Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
49,534 skills from 2,407 repositories · updated 44 minutes ago
10,681 skills
- 都市悬疑-设计事件案件引擎lornshrimp/Lorn.NovelWriteSkills用于【都市悬疑】题材下的单元案、事件母板与案件供血设计。作为题材包装层与路由层，负责保留都市悬疑标准入口名，并明确要求优先强制加载并使用 `通用-设计事件案件引擎`。OtherNo warnings★ 249↓ —
- 异能志怪-输出微信订阅号版lornshrimp/Lorn.NovelWriteSkills用于【异能志怪】题材下的微信订阅号平台输出任务。作为题材包装层、兼容入口与路由层，负责保留异能志怪入口、补充连续追更与民俗悬念边界，并明确要求优先强制加载并使用 `通用-输出微信订阅号版`。关键词：异能志怪微信订阅号版、公众号连载、民俗悬念、微钩子。OtherNo warnings★ 249↓ —
- 都市悬疑-大纲审阅优化闭环lornshrimp/Lorn.NovelWriteSkills用于【都市悬疑】题材下的提纲审阅优化 SOP 编排。作为题材包装层、兼容入口与路由层，负责保留都市悬疑入口名，并明确要求优先强制加载并使用 `通用-大纲审阅优化闭环`，同时按总纲 / 分卷对象分流到对应题材审阅与设计 Skill。OtherNo warnings★ 249↓ —
- 都市悬疑-输出纵横小说版lornshrimp/Lorn.NovelWriteSkills用于【都市悬疑】题材下的纵横小说网平台输出任务。作为题材包装层、兼容入口与路由层，负责保留都市悬疑入口、补充证据链条与人性落点边界，并明确要求优先强制加载并使用 `通用-输出纵横小说版`。关键词：都市悬疑纵横版、纵横中文网、中等节奏、现实锚点、职业流、民俗流。OtherNo warnings★ 249↓ —
- 通用-平台签约评估框架lornshrimp/Lorn.NovelWriteSkills用于以默认极严、保守、负面证据优先的口径评估作品在目标平台的签约或过稿潜力。适合统一承接评估流程骨架、分阶段准入评估、材料完整度判断、评分维度、概率区间、封顶与一票否决规则，并兼容竞争位 / 竞品威胁评估语境。评估{目标平台}项目时，强制要求使用多种可用网络搜索工具检索{目标平台}同题材 TopN 候选池（起点默认按起点中文网榜单检索，其他平台按可用性调整），并按 "TopN 候选池 + 3–5 主压制样本 + 四层竞对拆解"做从严对照。目标平台路由优先级：用户显式指定 > Agents.md 主输出平台 > 默认回退起点中文网。关键词：平台签约评估、极严评估、分阶段准入评估、总纲预评估、分卷预评估、正文准入、过稿潜力、签约概率评估、概率区间、一票否决、竞品威胁评估、评估报告、榜单对照。"OtherNo warnings★ 249↓ —
- benchmarknota-america/forgecat-agent-profilesPerformance regression detection. (gstack)OtherNo warnings★ 93↓ —
- AI科幻-大纲审阅优化闭环lornshrimp/Lorn.NovelWriteSkills用于【AI科幻】题材下的提纲审阅优化 SOP 编排。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口名，并明确要求优先强制加载并使用 `通用-大纲审阅优化闭环`，同时按总纲 / 分卷对象分流到对应题材审阅与设计 Skill。OtherNo warnings★ 249↓ —
- 异能志怪-管理连续性冷热线lornshrimp/Lorn.NovelWriteSkillsUse when: 连续性控盘、动态状态、冷热线、伏笔超期、人物回归压力、关系桥接、时间线连贯、线索失温、章节后写回、忘线预警。常见说法：帮我看哪些线快忘了、这几章哪些人物该回来了、哪些伏笔超期了、写完这章后更新动态状态、看中段有没有失温。OtherNo warnings★ 249↓ —
- AI科幻-多平台小说适配lornshrimp/Lorn.NovelWriteSkills用于【AI科幻】题材下的多平台适配策略。作为题材包装层与兼容入口，负责保留AI科幻入口名、补充异常数据、系统摩擦、数字压迫感与长期谜团在各平台的保真边界，并明确要求优先强制加载并使用 `通用-多平台小说适配`。关键词：AI科幻多平台适配、平台差异、改写前推演、平台保真。OtherNo warnings★ 249↓ —
- 都市悬疑-小说项目初始化lornshrimp/Lorn.NovelWriteSkills用于【都市悬疑】题材下的项目级战略初始化——在选定平台后、设计大纲之前，补充都市悬疑特有的职业切口、异常证据体系、城市空间压迫感、现实代价锚点与平台适配偏好。作为题材包装层与路由层，强制加载并使用 `通用-小说项目初始化`。OtherNo warnings★ 249↓ —
- eni-burp-mcpalicewe1/alice_skill全局自动路由 | Burp Mcp reference and toolingOtherNo warnings★ 62↓ —
- deadpan-doodleshaorantang97/LabArt用通透的钢笔淡水彩画有冷幽默、童趣和反常比例的插画，适用于人物 IP、猫狗、花草、物件和小场景，也可局部修改已选作品。真人头像走专用模块；不用于写实肖像或精致萌系插画。OtherNo warnings★ 290↓ —
- quality-debt-analysisnaodeng/awesome-qa-skillsUse this skill when you need evidence-bounded quality-debt items, origins, impact, age, priority, ownership, and paydown tradeoffs; triggers include 质量债务 and quality debt.OtherNo warnings★ 297↓ —
- ca-releasearbiterForge/codeArbiterPrepare a declared release target, or preview it with --dry-run. Derive its version and require authorization before publication.OtherReview first★ 151↓ —
- performance-trace-guideproflead/codex-skills-libraryGuide collection and analysis of performance traces. Use when a mid-level developer needs to diagnose slowness.OtherNo warnings★ 167↓ —
- voice-clone-ttsNanmiCoder/creator-pipeline将文案与用户自己的参考录音合成为配音、SRT 和可交接时间轴。默认使用 MiniMax 与用户自己的音色；可显式选择免费本地 Qwen3-TTS（Apple Silicon 用 MLX）或 Nano CPU。适用于口播配音、声音复刻，以及为网页视频演示准备最终音频和字幕。OtherNo warnings★ 72↓ —
- error-message-explainerproflead/codex-skills-libraryExplain compiler/runtime errors in plain language. Use when a junior developer needs help understanding an error message.OtherNo warnings★ 167↓ —
- performance-budgetingproflead/codex-skills-libraryDefine performance budgets and guardrails. Use when a senior developer needs performance targets and enforcement.OtherNo warnings★ 167↓ —
- incident-postmortemproflead/codex-skills-libraryDraft an incident postmortem with timeline, RCA, and action items. Use when a senior developer needs a structured post-incident report.OtherNo warnings★ 167↓ —
- codebase-orientationproflead/codex-skills-libraryGuide quick orientation of an unfamiliar codebase with module mapping, entry points, and local run steps. Use when a junior developer needs to get situated fast.OtherNo warnings★ 167↓ —
- caching-strategy-helperproflead/codex-skills-libraryRecommend caching strategies and invalidation patterns. Use when a mid-level developer needs performance guidance.OtherNo warnings★ 167↓ —
- go-namingcxuu/golang-skillsUse when naming any Go identifier — packages, types, functions, methods, variables, constants, or receivers — to ensure idiomatic, clear names. Also use when a user is creating new types, packages, or exported APIs, even if they don't explicitly ask about naming conventions. Does not cover package organization (see go-packages).OtherNo warnings★ 190↓ —
- skill-stocktakemturac/everything-openai-codexUse when auditing Codex skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.OtherNo warnings★ 75↓ —
- continuous-learningmturac/everything-openai-codex[DEPRECATED - use continuous-learning-v2] Legacy v1 stop-hook skill extractor. v2 is a strict superset with instinct-based, project-scoped, hook-reliable learning. Do not invoke v1; route continuous learning, session learning, and pattern extraction requests to continuous-learning-v2.OtherNo warnings★ 75↓ —
automation-roi-analysis
naodeng/awesome-qa-skills
OtherUpdated 2 days ago
From the author
Use this skill when you need evidence-bounded automation candidates, build/run/maintenance costs, benefit assumptions, time horizon, and sensitivity; triggers include 自动化投资回报 and automation ROI.
Install
npx skills add naodeng/awesome-qa-skills --skill automation-roi-analysis -a claude-code
Installs to .claude/skills/automation-roi-analysis/ · Each command fetches the skill straight from GitHub with the open skills CLI.
No download: this skill’s licence (Custom or unclear) does not let us redistribute its files. The install commands fetch them from GitHub instead.
What it can touch
Runs bundled scriptsNo network use seenLicence: Custom or unclear
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 74
Security85
Provenance70
Maintenance100
Licence45
Adoption41
Files (14)
- SKILL.md
- agents/openai.yaml
- evals/cases/basic-success.yaml
- evals/cases/domain-method-regression.yaml
- evals/cases/edge-incomplete-input.yaml
- evals/cases/edge-scope-boundary.yaml
- evals/eval.yaml
- evals/fixtures/check-domain-decisions.sh
- evals/fixtures/check_domain_decisions.py
- evals/fixtures/domain-oracle.json
- evals/local-rules.json
- evals/trigger-prompts.csv
- +2 more