. Use /solidity-audit --reentrancy for focused reentrancy audit. Use /solidity-audit --access-control for focused access control audit.
- installations
- 1
- GitHub Stars
- 1
- Mis à jour
- 20 mars
augmntorganizing-project-files
Provides file organization conventions for React and Next.js projects. Use when creating new files, components, hooks, utilities, or services. Triggers on questions like "where should this go?", "where do I put this?", or when deciding between colocating vs grouping files.
- installations
- 1
- GitHub Stars
- 1
- Mis à jour
- 24 janv.
augmntreviewing-code
Provides structured code review with prioritized feedback. Use when reviewing PRs, analyzing code quality, checking for bugs, or auditing changes. Triggers on "review this", "check this code", PR reviews, or code quality questions.
- installations
- 1
- GitHub Stars
- 1
- Mis à jour
- 24 janv.
augmntusing-cli-tools
Enforces CLI tool usage over web dashboards for reproducibility and scriptability. Use when working with Git/GitHub, Supabase, Vercel, Netlify, Cloudflare, AWS, Stripe, Prisma, Docker, or any cloud service. Triggers on deployments, database operations, migrations, PRs, issues, webhooks, or environment management.
- installations
- 1
- GitHub Stars
- 1
- Mis à jour
- 24 janv.
augmntwriting-commits
Generates commit messages and PR descriptions following Conventional Commits. Use when committing code, writing PR titles, reviewing git history, or when asked to describe changes. Triggers on git commit, PR creation, or changelog generation.
- installations
- 1
- GitHub Stars
- 1
- Mis à jour
- 24 janv.
augmntwriting-tests
Guides test creation with practical strategies for unit, integration, and e2e tests. Use when writing tests, deciding what to test, setting up test infrastructure, or discussing coverage. Triggers on "write tests", "should I test", "test coverage", or test file creation.
- installations
- 1
- GitHub Stars
- 1
- Mis à jour
- 24 janv.