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.
46,100 skills from 2,198 repositories · updated 4 hours ago
9,541 skills
- jingzhuangxiu-gaizao-bikeng-zhinanzx029w/zhuangxiu-skills精装修改造避坑指南专用 Skill。覆盖老房旧房改造、厨房卫生间改造、墙地面翻新、拆改项目与顺序、预算报价与维权、精装修微改等全流程，倒序整合西安装修课堂会员版知识库精华，帮用户装出更省心、不踩坑的精装修改造避坑。OtherNo warnings★ 86↓ —
- 装修水电避坑指南zx029w/zhuangxiu-skills【装修隐蔽工程必看】水电是装修第一步、最容易被坑的环节——绕路加米数、不估价坐地起价、进口水管忽悠、水电包死偷工、走顶多花钱、横平竖直当质量、验收一堆专业名词看不懂？这个Skill专治各种水电套路，覆盖水电规划、计费方式、估价谈判、验收标准、常见坑点。适合拿到水电报价、准备交底、担心被加价、想自己看懂水电的业主。OtherNo warnings★ 86↓ —
- pm-releasekonglong87/superPMUse when: 风险管控完成后准备上线发布、需要制定上线检查清单与回滚方案、正式发版流程 Do NOT use when: 上线流程已标准化且由运维自动化执行、仅需简单发布无需检查清单OtherNo warnings★ 84↓ —
- pm-featurekonglong87/superPMUse when: 需要细化功能实现细节、拆解复杂功能、为开发准备详细任务、功能点需多维度描述 Do NOT use when: 功能已足够简单可直接进入开发、仅需功能列表无需深度拆解OtherNo warnings★ 84↓ —
- hunt-cacheEncod3d-Sec/TORCHWeb cache poisoning + cache deception hunting - unkeyed input poisoning, cache-key analysis, path-confusion deception, header/parameter cloaking. Wiki-first, FIND schema output.OtherNo warnings★ 336↓ —
- pm-reportkonglong87/superPMUse when: 需要生成数据报告、收集整理用户反馈、进行数据驱动的分析汇报 Do NOT use when: 数据已由BI系统自动生成、无需人工分析OtherNo warnings★ 84↓ —
- incorporationkazukinagata/shinkoku法人成り（個人事業主から法人への移行）に関する相談。税額比較シミュレーション、 法人形態の選択、設立手続き、役員報酬戦略、社会保険の比較を支援する。 Trigger: "法人成り", "会社設立", "法人化", "株式会社にしたい", "合同会社", "法人税と所得税の比較", "役員報酬", "法人成りのタイミング", "マイクロ法人", "1人法人"OtherNo warnings★ 366↓ —
- limit-based-strategyitseffi/agentic-osDevelop a limit-based product strategy with convergence milestones, acceleration levers, assumptions, and phased execution.OtherNo warnings★ 117↓ —
- daily-trendingaAAaqwq/AGI-Super-Team获取今日热榜，从tophub.today抓取各平台热搜榜单。当用户询问"今天有什么热搜"、"热榜"、"微博热搜"时触发。OtherNo warnings★ 112↓ —
- pm-feedbackkonglong87/superPMUse when: 需要分析用户反馈和评论、评估用户满意度、收集产品改进建议、进行情感分析 Do NOT use when: 用户反馈数据极少、仅需收集无需分析OtherNo warnings★ 84↓ —
- pm-techkonglong87/superPMUse when: 需要与技术团队对接技术方案、评估技术可行性、制定技术架构、评估第三方服务 Do NOT use when: 技术方案已由技术团队确定、仅需功能描述无需技术评估OtherNo warnings★ 84↓ —
- root-cause-analysisitseffi/agentic-osUncover root causes through recursive Why questioning and consequence exploration. Use before acting on problems.OtherNo warnings★ 117↓ —
- pm-abtestkonglong87/superPMUse when: 需要验证产品优化效果、进行数据驱动的A/B实验决策、评估功能改动的因果影响 Do NOT use when: 改动无法量化测量、样本量不足、不需要严格统计验证OtherNo warnings★ 84↓ —
- gh-issue-analysiscxcscmu/SkillLearnBenchHow to fetch and analyze GitHub issues for a repository within a date range: total counts, bug report identification by label substring matching, and resolved bug counts. Use this skill whenever the user asks about issue metrics, bug counts, triage stats, or community health reports for a GitHub repo.OtherNo warnings★ 91↓ —
- d3-interactive-chartscxcscmu/SkillLearnBenchD3.js techniques for tooltips, hover effects, click handlers, and cross-filtering between visualizationsOtherNo warnings★ 91↓ —
- pm-funnelkonglong87/superPMUse when: 需要分析用户转化漏斗、诊断流失原因、生成优化建议、提升用户转化率 Do NOT use when: 用户转化路径已非常清晰、仅需单一指标监控无需全链路分析OtherNo warnings★ 84↓ —
- pm-competitorkonglong87/superPMUse when: 需要持续监控竞品动态、建立竞品情报预警、定期输出竞品监控月报、追踪竞品版本/定价/功能/舆情/融资异动 Do NOT use when: 仅需一次性竞品调研（用 pm-market / pm-search --type=competitor）；产品尚无明确竞品OtherNo warnings★ 84↓ —
- crux-diagnosisitseffi/agentic-osIdentify the pivotal obstacle between current state and desired future. Use when developing strategy.OtherNo warnings★ 117↓ —
- decision-journalitseffi/agentic-osCreate structured records of decisions with expected outcomes, probabilities, and quit conditions. Use for important decisions.OtherNo warnings★ 117↓ —
- influence-strategiesitseffi/agentic-osGenerate influence strategies using Cialdini's seven principles. Use when you need to influence toward an outcome.OtherNo warnings★ 117↓ —
- validate-ideakonglong87/superPM专为产品经理设计的 AI工具 Skills技能，一键实现全生命周期的产品管理工作流。skills frame for superPM！OtherNo warnings★ 84↓ —
- brand-identityaAAaqwq/AGI-Super-TeamDefine brand strategy, voice, visual direction, tagline, and usage guidelines. Use when creating, refreshing, or standardizing a product or company brand.OtherNo warnings★ 112↓ —
- mece-analysisitseffi/agentic-osStructure thinking using Mutually Exclusive, Collectively Exhaustive categories. Use when breaking down problems or ensuring complete coverage.OtherNo warnings★ 117↓ —
- geojson-processingcxcscmu/SkillLearnBenchLoading and processing GeoJSON earthquake and plate boundary data with GeoPandas for spatial analysis.OtherNo warnings★ 91↓ —
sample-skill
kyungseo/skillstead
OtherUpdated 2 days ago
From the author
Replace this reserved identity and describe the concrete user outcome, selection boundary, and important non-goals. Do not use this package before every sample-skill identity has been replaced.
Install
npx skills add kyungseo/skillstead --skill sample-skill -a claude-code
Installs to .claude/skills/sample-skill/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 83
Security100
Provenance63
Maintenance100
Licence100
Adoption34
Files (5)
- CHANGELOG.md
- LICENSE.txt
- README.ko.md
- README.md
- SKILL.md