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
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
Handles experimental features that lack proper ticketing by retroactively creating Linear tickets and PRs from commits. Use when user has made commits without tickets, mentions "founder mode", or asks to formalize experimental work.
Handles experimental features that lack proper ticketing by retroactively creating Linear tickets and PRs from commits. Use when user has made commits without tickets, mentions "founder mode", or asks to formalize experimental work.
Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.
Reviews code changes for bugs, performance issues, security problems, and best practice violations. Use when reviewing PRs, before committing, after making code changes, or when user asks to review, check, or look over code. Catches N+1 queries, miss...
Refactor code to improve quality, apply SOLID principles, remove code smells, and suggest better patterns. Use when improving code structure or modernizing legacy code.
Review configuration, secrets, and environment handling. Checks for safe defaults, secret management, feature flags, and environment parity. Use when reviewing config files, environment variables, or feature flags.
Detect code smells and apply safe refactoring techniques
Design, evaluate, and document software architecture patterns
Reasoning and Acting patterns for agentic LLM workflows
Instrument multi-agent workflows, handoffs, and parent-child relationships
Reviews test coverage and suggests missing test cases for error paths, edge cases, and business logic. Activates when users write tests or implement new features.
ONLY use when user explicitly says 'deep research', 'exhaustive', 'comprehensive report', or 'thorough investigation'. Slower and more expensive than parallel-web-search. For normal research/lookup requests, use parallel-web-search instead.
Deploy applications to production using Vercel CLI commands.
CRITICAL: Use for Makepad GUI screenshot debugging and visual inspection. Triggers on: /screenshot, 截图, 看看UI, 查看界面, capture makepad, run and capture, 运行并截图, 看看效果, UI截图, 界面截图, screenshot makepad, capture app, 截取应用, bring to front
Expert Agent Brain skill for document search with BM25 keyword, semantic vector, hybrid, graph, and multi retrieval modes. Use when asked to "search documentation", "query domain", "find in docs", "bm25 search", "hybrid search", "semantic search", "g...
定位 JS 中参数的生成入口。当用户问"xxx 参数在哪生成"、"找加密入口"、"定位签名函数"、"请求参数怎么加密的"时使用
Use this skill when starting a new project or adding AgenticDev to an existing project. Scaffolds the directory structure (docs/specs, docs/changes) and configuration files needed for the spec-driven development workflow.
Scaffold a new SKILL.md file following the agentskills.io open format. Use when asked to create a new skill, package a capability, or codify a process. Produces a correctly structured skill with frontmatter, progressive disclosure, and optional refer...
Rebase an existing GitHub PR branch onto the repository default branch. Use when Codex needs to fetch the latest default-branch history, keep the local default branch current when that is safe, rebase the current feature branch, resolve straightforwa...
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers sessio...
CMAP Validation Suite v8.0.0 - 36 validators, 165 error codes across 7 categories for Power Platform deployments. ZERO WARNINGS POLICY: All checks are PASS or FAIL only. Triggers: "/validate", "validate solution", "CMAP validation", "import failed".
Manage Railway deployments, view logs, check status, and manage environment variables. Use when working with Railway hosting, deployments, or infrastructure.
Showing 6769 to 6792 of 261.1k results
Command Palette
Search for a command to run...