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
@microsoft
openclaw
@openclaw
OpenAI
@openai
The Apache Software Foundation
@apache
GitHub
@github
Anthropic
@anthropics
AutoGPT
@Significant-Gravitas
Garry Tan
@garrytan全部 Skills 196935
opsward-diagnose
Diagnose the health of this project's AI agent setup. Use when the user asks to check, audit, or score the project's CLAUDE.md, skills, docs, or agent configuration.
opsward
Run opsward to assess and improve this project's AI agent setup. Use when the user says 'opsward', 'check my setup', 'improve my AI config', or wants a full audit and remediation.
opsward-subagents
Decide which of a repo's skills should also run as subagents (in their own context), declare it in each skill's frontmatter, and generate or refresh the twin agent files with opsward. Use when a skill does bulky or read-heavy work whose output should stay out of the main context, when a skill needs a tool restriction or a cheaper model, when a hand-written agent duplicates a skill, when `opsward maintain` reports a `subagent_twin` finding, or when asked "should this skill be a subagent", "make this skill usable as a subagent", "generate agents from skills", or to sweep a repo for skill/agent pairs. Also usable as a subagent itself.
opsward-maintain
Check documentation and AI setup for staleness, drift, or inconsistency. Use when the user asks to maintain, refresh, or update project docs and AI configuration.
opsward-generate
Generate missing AI setup artifacts for this project. Use when the user asks to scaffold, create, or bootstrap CLAUDE.md, docs, skills, or agent configuration.
opsward-diagnose
Diagnose the health of this project's AI agent setup. Use when the user asks to check, audit, or score the project's CLAUDE.md, skills, docs, or agent configuration.
opsward-dev
Contributor guide for developing opsward itself — its architecture, hard invariants, and where each kind of change goes. Use when modifying opsward's own source (scan/score/generate/maintain/recommend/cli), adding a template, scoring dimension, or skill recommendation, or when unsure which module owns a change. NOT for running opsward on a target project (use the `opsward` skill for that).
opsward-add-template
Add or edit a generation template in opsward — a doc template (architecture.md, testing.md, …), an installable skill (SKILL.md), or an agent definition — and wire it into generate.py so opsward produces it. Use when adding a new artifact opsward should scaffold into target projects, adding a template variable, or changing what `opsward generate` / `install-skills` emit. Covers string.Template rules and the python/jsts/shared layout.
opsward-add-scoring
Add or adjust opsward's quality scoring — a CLAUDE.md sub-dimension, a whole weighted component, or the skill/spec validation rules — in score.py. Use when changing how `opsward diagnose` grades a project, tuning weights or point thresholds, adding a new ComponentScore, or modifying validate_skill_spec. Explains the pure-function contract, the weighting math, and the constants to keep balanced.
opsward-add-scan-field
Add a new fact that opsward learns about a target project — a field on ScanResult populated by scan.py — and consume it downstream in score/generate/maintain/recommend. Use when a new check, score, template variable, or drift detector needs data the scan does not yet collect (a new config file, a new .claude/ inventory, a project signal), or when changing project-type detection. Covers the read-only contract, the dataclass-default rule, the util read helpers, and the CLI goldens a scan change can move.
opsward-add-recommendation
Add a tech-stack→skill mapping to opsward's recommendation engine in recommend.py, so `opsward recommend` suggests an ecosystem skill when it detects a dependency or framework (e.g. Supabase, FastAPI, Tailwind). Use when extending the curated `_RECOMMENDATIONS` list, adding a new detection signal, or changing where recommended skills are sourced from.
opsward-add-drift-check
Add a new staleness or drift check to opsward's maintain stage (maintain.py), so `opsward maintain` reports a new kind of MaintenanceSuggestion — a stale reference, an out-of-sync index, an outdated or empty doc, an incomplete skill. Use when extending what `opsward maintain` detects, adding a suggestion category, or deciding whether a finding belongs in maintain or in the diagnose score. Covers the check-generator shape, categories, the diff field, the exit-code contract, and the CLI golden it can move.
upstream-fix
Traces quality failures upstream to spec, rule, or workflow root cause. Proposes fixes at the right level.
triage
Dedup gate + batch-classify observations into five classes, enrich ARTIFACTs, batch-approve, delegate to intake/decision or queue.
sprint-planning
Sprint planning — story selection, team composition, Gherkin specs, and visual companion plan gate for developer sign-off.
sprint-manager
Sole writer of stories/index.json and sprints/index.json — validates state transitions, activates sprints, manages epic membership.
sprint-dev
Sprint execution — dependency-driven story development, post-merge AVFL, and team review.
retro
Sprint retrospective — transcript audit engine (dynamic Workflow), story verification, findings document, and sprint closure.