热门技能
当前社区里最受关注、增长最快的技能。
speckit.clarify
kbrdn1
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
benchmark-zsh-startup
prateek
Benchmark and attribute zsh startup and prompt latency. Use when asked to profile a slow zsh prompt, explain where shell startup time is spent, compare zsh-bench with zprof or xtrace, or decide which zsh plugin, hook, or startup file to optimize first. Also use when the task is to track which zsh features, widgets, completions, or plugin-provided commands are actually being used.
a11y-audit
youlianvr
"Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines."
seo-checklist
AGilbertDev
On-page SEO checklist for Nuxt pages, covering useSeoMeta, structured data, sitemap, robots, Core Web Vitals hints, and hreflang. Use when a public page ships or the user asks to improve search visibility.
me:loop:rgaa-until-clean
kbrdn1
Loop auto-cadencé — relance l'audit d'accessibilité automatisé (axe-core / pa11y) sur les routes modifiées, corrige les violations via la skill me:rgaa, et reboucle jusqu'à 0 violation automatiquement détectable, max 6 itérations. Déclencheurs : "/me:loop:rgaa-until-clean", "lance le loop rgaa-until-clean", "boucle a11y jusqu'à clean", "corrige l'accessibilité jusqu'à ce que axe passe".
speckit.install
kbrdn1
Bootstrap the SpecKit spec-driven development system into any project directory.
ask-server-shell-setup
OpenSourceAGI
Guide to server-shell-setup (packages/server-shell-setup), the one-command dev-environment bootstrap for fish, nushell, nvim, helix, node via Volta, bun, docker, starship, code-server and more — interactive vs unattended installs, selecting individual components, the fish aliases it adds, and the supported distros. Use when working with server-shell-setup or troubleshooting it — the installer aborting on a fresh server, sudo or password prompts, a shell that doesn't become the default, docker rootless issues, or components that silently skip on an unsupported distro.
Skill: 选题分析
frankfika
至少评估 5 个备选话题
writing-resolver-dotnet
AtomiCloud
Write or modify CyanPrint resolver code in C#. Use when the user asks to change conflict resolution logic, modify merge strategies, handle file origins, or change resolution behavior. Covers entry point (CyanEngine.StartResolver), ResolverInput/ResolverOutput, ResolvedFile, and FileOrigin. Must ensure commutativity and associativity (sort, unique, deterministic ordering).
doc-generator
luongnv89
Генерація вичерпної, точної документації API з вихідного коду. Використовуйте при створенні або оновленні документації API, генерації специфікацій OpenAPI, або коли користувачі згадують документацію API, ендпоінти чи документацію.
motion-graphics
Sma1lboy
"Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s and up to ~30s, with no live-action subject. Can render to MP4 or transparent overlay. Not for longer, multi-scene, or brand-reel pieces (use general-video), topic explainers (faceless-explainer), PR videos (pr-to-video), or captions on existing footage (embedded-captions). When unsure whether it's a quick motion-first piece or a longer treatment, see /hyperframes.\n"
create-agent
kbrdn1
Cree un nouvel agent Claude Code (.claude/agents/) avec role, outils, modele et permissions
amg-wip-payroll-vs-rth-analysis
joecastelino
Analyze an AMG per-store semi-monthly WIP workbook (tech payroll vs RTH / labor relieved to WIP) and produce Joe's service-manager meeting prep — trend table, per-tech gap ranking, talking points, recoverable-$ target. First run 2026-07-08 on "2026- SCWV Wip.xlsx" (Stevens Creek VW); Joe approved the format verbatim.
documenting-resolver
AtomiCloud
Document this CyanPrint resolver into README.MD. Use when the user asks to document the resolver, write a README, explain conflict resolution strategy, or describe merge behavior. Reads cyan.yaml and entry point code to extract config schema and resolution logic.
image-video-helper
403name
Image and video processing guide for Node.js and Python. Suggests packages for manipulation, encoding, analysis, and transformation. Use when building media processing pipelines, thumbnails, video editors, or computer vision features.
banner-repo
kbrdn1
Génère une bannière promo de repo (PNG dark + light) au thème "Claude Dark" — générique et adaptable au repo (wordmark, tagline, features, install, + un motif à droite : graphe de branches intégré ou HTML/SVG custom). Pour le haut de README d'un projet. Déclencheurs : "bannière repo", "banniere projet", "repo banner", "promo repo", "banner readme projet", /me:banner-repo.
agent-reach
youlianvr
'MUST USE when user wants to research/search/look up anything on the internet — e.g. research X / look up X /
quebec-french
AGilbertDev
Rules for writing Québécois French copy, including the U+00A0 no-break space before ? ! : ; and how to check it. Use before writing or reviewing any French UI copy, locale file, or French prose.
pipeline-blueprint
zebbern
"Provide CI/CD best practices and pipeline templates for GitHub Actions and GitLab CI, recommending configurations based on project type (frontend, backend, fullstack, library, monorepo, mobile). Trigger when users ask about setting up CI/CD, automating builds, improving pipelines, or mention keywords like GitHub Actions, GitLab CI, pipeline templates, or deployment automation."
owasp-review
DonArtkins
"OWASP Top-10 basics review for the Griot estate: injection (parameterized SQL), broken auth (refresh rotation), sensitive data (no localStorage tokens), CORS allow-list, AI principal scope."
aggg2-persona
youlianvr
Use for ANY communication with the user — how to speak and respond: when to explain simply and step by step, when briefly, how to react to a difficult situation, how to verify your own answers, how to reduce the interlocutor's load, how not to pass guesses off as facts. Covers: tone and style (calm, human, no sugarcoating), adaptation to the interlocutor (pace, level, mood), "explain step by step" mode, how to explain complex things (audience → layers → analogy → comprehension check), visual presentation (tables, hierarchy, highlighting, diagrams), importance of no hallucinations (fact checking, "verify" instead of guessing), testing answers through a beginner's eyes, answer structure (result first, next step last). Not for techniques (web-research-camoufox, db-first-search) — this skill is about HOW to speak.
general-video
Sma1lboy
"The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand / sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a website, a topic explainer, a GitHub PR, existing footage, a short motion graphic, or a Remotion port — prefer it (see /hyperframes); use this only as the general fallback when none fit.\n"
compliance
AGilbertDev
AGilbertDev's universal privacy, security, and minimum-legal baseline for every project — Québec Law 25 + Charter of the French Language (Law 101/96), PIPEDA, GDPR/UK GDPR, US state laws, COPPA, CASL/CAN-SPAM, consumer protection, accessibility (WCAG/EAA), IP & asset licensing, and digital-sales tax. Security baseline — secrets, encryption, auth, dependency & input hygiene. Use when building anything that collects data, sends email, sells to consumers, uses third-party IP/assets, or needs legal pages/consent. REQUIRED baselines. Store-specific rules (Google Play, App Store) are PROJECT-level — see the project's PLAYSTORE.md, not this skill.
academy-guide
anthropics
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.