AGENT SKILLS · ÉQUIPEMENT DE MISSION
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
- 23 248
- dépôts
- 3589
- dernière synchronisation
- 4 nov. 2026
zernietest-harness
Install vigiles and test a Claude Code harness — hooks, skills, agents, settings, CLAUDE.md — by picking the right tier (unit / deterministic / eval) and writing a test that passes. Use to check that a hook fires or blocks, that a skill triggers, that injected context lands; or to observe a run — which tools it called, whether it stayed inside its declared allowed-tools, what files and side effects it produced, how to intercept a call without executing it.
- Installations / 1h
- 4
- GitHub Stars
- 15
- Mis à jour
- 7 oct.
sanyuan0704book-study
Reading coach: guides users through books systematically with knowledge compilation, mastery testing, spaced repetition, and knowledge querying. Use when user says 'read this book with me', 'book study', 'start studying X', 'reading plan', 'ingest this chapter', 'review what I read', 'quiz me on the book', 'what did the book say about X', or invokes /book-study. Supports sub-commands: ingest, query, review, compare, status. Triggers: book, study, read, chapter, ingest, review, quiz, reading plan
- Installations / 1h
- 4
- GitHub Stars
- 3,9 k
- Mis à jour
- 11 mai
muthuisherehand-drawn-diagrams
Create hand-drawn Excalidraw diagrams, flows, explainers, wireframes, and page mockups. Default to monochrome sketch output; allow restrained color only for page mockups when the user explicitly wants webpage-like fidelity. Use when the user asks for a diagram, flowchart, wireframe, sketch, visual explanation, mind map, architecture overview, or any Excalidraw-based drawing.
- Installations / 1h
- 4
- GitHub Stars
- 79
- Mis à jour
- 27 sept.
suzhengk2f-cover-letter
Turn a job posting, resume, and candidate notes into a tailored one-page cover letter with a sharp hook, requirement-matched proof, and company-specific fit—not a resume recap or generic application template. Use when the user asks for a cover letter, application letter, referral letter, or role-specific letter for job applications (including career change or entry-level). Create cover letters with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpos
- Installations / 1h
- 4
- GitHub Stars
- 2
- Mis à jour
- 1 oct.
apidojo-iofinding-instagram-creators-by-location
Finds Instagram content creators and influencers posting from a specific location using apidojo's Instagram location scraper on Apify. Triggers when the user asks to: find Instagram creators based in a city, discover local influencers in a geographic market, find content creators who post from a specific venue or neighborhood, identify local Instagram micro-influencers for geo-targeted campaigns, find creators in a country for regional brand partnerships, or discover influencers who have visited
- Installations / 1h
- 4
- GitHub Stars
- 1
- Mis à jour
- 13 mai
earthtojakecad-mcp-setup
Check that the CAD app can start after the CAD plugin is installed or updated, in Codex, Claude Code, Claude Desktop or another agent app - confirm uv is installed, point the user to uv's official installation guide when it is not, and tell them how CAD appears in their app and when to restart it. Use right after the CAD plugin is installed or updated, or when CAD's viewer did not start.
- Installations / 1h
- 4
- GitHub Stars
- 16,6 k
- Mis à jour
- 3 oct.
hithink-techhithink-finance
通过同花顺金融数据服务查询、分析、同步或导出 A 股、指数、基金、期货、期权与本地 DuckDB 数据；用于选择和配置 CLI、MCP、REST API，以及执行金融取数任务。
- Installations / 1h
- 4
- GitHub Stars
- 4 k
- Mis à jour
- 22 sept.
testdino-hqplaywright-skill
Battle-tested Playwright patterns for writing, debugging, and scaling reliable test suites. Use when you need guidance for E2E, API, component, visual, accessibility, or security testing, plus CI/CD, CLI automation, page objects, and migration from Cypress or Selenium. TypeScript and JavaScript.
- Installations / 1h
- 4
- GitHub Stars
- 383
- Mis à jour
- 6 sept.
temichsvas
Async Svelte stores (svas): fetching, caching, revalidation, persistence. Use when UI presents data from the API.
- Installations / 1h
- 4
- GitHub Stars
- 1
- Mis à jour
- 28 sept.
bootloops-aiacceptance-gate
The standard a computed result must meet before it may be called done. Use whenever an agent claims an integral is solved, a fit has closed, a formula is identified, or any quantitative answer is ready — the claim is not done until it passes this gate.
- Installations / 1h
- 4
- GitHub Stars
- 6
- Mis à jour
- 1 oct.
bootloops-aibootloops-setup
Set up the BootLoops protocol skills for this user. Use when the user asks to set up BootLoops, activate or install its skills, or asks what discipline the toolkit ships with. Presents the roster, asks which skills to activate, and installs only what the user chooses.
- Installations / 1h
- 4
- GitHub Stars
- 6
- Mis à jour
- 1 oct.
bootloops-aiconstant-recognition
Discipline for integer-relation searches (PSLQ, LLL) that turn high-precision digits into exact constants. Use whenever recognizing a numerical value as a closed form, fitting boundary constants, or reporting that no closed form exists.
- Installations / 1h
- 4
- GitHub Stars
- 6
- Mis à jour
- 1 oct.
bootloops-aiindependence-bookkeeping
Provenance rules that keep checks independent. Use when setting up any comparison, oracle, or reference value — and whenever tempted to certify a result with machinery that helped produce it.
- Installations / 1h
- 4
- GitHub Stars
- 6
- Mis à jour
- 1 oct.
bootloops-ailit-review
Deep literature review behind a research project's novelty claims — a protocol whose one job is to prevent shortcuts. It demands the papers be actually read (nothing from memory), makes thoroughness falsifiable (read ledgers, search receipts, gap statements), tracks citation chains in both directions, and lists the places to look. Use before any novelty claim ships, when writing or reviewing a related-work section, and when refereeing.
- Installations / 1h
- 4
- GitHub Stars
- 6
- Mis à jour
- 1 oct.
bootloops-aiplanted-truth
Synthetic-truth controls for analysis pipelines. Use before running any statistical fit, solver, audit, or search on real data — the pipeline must first prove it can recover a known planted answer and catch a deliberately corrupted input.
- Installations / 1h
- 4
- GitHub Stars
- 6
- Mis à jour
- 1 oct.
bootloops-aiprove-protocol
Multi-agent protocol for proving or refuting mathematical statements. Use when trying to prove a mathematical statement with agents, when a claimed lemma keeps dying under scrutiny, or when the true statement itself is still unknown (theory-finding regime).
- Installations / 1h
- 4
- GitHub Stars
- 6
- Mis à jour
- 1 oct.
bootloops-aireading-contract
Sources-only discipline for any instrument or agent that reads documents and asserts facts from them — literature audits, record replays, data extraction, citation of prior work.
- Installations / 1h
- 4
- GitHub Stars
- 6
- Mis à jour
- 1 oct.
bootloops-airef-check
Careful bibliography verification and entry-addition for papers — verify every author, title, journal, volume, pages, year, arXiv ID, and DOI against authoritative online sources (INSPIRE, arXiv, CrossRef/DOI, zbMATH, publisher) before anything enters or stays in a .bib file. Use whenever adding bib entries, auditing a bibliography, checking citations, fixing references, or when asked to "check the references". Encodes the report-then-fix pattern for full-file audits and the folklore-error traps
- Installations / 1h
- 4
- GitHub Stars
- 6
- Mis à jour
- 1 oct.
bootloops-aireferee-sim
Use before circulating any outward-facing scientific document — simulate the strongest standard objection from every audience it claims and verify the document answers each where that reader would look.
- Installations / 1h
- 4
- GitHub Stars
- 6
- Mis à jour
- 1 oct.
bootloops-aitiming-discipline
Compute-planning rules. Use before launching any calculation whose runtime is not already measured — and whenever an agent proposes a long run, an overnight grind, or a bigger machine as the way forward.
- Installations / 1h
- 4
- GitHub Stars
- 6
- Mis à jour
- 1 oct.
bootloops-aitool-stewardship
How the toolkit is consulted, extended, and documented. Use before writing any new code — and after, when a genuinely new instrument has earned its place.
- Installations / 1h
- 4
- GitHub Stars
- 6
- Mis à jour
- 1 oct.
diegosouzapwconfig-codex-cli
Step-by-step agent workflow to configure the OpenAI Codex CLI on any machine (Linux, macOS, Windows) to use OmniRoute as an OpenAI-compatible backend. Detects OS and shell, writes config.toml and 7 named profiles, sets environment variables, and verifies the setup.
- Installations / 1h
- 4
- GitHub Stars
- 72 k
- Mis à jour
- 30 sept.
diegosouzapwomni-budget
Configure spending limits, token quotas, and rate-limit policies per API key or globally. Inspect current consumption and enforce cost controls across providers.
- Installations / 1h
- 4
- GitHub Stars
- 72 k
- Mis à jour
- 30 sept.
slint-uislint
Use when writing, editing, debugging, or reviewing .slint UI code, or wiring it to Rust/C++/JS/Python — the Slint language, layout, compile-time gotchas, interop, and the MCP server for runtime checks.
- Installations / 1h
- 4
- GitHub Stars
- 12
- Mis à jour
- 21 sept.