Skills MCP Plugins Subagents

Browse by category

DevOps & CI/CD Skills Productivity & Workflow Skills Other Skills Product & Project Management Skills Documentation & Knowledge Skills Code Review & Refactor Skills Backend & APIs Skills Agent Meta & Communication Skills Research Skills Security Skills UX UI & Design Skills Testing & QA Skills See all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →

Agent Skills MCP Servers Plugins Subagents Coding Agents

Collections Official publishers Glossary FAQ Blog Search Saved Feedback

Privacy Terms llms.txt Sitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/agent-sh/agnix

home/skills/agent-sh/agnix

agent-sh/agnix

31 skills · 40 total installs

$npx skills add agent-sh/agnix

SkillInstalls

agnixUse when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'.40 agent-without-contextUse when testing agent without context validation—argument-hint-no-argsUse when testing argument hints—code-reviewUse when user asks to review code for quality and security issues.—context-without-agentUse when testing context without agent validation—deep-referenceUse when validating deep references—deploy-prodDeploys to production—fork-no-instructionsUse when looking up documentation—fork-with-instructionsUse when analyzing code quality—indexed-arguments-no-hintUse when validating indexed arguments—invalid-agent invalid-context invalid-hooks invalid-model invalid-name name-directory-mismatch social-source-evidenceUse when reviewing X/Twitter exports as source evidence for social content decisions.—string-boolean-disable string-boolean-invocable test-skillUse when testing per-client skill rules—too-many-injections unknown-frontmatter-field unknown-tool unreachable-skill vague-name windows-path with-argument-hintUse when greeting users—with-context-agentUse when testing valid context and agent configuration—with-custom-agentUse when testing custom agent validation—with-hooksUse when testing valid hooks—with-modelUse when testing valid model configuration—