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 10 hours ago
9,541 skills
- ai-safety-governance-expertroedyrustam/vibes-plugAI safety, guardrails (NeMo, Llama Guard), bias audit, EU AI Act / Keamanan AI, guardrail (NeMo, Llama Guard), dan tata kelola AI.OtherNo warnings★ 115↓ —
- cm-product-managerkingxiaozhe/cm-workflow产品经理 Skill，负责需求分析、用户故事与验收标准编写、歧义清单生成、变更影响分析、业务验收走查；把关型角色，不做技术设计与技术测试OtherNo warnings★ 97↓ —
- hylo-setupskoowoo/hyloWalks the user through setting up Hylo itself in chat, one step at a time, and picks up where they left off. Use only when told to run hylo-setup (the first chat after onboarding is), or when the user explicitly asks to set up, continue or redo the setup of Hylo, e.g. 'continue Hylo setup', 'run Hylo setup again', '继续 Hylo 设置', '重新运行 Hylo 设置'. Do not use for setting up anything else (a tool, project, bot or app), for one-off changes like adding a bot or trigger, or for questions about how Hylo works.OtherNo warnings★ 101↓ —
- after-salesaAAaqwq/AGI-Super-TeamUse when managing post-purchase experience, building customer loyalty, or increasing repeat purchasesOtherNo warnings★ 112↓ —
- web-searchaAAaqwq/AGI-Super-Team网络搜索与网页内容获取。当用户需要搜索互联网信息、获取网页内容、查找实时数据、进行 websearch 时使用此技能。支持多种搜索工具：WebFetch、Firecrawl skill、Tavily skill。OtherNo warnings★ 112↓ —
- using-stringstring-os/stringUse the installed String MCP tool for String apps, SFMD, web pages, shell sessions, and commands like /open, /act, /install, or /set.OtherNo warnings★ 78↓ —
- lidang-perspectiveappleweiping/AGENT_RESOURCE立党(Lidang)的路径工程思维框架与表达方式。基于GitHub项目、YouTube直播、Substack长文、X公开资料的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为路径规划顾问，用立党的视角分析职业选择、技术趋势、移民决策、创业路径、教育投资。 当用户提到「用立党的视角」「立党会怎么看」「立党模式」「lidang perspective」时使用。 即使用户只是说「帮我用立党的角度想想」「如果立党会怎么做」「切换到立党」也应触发。OtherNo warnings★ 78↓ —
- ardot-usebalabalabalading/huuuuuuho-skills**强制性前置条件** — 每次调用 `batch_edit` 工具之前，必须先调用此技能。 未经加载此技能，绝不能直接调用 `batch_edit`。 当用户想要在 Ardot 设计文件中创建、更新、移动或删除节点时触发 — 例如插入框架、文本、形状、组件；将变量绑定到填充/描边； 构建屏幕、组件或设计库。当涉及 batch_edit DSL 操作时也加载 （I/U/M/D/C/G 操作符）。OtherNo warnings★ 118↓ —
- ctf-pwn26zl/cybersec-toolkitUse when solving binary exploitation / pwn CTF challenges — buffer overflows, ROP, format strings, heap, kernel pwn. Provides a decision tree, exploit primitive catalog, and uses pwntools via the run_script(venv="pwntools") MCP path. Triggers on "ctf pwn", "binary exploit", "rop", "buffer overflow", "format string", "heap challenge".OtherNo warnings★ 85↓ —
- shorts-segmentsJimLiu/baocut用户有一个长视频（访谈、讲座、直播回放、口播），想从中切出几支能单独发布的短视频时用：读转写找出最值得发的话题，每个话题从开头的钩子剪到讲完，建成可编辑的子视频，用户在编辑器里接着调；几支、每支多长可以交给你按话题定。需要视频的转写。不用于按主题从零做一个新的短视频，也不用于把整段口播剪干净（用剪口播）。OtherNo warnings★ 1.6K↓ —
- pareto-optimizationcxcscmu/SkillLearnBenchMulti-objective optimization with Pareto frontiers for finding trade-off solutions between conflicting objectives.OtherNo warnings★ 91↓ —
- rationaleNoobyGains/godmodeUse when the user asks for new work such as a feature, component, integration, service or dependency, especially when the request names a solution instead of a problem, the scope looks larger than the user may expect, or the motivation is that other products have itOtherNo warnings★ 115↓ —
- podmanlingxling/awesome-skills-cnManage containers using Podman, the daemonless container engine.OtherNo warnings★ 325↓ —
- zhangyi-relayaph199686/zhangyi-studio张翼接力：跨会话的项目连续性管理。新会话开局生成交接提示词（开场白九模块）、核验上一会话遗留状态、每批工作收尾时沉淀交接段（遗留待办/新红线/新环境坑）。Use when the user starts a new session to continue existing work, asks to sync project status, wants a handoff/continuation prompt, or finishes a batch of work. 用户开新会话继续旧项目、需要交接提示词、同步项目进度、或一批工作收尾时使用。不限于游戏项目。OtherNo warnings★ 119↓ —
- bounty-mobile26zl/cybersec-toolkitUse when bug-bountying an Android (APK) or iOS (IPA) app. Covers static + dynamic analysis, Frida hooking, certificate pinning bypass, deep link / intent abuse, IPC, secrets in bundles. Triggers on "bounty mobile", "android app", "ios app", "apk analysis", "frida".OtherNo warnings★ 85↓ —
- skeptical-triageavelikiy/great_ctoReusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of ~4 extra LLM turns.OtherNo warnings★ 108↓ —
- batch-organizercxcscmu/SkillLearnBenchEfficiently organizes large numbers of files into directories.OtherNo warnings★ 91↓ —
- bad-news-memoThomasMoreAI/legal-skills-openFür Bad News Memo: erstellt Entwurf mit Antrag, Beweis und Anlagen; Ergebnis: Schriftsatz mit Begründungs- und Anlagenlogik.OtherNo warnings★ 96↓ —
- qualitygate-gebrmgThomasMoreAI/legal-skills-openFür Qualitygate Gebrmg: prüft Ergebnis, Beweislast und Gegenposition; Ergebnis: Gegenprüfung mit Beweis- und Fristencheck.OtherNo warnings★ 96↓ —
- press-mediarshankras/claude-code-apple-skillsGet press coverage and media attention for your indie app. Covers press kit preparation, finding journalists/bloggers/YouTubers, pitch timing, embargo strategy, and story angles that get coverage. Use when user wants press coverage, is preparing for a launch, or wants to build a media kit.OtherNo warnings★ 840↓ —
- web-style-directorTheGoat395/Codex-SkillsRefine an approved visual lane.OtherNo warnings★ 135↓ —
- crystallizeavelikiy/great_ctoDistils repeating patterns from session logs and lessons.md into draft skill files. Run after ≥10 sessions to extract durable knowledge. Output: draft skills/ files + promotion report.OtherNo warnings★ 108↓ —
- parallel-processingcxcscmu/SkillLearnBenchParallel processing with joblib for grid search and batch computations across multiple CPU cores.OtherNo warnings★ 91↓ —
- verletzungs-triageThomasMoreAI/legal-skills-openFür Verletzungs-Triage: routet Rolle, Frist, Unterlagen und Fachschritt; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 96↓ —
skill-creator
feiskyer/claude-code-settings
OtherUpdated Sep 27, 2026
From the author
Create, refine, and benchmark agent skills. Use when building a new skill, updating an existing one, running evals, checking trigger quality, or improving a skill description.
Install
npx skills add feiskyer/claude-code-settings --skill skill-creator -a claude-code
Installs to .claude/skills/skill-creator/ · 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
Runs bundled scriptsUses the networkLicence: APACHE-2.0
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 83
Security85
Provenance79
Maintenance100
Licence100
Adoption52
Files (24)
- LICENSE.txt
- README.md
- SKILL.md
- agents/analyzer.md
- agents/comparator.md
- agents/grader.md
- assets/eval_review.html
- eval-viewer/generate_review.py
- eval-viewer/viewer.html
- references/schemas.md
- scripts/__init__.py
- scripts/aggregate_benchmark.py
- +12 more