菜单
Helps users discover and install agent skills from the open agent skills ecosystem. Use when the user asks "how do I do X", "find a skill for X", "is there a skill that can...", or expresses interest in extending capabilities with specialized tools or workflows.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | find-skills |
| description | Helps users discover and install agent skills from the open agent skills ecosystem. Use when the user asks "how do I do X", "find a skill for X", "is there a skill that can...", or expresses interest in extending capabilities with specialized tools or workflows. |
This skill helps you discover and install skills from the open agent skills ecosystem.
Use this skill when the user:
The Skills CLI (npx skills) is the package manager for the open agent skills ecosystem. Skills are modular packages that extend agent capabilities with specialized knowledge, workflows, and tools.
Key commands:
npx skills find [query] - Search for skills interactively or by keywordnpx skills add <package> - Install a skill from GitHub or other sourcesnpx skills check - Check for skill updatesnpx skills update - Update all installed skillsBrowse skills at: https://skills.sh/
When a user asks for help with something, identify:
Run the find command with a relevant query:
npx skills find [query]
For example:
npx skills find react performancenpx skills find pr reviewnpx skills find changelogThe command will return results like:
Install with npx skills add <owner/repo@skill>
vercel-labs/agent-skills@vercel-react-best-practices
└ https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices
When you find relevant skills, present them to the user with:
Example response:
I found a skill that might help! The "vercel-react-best-practices" skill provides
React and Next.js performance optimization guidelines from Vercel Engineering.
To install it:
npx skills add vercel-labs/agent-skills@vercel-react-best-practices
Learn more: https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices
If the user wants to proceed, you can install the skill for them:
npx skills add <owner/repo@skill> -g -y
The -g flag installs globally (user-level) and -y skips confirmation prompts.
When searching, consider these common categories:
| Category | Example Queries |
|---|---|
| Web Development | react, nextjs, typescript, css, tailwind |
| Testing | testing, jest, playwright, e2e |
| DevOps | deploy, docker, kubernetes, ci-cd |
| Documentation | docs, readme, changelog, api-docs |
| Code Quality | review, lint, refactor, best-practices |
| Design | ui, ux, design-system, accessibility |
| Productivity | workflow, automation, git |
vercel-labs/agent-skills or ComposioHQ/awesome-claude-skillsIf no relevant skills exist:
npx skills initExample:
I searched for skills related to "xyz" but didn't find any matches.
I can still help you with this task directly! Would you like me to proceed?
If this is something you do often, you could create your own skill:
npx skills init my-xyz-skill
Find commits on `master` that have not been released yet, map each author to their Slack user ID via email, and draft a Slack message pinging them for prod-release sign-off. Use when the user asks to "check unreleased commits", "ping authors before prod release", or "who hasn't signed off on the release yet" for a GitLab-hosted repo (e.g. dashboard-v4).
Conventions for building components in Aircall's UI libraries — @aircall/ds (design system, Tailwind 4 + Base UI) and @aircall/blocks (higher-level compositions) — as they live in the Aircall Hydra monorepo. Use when adding or refactoring a component in packages/ds or packages/blocks, deciding between a compound component and a prop, wiring variants, polymorphism, or exports. Triggers on "build a DS component", "add a block", or work touching packages/ds / packages/blocks inside Hydra.
Fix a broken Playwright e2e test by reproducing the failure in a real browser FIRST and capturing the live UI, then editing the test once - instead of the blind edit-rerun-repeat loop. Use when an Aircall Playwright e2e test is failing/flaky, a CI e2e job is red, or on "fix this broken test". Leans on agent-browser-aircall-local for auth + portless URLs. Guards against masking a real product regression by editing the test to pass.
Browse Aircall staging or local dev URLs with automatic authentication. USE THIS skill (not the generic agent-browser skill) whenever the target URL contains "aircall" in the hostname (e.g. dashboard.aircall-staging.com, localhost running Aircall).
Orchestrates Kento's per-ticket dev loop end-to-end: optional Jira ticket → create/reuse a git worktree → implement → debug in the browser → commit, push, open the MR → optionally watch the pipeline. Runs autonomously through setup and implementation, then STOPS at a readiness gate before shipping. Use when the user wants to start work on a ticket/feature/fix, "spin up a worktree and implement", "take this from ticket to MR", or kick off the dev flow. Delegates each step to existing skills — it does not reimplement them.
Drive a fast-forward GitLab "merge train" on Aircall repos — merge a set of approved MRs one-by-one (rebase → arm merge-when-pipeline-succeeds → poll → merge), handling approval-resets, Cursor Bugbot gates, rebase conflicts, and flaky E2E retries. Supervised, CI-paced, human-gated. Use after aircall-react-doctor-pipeline produces Ready MRs, or whenever the user asks to "watch and merge" any batch of approved MRs on an Aircall GitLab repo whose merge_method is ff. Repo-agnostic within Aircall (reads merge settings dynamically); not react-doctor-specific.