Every Agent Skill,
One Registry
curl -fsSL askill.sh | shBrowse
Search the registry for skills built by the community.
AI Score
AI scores Safety, Clarity, Reusability, Completeness, and Actionability to filter risky skills.
Install
One command. Works with your agent automatically.
Works with 40+ agents
Write SKILL.md for the user using all available wisdom and documented guidance about how Agent Skills are made. New skills are written carefully to be orthogonal to the existing skills in the same repo.
Princípios do Tailwind CSS v4. Configuração CSS-first, container queries, padrões modernos, arquitetura de design tokens.
Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) u...
Perform systematic code reviews following best practices and team standards
Execute Shopify Admin API calls via GraphQL in Shopify Remix apps. Use when querying or mutating Shopify data (customers, orders, products, shop, segments, subscriptions), when writing GraphQL for the Admin API, or when handling throttling and retrie...
Execute the next task/phase of the PLAN.md — plan, implement, test, commit, and update PLAN.md.
Claude must use this skill whenever it writes, reviews, edits, or suggests a git commit message. This includes: composing a commit message during "commit this" or "save my changes" requests, reviewing or rewriting existing commit messages, preparing...
Restructure existing code — identify smells, plan safe incremental changes, and improve design without changing behavior
Audit TypeScript code for AI-generated noise — redundant comments, verbose documentation, style drift from project conventions, and trivially dead code. Surface-level hygiene pass; defaults to branch diff but supports any scope. Use when: reviewing...
This skill should be used when the user asks to "test this website", "run exploratory testing", "check for accessibility issues", "verify the login flow works", "find bugs on this page", or requests automated QA testing. Triggers on web application t...
Write clear, plain-spoken code comments and documentation that lives alongside the code. Use when writing or reviewing code that needs inline documentation—file headers, function docs, architectural decisions, or explanatory comments. Optimized for b...
Turn requirements or rough ideas into concrete implementation plans with scoped tasks, exact file targets, test strategy, verification commands, and checkpoint flow. Use when work should be planned before coding or when a team needs an actionable bui...
Use when managing GitHub issue labels for user requests, setting priorities, or reporting status to users. Covers priority and status label taxonomy. Trigger with `/eama-label-taxonomy`.
QA an analysis before sharing with stakeholders — methodology checks, accuracy verification, and bias detection. Use when reviewing an analysis for errors, checking for survivorship bias, validating aggregation logic, or preparing documentation for r...
Suggest Conventional Commit message(s) from current changes and provide a copy-ready snippet.
Clean up local git branches that track deleted remote branches. Use when asked to "clean git branches", "remove deleted branches", "prune branches", "cleanup stale branches", or when you see branches marked as "gone" in git status. Works on Windows,...
Refines code changes for better reviewability. Validates change cohesion (no mixed concerns), generates clear commit messages, creates PR/MR with reviewer-focused descriptions. Use when committing, reviewing, creating PR/MR, or mentions "commit", "re...
Elevate projects to production quality using proven patterns. Use when starting a project, reviewing architecture, auditing code, or when user mentions "elevate-code", "production ready", "patterns", "make it production grade".
PRD（Product Requirements Document）を、Universal PRDフォーマット（軽量1ページ〜詳細版まで同じ型）で作成する。 ユーザーが「PRDを書いて」「要件定義書を作って」「仕様をまとめて」「Press Release / FAQ（Working Backwards）を書いて」 「Shape UpのPitchっぽく提案書を作って」「成功指標/KPIとスコープを整理して」などを依頼したときに使う。 出力はMarkdown。必要に応じて1ページ版→標準版→詳細版へ...
UXの「5層モデル（Strategy/Scope/Structure/Skeleton/Surface）」に基づいて、要件〜画面設計を一貫して設計し、 各層の問い・意思決定・成果物をMarkdownで作成するUXデザイナーとして振る舞うSkill。 新規プロダクト/機能のUX設計、既存UXの課題診断、PRD/仕様/画面フロー/ワイヤー/モックの整合性レビューに適用する。 トリガー例: 「UXを5層で設計」「Garrett 5 planes」「戦略/要件/構造/骨格/表層」「ユーザーフロー/サイト...
Unified testing, debugging, and error-fixing skill for backend, database, and frontend. Use when investigating bugs, running tests, analyzing logs, or fixing errors. Consolidates systematic-debugging, testing-patterns, vulnerability-scanner, and weba...
OWASP API Security Top 10 - prevention, detection, and remediation for REST/GraphQL/API security. Use when designing or reviewing APIs - object- and function-level authorization, authentication, rate limiting and resource consumption, sensitive busin...
Connect a new data source to AnomalyArmor. Handles "connect my database", "add snowflake", "setup postgres", "connect warehouse".
Showing 6721 to 6744 of 261.1k results
Command Palette
Search for a command to run...