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.
45,100 skills from 2,196 repositories · updated 16 hours ago
9,668 skills
- davciitseffi/agentic-osDefine clear decision rights - Decider, Approver, Veto, Consulted, Informed. Use when clarifying who decides.OtherNo warnings★ 117↓ —
- challenging-stakeholder-questionsitseffi/agentic-osGenerate rigorous stakeholder challenge questions for proposal or meeting preparation.OtherNo warnings★ 117↓ —
- titles-and-descriptionJimLiu/baocut用户要为准备发布的视频起标题、要几个标题候选、再来一批或照某个再来几个,或要写视频简介(视频页标题下的说明文字、章节列表、标签)时用。写给发布视频的人:吸引人,并且每句都由视频兑现。需要视频的转写。不用于给文章起标题等与视频无关的写作。OtherNo warnings★ 1.5K↓ —
- aesthetic-instrumentavelikiy/great_ctogreat_cto's own committed aesthetic — the instrument panel. Dark five-step surface ladder, exactly one accent, two faces divided by MEANING (Geist speaks, Geist Mono is machine-truth), tabular numerals, and a dash that is not a nought. Twelve checkable rules measured from packages/board and greatcto.systems, not designed for this file. Use when building or extending any great_cto surface — the board, the site, a report, a share page.OtherNo warnings★ 106↓ —
- output-versandThomasMoreAI/legal-skills-openFür Output und Versandsteuerung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- parallel-agent-contractsparcadei/Continuous-Claude-v3Parallel Agent Type ContractsOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- open-setsparcadei/Continuous-Claude-v3Problem-solving strategies for open sets in topologyOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- haptik-und-tastmarkeThomasMoreAI/legal-skills-openFür Tastmarken und Haptik-Marken: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- ribaoorziz/odai日报、周报、工作总结、状态更新:基于可核证事实形成完整汇报。用户要求汇报一段时期的工作、沿用既有汇报模板、整理进展与风险,或 odai 判断专业汇报工艺会改善结果时使用。OtherNo warnings★ 119↓ —
- zhangyi-systemsaph199686/zhangyi-studio张翼机制与系统设计:核心循环细化、新机制评审过闸、数值纪律与平衡裁决。每个机制必须回答'解决哪个病灶'、区分'强化内核还是堆系统'、推演诱发的玩家行为与情绪,输出系统裁决书。Use when the user designs mechanics/systems, tunes numbers or balance, evaluates adding a new mechanic, designs core loop details, or asks whether a feature is worth building. 用户设计机制与系统、调数值做平衡、纠结加不加某个机制、细化核心循环、或问某个功能值不值得做时使用。OtherNo warnings★ 119↓ —
- search-hierarchyparcadei/Continuous-Claude-v3Search Tool HierarchyOtherNo warnings★ 3.9K↓ —
- qlty-during-developmentparcadei/Continuous-Claude-v3QLTY During DevelopmentOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- glm-simulationcxcscmu/SkillLearnBenchRunning the General Lake Model (GLM) with configuration files and parameter calibrationOtherNo warnings★ 91↓ —
- deckungsklageThomasMoreAI/legal-skills-openFür Deckungsklage: erstellt Entwurf mit Antrag, Beweis und Anlagen; Ergebnis: Schriftsatz mit Begründungs- und Anlagenlogik. Fachgebiet: Fachanwalt Versicherungsrecht. Route: deckungsklage.OtherNo warnings★ 95↓ —
- subskriptionspreis-eThomasMoreAI/legal-skills-openFür Verl-012 · Subskriptionspreis, Einführungspreis und Aktionspreis: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- preisangabenThomasMoreAI/legal-skills-openFür Preisangaben (PAngV 2022): ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- clearance-zhou210712ThomasMoreAI/legal-skills-open商标清除初步检索——排除性筛查+近似商标查询,产出标注清单而非清除法律意见。当新商标 被提出、被询问某商标是否可用或需要进行排除检索、或在完整专业检索前评估混淆可能性因素 时使用。本技能绝不作出商标无冲突的结论。OtherNo warnings★ 95↓ —
- patent-digestThomasMoreAI/legal-skills-open专利文档智能解析与结构化摘要生成。支持提取基本信息、摘要、权利要求、创新点及技术方案,并输出标准化 Markdown 报告。适用于 OpenClaw、OpenCode、Hermes 等通用 Agent 。OtherNo warnings★ 95↓ —
- bmad-epsilon-v2alvin-reyes/better-agentic-ideA fixture skill with frontmatter and body problems.OtherNo warnings★ 85↓ —
- janitor-reportkhendzel/skills-janitorFull health check of all your skills in one report. Use when the user wants to check for errors, find duplicates, detect broken skills, or get a complete overview of skill health. Pass --brief for inventory only. Trigger with '/janitor-report'.OtherNo warnings★ 122↓ —
- example-vueBintzGavin/heliosPatterns for using Helios with Vue. Use when building compositions in a Vue environment.OtherNo warnings★ 123↓ —
- graceful-degradationparcadei/Continuous-Claude-v3Graceful Degradation with Helpful MessagesOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- bmod-alphaalvin-reyes/better-agentic-ideBetter Agentic Development EnvironmentOtherNo warnings★ 85↓ —
- search-toolsparcadei/Continuous-Claude-v3Search Tool HierarchyOtherNo warnings★ 3.9K↓ —
startup-idea
fabricioctelles/skills
From the author
Analyze startups with Paul Graham mindset (pressure, founder-market fit, brutal validation), Dan Koe discipline (monetization, offer, distribution, sales), and Seth Godin principles (differentiation, narrative, smallest viable audience). Triggers on startup idea, business validation, MVP, first customers, revenue model, GTM, product-market fit, "I have an idea".
Install
npx skills add fabricioctelles/skills --skill startup-idea -a claude-code
Installs to .claude/skills/startup-idea/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Safety checks on SKILL.md
No warnings.
Why 83
Files (2)
- SKILL.md
- evals/evals.json