热门技能
当前社区里最受关注、增长最快的技能。
apple-reminders
joecastelino
Manage Apple Reminders via remindctl CLI (list, add, complete, delete).
markdown-style
kbrdn1
Skill migrated from _fragments/docs/markdown-style
speckit.checklist
kbrdn1
Generate a custom checklist for the current feature based on user requirements.
feature-block-design
taika-izumi
"brainstorming で合意した全体方針を、疎結合な機能ブロックに分割し、各ブロックの詳細仕様をディレクトリ分割形式（docs/current/specs/YYYY-MM-DD-<topic>/）で作成または更新する。brainstorming と writing-plans の間で発動する。"
ask-cloudflare-to-claude-fix
OpenSourceAGI
Guide to cloudflare-to-claude-fix (packages/cloudflare-to-claude-fix), the Cloudflare Queue consumer that fires a Claude Code routine when a Workers build fails — creating the queue and DLQ, enabling build Event Subscriptions, the routine /fire API and its beta header, the ROUTINE_FIRE_URL / ROUTINE_FIRE_TOKEN / NOTIFY_WEBHOOK_URL secrets, retries, and local testing. Use when working with this Worker or troubleshooting it — routines that never fire, 400/401/403/404/429 from the fire endpoint, messages piling up in the dead-letter queue, or build events that never reach the consumer.
speckit.implement
kbrdn1
Execute the implementation plan by processing and executing all tasks defined in tasks.md
me:create-loop
kbrdn1
Utiliser quand l'utilisateur veut CRÉER ou définir un nouveau loop auto-cadencé (pas en lancer un existant). Conçoit un loop SUR MESURE (closed-loop discovery→planning→execution→verification→iteration), demande la portée (globale ~/.claude ou per-project <repo>/.claude) et les dimensions (mode closed/open, trigger self-pace/stop-hook, single/fleet) si non précisées, puis scaffolde la skill me:loop:<name> + sa commande /me:loop:<name> (+ hook si stop-hook).
testing-template
AtomiCloud
Test this CyanPrint template. Use when the user asks to write tests, add test cases, update snapshots, or debug template test failures. Covers test.cyan.yaml format with answer_state, deterministic_state, validate commands, and expected output.
ask-app-store-buttons
OpenSourceAGI
Guide to the app store download badges in packages/react-app-store-buttons — rendering DownloadAppButton for iOS, Android, Chrome, macOS, Windows, Linux and Snap, appId vs href, native deep links, autoHighlight OS detection, badge sizing, the styles import, and the getOS/buildStoreUrl/buildDeepLink helpers. Use when working with these buttons or troubleshooting them — a badge that doesn't render, the wrong package name on install, deep links that don't open the store app, highlight not matching the user's OS, or SSR/hydration mismatches from userAgent detection.
hyperframes-core
Sma1lboy
"The HyperFrames composition contract — build one renderable project. Use for composition structure, the data-* timing attributes, class=\"clip\", tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML."
r3f-best-practices
zebbern
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
start-work
taika-izumi
"新しい作業（新規開発、改修、デバッグ、レビュー、調査など）を開始する起点スキル。セッション継続チェック、状況診断、次手ナビゲーションを行い、横断関心（handoff更新、ADR検出、不可逆操作レビュー）を一貫して適用する。"
agent-skill-management
prateek
Manage agent-marketplace packages, reviewed APM caches and patches, plugin materialization, and Claude, Codex, Cursor, or pi activation in this dotfiles repo. Use for skill imports or edits, package policy, the console's guarded edits, apply hooks, and related architecture docs.
code-vuln-audit
zebbern
"Scan code for security issues: dependency vulnerabilities (npm/pip audit), secret leaks (regex and entropy analysis), and OWASP anti-patterns like SQL injection, XSS, or command injection. Use when the user mentions security scans, vulnerability detection, secret leaks, API keys, OWASP, npm audit, pip-audit, hardcoded passwords, or code security checks."
disk-space-triage
automationjp
Find out why a disk is full and what can safely be freed, using the HyperDU scanner. Use when a drive is out of space, a build fails with "no space left on device", or the user asks what is using their disk, which directories are largest, or what is safe to delete. Covers per-volume free space, largest-directory scans, and separating regenerable build output (Cargo target, node_modules, virtualenvs) from data that cannot be rebuilt.
me:loop:claude-review-pr
kbrdn1
Loop auto-cadencé — relance une review par agent Claude (spawné depuis la session, effort high minimum) sur la PR de la branche courante et corrige jusqu'à 0 finding bloquant pertinent (P0/P1/P2), max 8 itérations, avec analyse de convergence pour s'arrêter quand les passes n'apportent plus rien. Déclencheurs : "/me:loop:claude-review-pr", "lance le loop claude-review-pr", "review claude jusqu'à ce que la PR soit clean".
land-changes
prateek
Land a finished dotfiles branch onto master the way Prateek does it — no PRs, linear history, one commit per change. Use when the user says "land", "ship it", "land this branch", "merge into master", "ff-only merge", or "push to master". Rebases the branch onto the latest master, squashes to one commit, runs the checks for that diff, fast-forward-only merges into the ~/dotfiles checkout, and pushes. Then confirms chezmoi's source is ~/dotfiles and summarizes what a chezmoi apply would change — it does not apply chezmoi unless asked. Not for GitHub PRs (this repo lands locally), creating worktrees (Orca owns those), or landing in other repos.
jay-google-sheets-drive-access
joecastelino
Access Joe's Google Sheets and Drive files from Jay's profile — token symlink bootstrap, reading/writing native Sheets, downloading Drive-hosted .xlsx files (like AMG WIP.xlsx) via alt=media, and the xlsx-vs-native-Sheet write limitation. Established 2026-08-02.
writing-template-dotnet
AtomiCloud
Write or modify CyanPrint template code in C#. Use when the user asks to add prompts, change template logic, modify the entry point, add processors/plugins/resolvers, or change generated output for a C#/.NET template. Covers IInquirer question types (Text, Select, Checkbox, Confirm, Password, DateSelect), processor configuration, and IDeterminism for non-deterministic values.
agent-designer
youlianvr
"Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use orchestrator)."
me:release
kbrdn1
"Publier une version : migration du changelog vers changelogs/<version>.md, bump des fichiers de version, merge dev → main, tag APRÈS le merge, release GitHub (CI sur tag ou gh release create), propagation post-release. Protocole générique, extrait du /release de bijouterie-julian et du flow réel de gwm-cli. À utiliser dès qu'il s'agit de sortir/publier une version, taguer, faire une release, propager dev vers main, ou préparer un changelog de release. Remplace l'ancien /generate-changelog. Triggers: /me:release, release, publier une version, sortir une version, cut a release, tag, bump version, propager dev main, changelog de release."
llm-wiki
prateek
The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources → wiki → schema). Also use when discussing knowledge management strategy, wiki structure decisions, or how to organize distilled knowledge. This is the "theory" skill — other skills handle specific operations (ingesting, querying, linting).
codebase-context
Barnett-Studios
"Use when the user asks about codebase structure, architecture, what a project does, how components relate, or needs project-wide context to answer a question."
algorithmic-art
anthropics
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.