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.
49,104 skills from 2,358 repositories · updated 14 minutes ago
10,562 skills
- mk-129backtrue/thinkwithblack-skill銷售頁段落順序診斷。用於需要讀者理解與決策順序的問題的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- mk-131backtrue/thinkwithblack-skill銷售頁缺證據檢查。用於需要缺來源、假見證與空泛保證的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- mk-137backtrue/thinkwithblack-skill臉書廣告三行分段法。先確認三個比較式 USP，從 Persona 購買動機選擇第一行情境，不固定寫痛點，再產出積極、友善、專業三組文案，逐行核對字數、完整 CTA 與消費者主詞OtherNo warnings★ 252↓ —
- mk-142backtrue/thinkwithblack-skill同賣點跨受眾改稿。用於需要保留事實但調整情境與利益的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- mk-145backtrue/thinkwithblack-skill直式素材改編。用於需要依垂直觀看情境重組的版稿的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- mk-148backtrue/thinkwithblack-skill消費者購買疑慮分類。用於需要價格、信任、使用與交付疑慮的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- mk-149backtrue/thinkwithblack-skill真實評價重點萃取。用於需要保留原意的顧客評價重點的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- mk-152backtrue/thinkwithblack-skill評論拼圖素材規劃。用於需要原文摘錄與畫面安排的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- building-github-indexoaustegard/claude-skillsGenerate progressive disclosure indexes for GitHub repositories to use as Claude project knowledge. Use when setting up projects referencing external documentation, creating searchable indexes of technical blogs or knowledge bases, combining multiple repos into one index, or when user mentions "index", "github repo", "project knowledge", or "documentation reference".OtherNo warnings★ 158↓ —Also in 1 other repo
- lemo-opuscarNewSwotAtmk/infinite-creation用「代码渲染」方式把用户挑选的风格模板 + 上传的图片/视频/音频素材 + 提示词合成为对应风格的成片视频（脱离 ComfyUI）。当用户要在「无限・秩影」模式下、或指定某个 Lemo-Opuscar 风格（油画厚涂/浮世绘/皮影戏/卫星简报/产品拆解 等 66 种）制作短片时使用。OtherNo warnings★ 176↓ —
- provenanceanbeime/skill收集系统全链路操作日志，生成可追溯的执行证据链与向量索引，是多智能体系统可观测性与安全审计的底座。OtherNo warnings★ 9K↓ —
- agent-readymblode/agent-skillsImplements agent-readiness on public sites and docs from Mintlify Agent Score, AFDocs, Is Agentic, Is It Agent Ready, or url-discovery-bench reports, or from server logs of agents 404ing on guessed URLs. Use when asked to "make our site agent-ready", "improve Agent Score", "fix llms.txt coverage", "agents keep 404ing on our docs", or when a pasted scorecard is the brief.OtherNo warnings★ 180↓ —
- continuous-learning-v2vibeeval/vibecosystemInstinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.OtherNo warnings★ 541↓ —
- mapsmgifford/accessibility-skillsLoad this skill whenever the project contains static or interactive maps, embedded map widgets (Google Maps, Leaflet, Mapbox, OpenStreetMap), or any geographic visualizations. Under no circumstances embed a map without a text-based alternative conveying the same information. Absolutely always ensure map controls are keyboard-accessible and that all meaningful map content is available without the visual map.OtherNo warnings★ 57↓ —
- tooltipsmgifford/accessibility-skillsLoad this skill whenever the project contains tooltip components, hover- triggered informational popups, title attribute tooltips, or any content revealed on hover or focus. Under no circumstances create tooltips that are only triggered by hover without keyboard equivalent access. Absolutely always ensure tooltips are dismissible, persistent enough to read, and not the sole source of essential information.OtherNo warnings★ 57↓ —
- awesome-student-ai-skillscuic19053-hue/awesome-student-ai-skills35 个大学生竞赛与立项 AI Skill 集合 | 覆盖大创/挑战杯/互联网+/国家级项目/答辩模拟等 | 零门槛即用 | Agent Skills 标准OtherNo warnings★ 150↓ —
- reporting-and-archiving-findingsK-Dense-AI/science-superpowersUse when an analysis is complete and verified, and you need to decide how to report it and archive the work for reproducibilityOtherNo warnings★ 368↓ —
- quality-auditNickCrew/Claude-CortexMeta-skill for auditing and validating skill quality. Use when reviewing skills for consistency, completeness, accuracy, and adherence to standards. Provides structured rubrics, scoring frameworks, and actionable recommendations.OtherNo warnings★ 63↓ —
- shuangdiantance-mang/chinese-webnovel-skills中文网文爽点与打脸桥段设计。当用户要设计打脸、扮猪吃老虎、装13、逆袭、复仇、碾压反派、或抱怨剧情"不够爽/太平淡/读者说没爽点"时使用。产出三段式爽点闭环和打脸四拍，并保证爽点升级不重复。OtherNo warnings★ 96↓ —
- goldfingertance-mang/chinese-webnovel-skills中文网文金手指（外挂/系统）设计。当用户要设计系统流、签到流、空间流、模拟器、重生先知、扮猪吃老虎等核心设定，或要给主角一个变强机制时使用。产出有门槛、有成长曲线、有代价、与主线绑定的金手指方案。OtherNo warnings★ 96↓ —
- continuitytance-mang/chinese-webnovel-skills中文网文长篇连贯性与逻辑检查。当用户写长篇怕"前后矛盾/写到一百章崩了/设定漂移"、要查时间线乱不乱、人物行为合不合理、资源凭空变、身份忽暴忽藏、伤势没延续、战力越级、或要对一卷/全书做逻辑体检时使用。逐章核对六条逻辑链+时间线，揪出和前文/档案的矛盾并给改法。OtherNo warnings★ 96↓ —
- aidetecttance-mang/chinese-webnovel-skills中文网文 AI 味量化检测与评分。当用户要给正文"打个 AI 味分/量化看看有多像 AI"、要知道"问题具体在第几句"、要查比喻密度/连续同句式/句长波动/段落分布/高频情绪词重复/极端词堆砌，或要在改稿前先定位 AI 味重灾区时使用。产出 AI 味指数(0–10)+八项指标实测+扣分定位清单。OtherNo warnings★ 96↓ —
- englishtance-mang/chinese-webnovel-skills英文网文出海写作（Wattpad / Royal Road / Webnovel / Radish / KDP）。当用户要写英文小说、出海英文平台、把中文故事改写成英文原生（不是翻译腔）、问英文平台怎么写/选哪个、或要去掉英文里的"中国网文翻译腔/AI腔"时使用。按英文网文规则产出像当地作者写的英文。OtherNo warnings★ 96↓ —
- trendstance-mang/chinese-webnovel-skills中文网文平台趋势与喜好实时调研。当用户想知道当下番茄/晋江/起点/UC/知乎盐选/Webnovel 平台流行什么题材、热门标签、上榜套路、读者偏好，或要做选题前的市场调研、追风口时使用。优先用联网搜索拉取最新数据，给可执行的选题/标签建议。OtherNo warnings★ 96↓ —
mk-360
backtrue/thinkwithblack-skill
OtherUpdated yesterday
From the author
AI 搜尋題目優先序。用於需要依商業關聯與代表性選題的工作；依本項方法處理已指定資料並核對交付
Install
npx skills add backtrue/thinkwithblack-skill --skill mk-360 -a claude-code
Installs to .claude/skills/mk-360/ · 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 scriptsNo network use seenLicence: MIT
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 79
Security85
Provenance69
Maintenance100
Licence100
Adoption40
Files (3)
- SKILL.md
- assets/check-context.py
- assets/context-contract.json