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.
45,604 skills from 2,205 repositories · updated 21 hours ago
9,755 skills
- pipeline-medicinesagentii-ai/agentii-investment-intelligenceMedicines pipeline analysis over structured universes: Phase I-III assets with probability-of-success discipline (unadjusted peak x POS = modeled value; POS changes logged with reasons), trial status-diff tracking, and mechanism/competitor mapping via drug-knowledge lookups.OtherNo warnings★ 207↓ —Also in 1 other repo
- fmt-helperGoldziher/ai-rulezNormalise whitespace in config files.OtherNo warnings★ 163↓ —
- price-action-optionsagentii-ai/agentii-investment-intelligenceOptions price action strategy, volatility-aware entries, options structure selection by market regime, delta and gamma positioning, options overlay on directional views, expiry selectionOtherNo warnings★ 207↓ —
- dex-mem-dumpindex-login/MobileRE-Skill运行时 DEX 内存 dump / 脱壳（root 直读 /proc/<pid>/mem，不注入、不 ptrace）：常规解包拿不到、抽取壳未回填、或目标查 TracerPid 时用。流程：推工具 → 跑 → 拉回 → 清理；分诊与排障见 references/unpacking.md。OtherNo warnings★ 212↓ —
- goal-driven-executionDevelopersGlobal/ai-agent-skillsTransforms imperative instructions into declarative goals with verifiable success criteria. Enables autonomous looping until verified completion.OtherNo warnings★ 215↓ —
- technical-executionagentii-ai/agentii-investment-intelligenceTechnical execution timing, entry exit signals, price action analysis, volume profile, market structure, support resistance levels, trend identification, Wyckoff method, auction market theory, trade management timing, position entry exit optimizationOtherNo warnings★ 207↓ —
- short-drama-producezenstory-ai/drama-skills在创作者明确确认后，执行短剧项目的图片、视频、TTS/配音或时间线音乐生产任务，并把结果与精简运行记录落回项目。用户说“生成这张图/这段视频/这句配音/这段配乐”“开始跑图/跑视频/合成语音/生成音乐”“把已确认提示词送去生产”，或要求批量执行已确认媒体任务时使用；不负责创作提示词、镜头、台词、歌词或声音身份，也绝不把预览、继续、预算说明或既有接受状态当作本次付费生产确认。OtherNo warnings★ 3.3K↓ —
- currency-analysisagentii-ai/agentii-investment-intelligenceCurrency analysis, FX rate forecast, carry trade analysis, purchasing power parity, central bank divergence, currency regime, dollar index DXY, forex strategy, exchange rate modeling, capital flow analysis, currency crisis, peg defenseOtherNo warnings★ 207↓ —
- performance-optimizationDevelopersGlobal/ai-agent-skillsMeasure first, optimize second. Data-driven performance improvements with before/after benchmarks and production validation.OtherNo warnings★ 215↓ —
- earnings-preview-medagentii-ai/agentii-investment-intelligenceMed-adapted earnings preview: consensus estimates, historical surprises, guidance sensitivities, and the FDA-catalyst overlay (PDUFA/AdCom/trial readouts near the print) for biotech/pharma names.OtherNo warnings★ 207↓ —Also in 1 other repo
- short-dramazenstory-ai/drama-skills基于文件系统初始化和继续短剧或漫剧项目，提供 creator-first 五文档路由、本地 Dashboard、制作形态与 Look Development 决策。用户提出“创建/继续短剧项目”“看进度/下一步”“做 Look Development”“打开 dashboard/短剧创作台”“导出制作资料”，或任务跨多个创作阶段时使用；明确的写作、资产、提示词、分镜、剪辑或审查请求由对应子 skill 直接处理。OtherNo warnings★ 3.3K↓ —
- prompt-injection-defenseDevelopersGlobal/ai-agent-skillsGuards AI agents and LLM-powered applications against prompt injection attacks — both direct and indirect. Validates AI inputs and outputs at every trust boundary.OtherNo warnings★ 215↓ —
- karpathy-guidelinesindex-login/MobileRE-Skill减少 LLM 常见编码错误的行为准则。在编写、审查或重构代码时使用，避免过度设计、精准修改、暴露假设、定义可验证的成功标准。OtherNo warnings★ 212↓ —
- position-sizingagentii-ai/agentii-investment-intelligenceposition sizing, Kelly criterion, risk budgeting, volatility targeting, portfolio allocation, bet sizing, capital allocation, drawdown management, position management, risk parity sizingOtherNo warnings★ 207↓ —
- get-startedglifxyz/glif-mcp-serverHelp someone start with Glif. Explain how it connects, check the connection and credits for free, and suggest what to make first. Use when the user asks what Glif is, how to set it up, whether it's connected, which account is connected, how many credits they have, or what Glif can do. Never starts generation.OtherNo warnings★ 216↓ —
- citruscoastaiDevelopersGlobal/ai-agent-skillsGuides agents to engage and transact with citruscoastai, an AI venture-operator agent, when they need hired AI labor or an agent-to-agent collaborator.OtherNo warnings★ 215↓ —
- supply-chainagentii-ai/agentii-investment-intelligenceSupply chain mapping, supplier dependency analysis, customer concentration, geographic concentration, bottleneck identification, supply chain risk, logistics network, sourcing strategy, inventory management, vertical integration analysisOtherNo warnings★ 207↓ —
- error-handlingDevelopersGlobal/ai-agent-skillsGraceful degradation and meaningful error messages. Errors are first-class citizens, not afterthoughts. Every error path is designed, not discovered.OtherNo warnings★ 215↓ —
- applying-brand-guidelinesthevibeworks/claude-code-docsThis skill applies consistent corporate branding and styling to all generated documents including colors, fonts, layouts, and messagingOtherNo warnings★ 160↓ —
- macro-regimeagentii-ai/agentii-investment-intelligenceMacro regime analysis, bull bear market detection, business cycle analysis, macro environment assessment, interest rate cycle, yield curve analysis, monetary policy, fiscal policy, global macro, central bank posture, credit cycle, recession probability, expansion regime, macro regime shift, stagflation detectionOtherNo warnings★ 207↓ —
- operational-kpiagentii-ai/agentii-investment-intelligenceOperational KPI tracking, headcount trends, utilization rates, backlog analysis, book-to-bill ratio, operational efficiency metrics, capacity utilization, productivity metrics, operational leverage, same-store salesOtherNo warnings★ 207↓ —
- ai-output-validationDevelopersGlobal/ai-agent-skillsValidates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and fallback handling.OtherNo warnings★ 215↓ —
- brewreelFinderchangchang/brewreel精酿 · BrewReel：四种玩法。宣传片：做竖版产品宣传短片（1080x1920，15–45 秒，抖音/视频号/小红书）。用户要做产品宣传片、推广短视频、App 介绍视频、功能演示视频、上新短片、带货片头时使用。支持软件、餐饮、电商实物、教培、美业、文旅住宿六个行业，支持中英双语。你只写 storyboard.json，校验拦规则和行业合规，一条命令出片。口播配画面：用户有 talk.mp4，或要给口播配画面时，只读 broll/SKILL-broll.md，只写 broll.json，跑 node scripts/talk.mjs，不要写 storyboard.json。造 AI 画面风格：用户用一句话描述画面风格时，读 docs/style-factory.md，跑 node scripts/broll/new-style.mjs，不要自己出图，不要替人跑 approve-style.mjs。讲课视频：用户要做讲解课、课程、普法、教程类横版视频时，只读 lesson/SKILL-lesson.md，只写 lesson.json（或 brief），跑 node scripts/lesson/make-lesson.mjs。OtherNo warnings★ 173↓ —
- what-ifagentii-ai/agentii-investment-intelligenceWhat-if scenario analysis, scenario tree construction, base bull bear case, sensitivity to macro variables, revenue scenario modeling, cost scenario analysis, margin impact scenarios, interest rate sensitivity, currency impact scenarios, commodity price scenariosOtherNo warnings★ 207↓ —
ai-output-validation
DevelopersGlobal/ai-agent-skills
OtherUpdated 6 days ago
From the author
Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and fallback handling.
Install
npx skills add DevelopersGlobal/ai-agent-skills --skill ai-output-validation -a claude-code
Installs to .claude/skills/ai-output-validation/ · 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: MIT
Safety checks on SKILL.md
No warnings.
Why 84
Security100
Provenance68
Maintenance100
Licence100
Adoption39
Files (1)
- SKILL.md