GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
cogbox-remote-access
Connect to this sandbox from outside with SSH, VS Code, scp, sftp, port forwards or mosh, and explain what users it is shared with can and cannot do.
cogbox-packages
Get a missing tool or language library, keep tools across restarts, or change services, environment variables or other NixOS configuration through a plugin module, and find out who installs it.
cogbox-network
Use whenever a fetch, curl, git clone, download or connection fails (refused, TLS EOF, empty reply, cert error) to diagnose egress and injected credentials, ask for access, or call the cogworx API.
cogbox-git
Clone, fetch or push repositories, call the git host API (merge requests, issues, pipelines) through host-held credentials, find granted repos, decode denials and know what to ask the owner for.
cogbox-filesystem
Decide where to write inside the sandbox so work survives a restart, and check a path's lifetime instead of assuming it.
cogbox-environment
Identify whether this sandbox runs locally or through cogworx before giving host, browser, or lifecycle instructions.
app-relay
Start a loopback web service and explain browser access in local cogbox or managed cogworx, including previews, notebooks and dev servers, and who can open it.
weekly-digest
CronFoundry smoke-test skill
hello-checker
Use this skill when asked to "verify", "check", or "validate" a file's existence and content. It provides a reliable workflow for confirming files meet their spec.
ask-skill
暂无简介
html-review-artifact
Framework-wide guidance for crafting polished human-review artifacts as markdown or HTML
converge-planning
Design a Converge playbook end-to-end. Use when the user says "plan a project", "design a playbook", "decompose into tasks", "scaffold a Converge workflow", "onboard to Converge", or asks how to write TASK.md / playbook.yml. Two entry points: plan a new playbook or update an existing one. Hand off to `/converge-control` after producing the playbook structure.
converge-control
Operate a Converge playbook end-to-end — start runs, monitor progress, narrow failures with `--select`, inspect runtime state, validate definitions, surgically reset subtrees, and stop stuck or orphaned runs. Use this skill whenever the user says "run my playbook", "execute this", "monitor the run", "converge failed", "the run is stuck", "retry failures", "babysit this playbook", "what's the status?", "show me the gantt", or asks how to use `converge run` / `--select` / `inspect` / `doctor` / `clean` / `stop`. Also use it for `HTTP 401` / `Invalid API key` failures on the first task — those are environment-not-playbook problems — and for any post-run cleanup work. Hand off to `converge-planning` if the user wants to design or restructure the playbook itself.
repair-taskts
Fix task.ts definition issues — Seed syntax, missing .build(), empty checks, import errors, TypeScript errors
repair-spawn-intermediate
Generate a new intermediate task when no existing task produces a required output
repair-skillmd
Fix SKILL.md frontmatter and structure issues — missing name, outputs, checks, malformed YAML
repair-router
Triage — diagnoses gap root cause and routes to the correct repair skill
repair-missing-output
Produce missing output files by reading the task definition and executing the required work