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.
49,456 skills from 2,407 repositories · updated 25 minutes ago
10,658 skills
- releasearbiterForge/codeArbiterPrepare a declared release target, or preview it with --dry-run. Derive its version and require authorization before publication.OtherReview first★ 151↓ —
- rules-distillmturac/everything-openai-codexScan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule filesOtherNo warnings★ 75↓ —
- my-novelxiaofeng-928/chinese-longnovel-skill长篇网络小说的开书、规划、写作、审修和导出。用于明确的小说项目任务;不用于一般文档或技能工程。OtherNo warnings★ 74↓ —
- re-crash-triagefreyrswift/UaStation崩溃/漏洞样本分析:确定性复现、ASAN/UBSAN 报告解读、输入最小化 (afl-tmin/cmin)、gdb 回溯定位、rr 录制重放、PoC 产出。 触发词:崩溃、crash、ASAN、UBSAN、未定义行为、UAF、堆溢出、越界、段错误、segfault、 core dump、PoC、漏洞分析、崩溃分析。OtherNo warnings★ 58↓ —
- find-skillsEXboys/evotownHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.OtherNo warnings★ 157↓ —
- distributed-trace-analysisnaodeng/awesome-qa-skillsUse this skill when you need to analyze distributed traces for call paths, latency, errors, and evidence gaps; triggers include 分布式 Trace 分析 and distributed trace analysis.OtherNo warnings★ 297↓ —
- readme-polishproflead/codex-skills-libraryImprove a README for clarity and completeness. Use when a junior developer needs guidance on documenting setup and usage.OtherNo warnings★ 167↓ —
- like-perspectivejangviktor-web/likeskill李可老中医(1930-2013)思维操作系统。基于13个来源(11本著作+2篇访谈)蒸馏, 含423个医案、120+首方剂、92种症状路由、24种假证识别。 核心能力:急危重症救治(心衰/中风/休克)、经方剂量体系、六经辨证、假证识别。 触发词:「李可」「用李可的视角」「李可会怎么看」「心衰怎么急救」「附子用量」「经方剂量」「假阳证」「破格救心汤」「六经辨证」。 注意:大剂量用药需在有经验的中医师指导下使用,本skill仅供学习参考。OtherNo warnings★ 140↓ —
- org-standardizationproflead/codex-skills-libraryDefine engineering standards across teams. Use when a senior developer needs to align practices.OtherNo warnings★ 167↓ —
- eni-kalialicewe1/alice_skill全局自动路由 | Kali reference and toolingOtherNo warnings★ 62↓ —
- releasearbiterForge/codeArbiterPrepare a declared release target, or preview it with --dry-run. Derive its version and require authorization before publication.OtherReview first★ 151↓ —
- peer-conversationTserenTserenov/FMT-exocortex-templateМноготуровый диалог писателя (Claude) с одним или несколькими напарниками (любой набор из kimi/codex/hermes/claude-headless) по задаче пилота (DP.SC.154). Ведёт turn-loop (2 участника) или round-loop (3+, WP-509), обнаруживает CONSENSUS/ESCALATE, после консенсуса — Decision Gate (зафиксировать vs реализовать → ревью → проверить → задеплоить), синтезирует report.md через Agent tool.OtherReview first★ 63↓ —
- releasearbiterForge/codeArbiterPrepare a declared release target, or preview it with --dry-run. Derive its version and require authorization before publication.OtherReview first★ 151↓ —
- seecutYeJe-cpu/SeeCut网感口播精剪(v3.4):口播视频加动效,自动剪成"网感口播精剪风格"竖版/横版样片,交付渲染成片+分层工程包(装了剪映引擎则再出剪映分层草稿,音效放草稿;没装则音效混进成片)。当用户给了口播粗剪(+B-roll/截图/录屏)并想要"口播动效/加卡片弹字/剪成短视频/做动效样片/网感口播精剪"时用。自循环:预检→素材理解→找真证据→编排→HyperFrames构建→硬门+两两对比自迭代(≤3版)→配音效→交付→用户终审。不做:纯字幕/纯配音/纯生图/BGM。OtherNo warnings★ 431↓ —
- longgraphlevi-qiao/longgraph-skillUse only when the user explicitly invokes /longgraph or names this skill. Routes and authors a durable longgraph run. Do not use unless named. Do not execute or resume generated runtime node files.OtherNo warnings★ 78↓ —
- liuyao-divinationsonggoldenwind-crypto/liuyao-skills用于六爻起卦、卦盘核对、断卦、取用神、旺衰病药、来意分析和应期推断,以及婚恋、求财、事业、出行、失物等具体占问。采用世爻用神人、双原与病药的测算体系;不用于八字、紫微、塔罗或一般现实预测。OtherNo warnings★ 66↓ —
- geo-diagnoseyaojingang/GEOHubDiagnose a brand, website, or page for evidence-backed GEO gaps and opportunities from user-supplied URLs, HTML, or evidence. Use for brand diagnosis, website or page audits, GEO gap analysis, and 品牌诊断、网站诊断、页面诊断. Excludes live AI-platform recall, ranking, and citation-share measurement.OtherNo warnings★ 170↓ —
- re-exploitfreyrswift/UaStation利用开发:ROP 链构造、堆利用。 触发词:ROP、堆利用、fastbin、tcache、利用开发、exploitOtherNo warnings★ 58↓ —
- asset-passportmachina-exm/film-studio-skillsCreate film-asset passports before generation. Use for characters, locations, props, and state variants that need repeatable visual identity.OtherNo warnings★ 172↓ —
- releasearbiterForge/codeArbiterPrepare a declared release target, or preview it with --dry-run. Derive its version and require authorization before publication.OtherReview first★ 151↓ —
- harness:certifyraphaelchristi/harness-evolverUse when the user wants to verify that the evolved agent's score is stable and reliable. Runs evaluation multiple times and reports mean ± std.OtherNo warnings★ 57↓ —
- pymc-bayesian-modelingBioTender-max/awesome-bio-agent-skillsBayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.OtherNo warnings★ 215↓ —
- better-prompthuangwb8/skills当用户明确要求"优化 prompt"、"改进提示词"、"润色指令"、"将简陋 prompt 转换为最佳实践版本",或要求"把 prompt 改写成伪代码"、"翻译成程序结构/可编程自然语言"时使用。支持两种输出模式:standard(基于 OpenAI/Anthropic 官方最佳实践做增强优化)与 prompt_program(严格等价翻译为 Prompt Program 方言)。OtherReview first★ 50↓ —
- scveloBioTender-max/awesome-bio-agent-skillsRNA velocity analysis with scVelo. Estimate cell state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy/scVI-tools for trajectory inference.OtherNo warnings★ 215↓ —