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 5 hours ago
9,541 skills
- risk-metrics-calculationaisa-group/skill-injectCalculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk, implementing risk limits, or building risk monitoring systems.OtherNo warnings★ 101↓ —
- go-to-market-stingerlegioncodeinc/vibe-coding-toolsChoose one acquisition channel from dated buyer evidence and team constraints, then draft a falsifiable experiment. Use before paid, organic, outbound or partner execution. Read README.md.OtherNo warnings★ 94↓ —
- client-health-radarlegioncodeinc/vibe-coding-toolsAssess client health from Littlebird evidence. Use for churn risk, scope creep, margin pressure, or weekly account reviews. Read README.md for the guide map.OtherNo warnings★ 94↓ —
- user-managementBagelHole/DevOps-Security-Agent-SkillsManage users, groups, and permissions on Linux systems. Configure sudo and access controls. Use when managing system access.OtherNo warnings★ 1.2K↓ —
- source-command-estimate-operating-costlegioncodeinc/vibe-coding-toolsEstimate low/base/high monthly cash operating costs and separate operator time value from supplied workload and dated rates.OtherNo warnings★ 94↓ —
- hr-payroll-stingerlegioncodeinc/vibe-coding-toolsChoose payroll and EOR tools. Use for Gusto vs Rippling, contractor classification, international hiring, or benefits. Read guides/ for the decision path.OtherNo warnings★ 94↓ —
- teachnota-america/forgecat-agent-profilesTeach the user a new skill or concept, within this workspace.OtherNo warnings★ 93↓ —
- 990-returnsopenaccountants/openaccountantsForm 990 (full return) in the United States: how I do itOtherNo warnings★ 463↓ —
- crackethanplusai/codex-on-crackLead substantial Codex builds with one configured implementation worker and lead acceptance. Use when the user requests codex-on-crack, names a model to delegate work to, asks to run subagents through Claude, or requests a lead/worker split. Keep host-only work direct; honor explicit external model choices. Workers must not invoke this orchestrator.OtherNo warnings★ 780↓ —
- incorporation-startup-stack-stingerlegioncodeinc/vibe-coding-toolsSet up a software company. Use for entity choice, Atlas vs Clerky, EIN, banking, bookkeeping, or founder paperwork. Read README.md for the guide map.OtherNo warnings★ 94↓ —
- source-command-choose-outcomelegioncodeinc/vibe-coding-toolsFind the qualified owner for a desired result. Use for choosing skills or packs; distinguish proposed coverage, source presence and selected installed capabilities.OtherNo warnings★ 94↓ —
- cn-iitopenaccountants/openaccountants在处理任何中国个人所得税（IIT）事项之前，必须先阅读本技能。本技能适用于中国税务居民个人和非居民个人的个人所得税申报、计算与审核工作，包括综合所得（工资薪金、劳务报酬、稿酬、特许权使用费）的累计预扣预缴与年度汇算清缴，经营所得的五级累进计税，专项附加扣除（子女教育、继续教育、大病医疗、住房贷款利息、住房租金、赡养老人、3岁以下婴幼儿照护），居民判定（183天规则），境外所得抵免，股权激励与全年一次性奖金单独计税过渡政策，以及通过个税APP、自然人电子税务局、单位代扣代缴等方式完成 3月1日至6月30日 综合所得年度汇算清缴的全过程。OtherNo warnings★ 463↓ —
- normal-modesoftcane/human-state-skillsUse when the user wants to stop any active human-state response mode and return to the assistant's normal response style. Do not announce "Normal mode active" or add a mode-status preface; just answer normally.OtherNo warnings★ 120↓ —Also in 1 other repo
- gtrk-ai-dramaGitruck/cliAI 情景动画分镜稿生成器——把成片 SOP 第③步（B-roll 底轨阶段）分到 AI_DRAMA 车道的 beat，逐个产**四段朴素描述（故事背景 / 角色 / 分镜 / 原文文稿）+ 独立视觉基调段 + 时长预算**，中英双版；Markdown 外壳默认严格兼容 gitruck-ai-drama-desk 解析器，可直接导入工作台，也可拿去任意外部 AI 漫剧管线（可灵 / 即梦 / Vidu / Veo / Runway / LTX / 本地开源，或 LibTV / OiiOii / TapNow 这类成片 agent 平台）上手用。创作与出片仍在 skill / 外部工作台；工作台导出的 return-v1 包用 `gtrk ai-drama lay` 确定性回填独立 AI 轨。当用户想「上 AI 情景动画 / 做 AI 分镜 / AI 动画描述 / 把这段做成 AI 视频 / 给这段配 AI 情景动画 / 弗洛伊德这段怎么做视频」时使用本 skill。通用拆镜 craft（蒙太奇段分层 / 四段描述结构 / 中英双语 / 时长预算）由本 skill 自持；栏目视觉 DNA（Style Lock）从栏目配置 style.skills 里 produces==AI_DRAMA 的条目解析注入，绝不硬编某栏目风格。凡把口播派单里 AI_DRAMA 段落转成可出片的描述稿，优先用本 skill，别手搓。OtherNo warnings★ 966↓ —
- tanstack-stingerlegioncodeinc/vibe-coding-toolsTanStack libraries in SvelteKit (Svelte 5) - Query SSR/caching/mutations, Table runes state, Form snippet validation, Virtual; states plainly that Router and Start have no official Svelte support.OtherNo warnings★ 94↓ —
- day-reconstructorlegioncodeinc/vibe-coding-toolsRebuild a work session from Littlebird activity. Use for a dev log, session changelog, or what-shipped recap. Read README.md for the guide map.OtherNo warnings★ 94↓ —
- source-command-prepare-learning-exerciselegioncodeinc/vibe-coding-toolsPrepare one source-linked technical exercise, teach-back and criterion-level evidence rubric without assuming mastery.OtherNo warnings★ 94↓ —
- openclaw-local-mac-miniBagelHole/DevOps-Security-Agent-SkillsSet up OpenClaw locally and run it reliably on a Mac mini for private, always-on local agent workflows.OtherNo warnings★ 1.2K↓ —
- source-command-choose-acquisition-channellegioncodeinc/vibe-coding-toolsChoose one acquisition channel from dated buyer evidence, operating constraints and a falsifiable experiment draft.OtherNo warnings★ 94↓ —
- source-command-secure-platform-foundationlegioncodeinc/vibe-coding-toolsPrepare and implement an authorized platform foundation with identity, secrets, environment and data-access boundaries.OtherNo warnings★ 94↓ —
- mcp-sheet-cache-bridgezapier/gtm-cheat-codesKeep Zapier Tables or another MCP-connected record store as the source of truth while Google Sheets-based tools read an event-driven cache tab.OtherNo warnings★ 351↓ —
- time-blocked-turnslegioncodeinc/vibe-coding-toolsFollow a requested agent work cadence. Use for timed blocks, retry limits, checkpoints, questions, and handoff reports. Read references/ for details.OtherNo warnings★ 94↓ —
- source-command-prepare-assetslegioncodeinc/vibe-coding-toolsPrepare the minimum launch assets and accounts with owners, environments, dated costs, prerequisites and blockers.OtherNo warnings★ 94↓ —
- plsno-ai/sno-station-skillsMANUAL-ONLY — load solely when the human owner types `/pl`, uses `$pl`, or asks you to act as the Project Lead (PL). Supervise one project lane and its executor agents. A charter or dispatch means: you are an EXECUTOR, not the PL.OtherNo warnings★ 884↓ —
finetuning-technique
awslabs/agent-plugins
OtherUpdated Oct 15, 2026
From the author
Selects a fine-tuning technique (SFT, DPO, RLVR, or RLAIF) for the user's use case and validates it against the selected model's available recipes. Use when the user has decided to finetune and needs to choose a technique, or when the technique needs to be validated against a model. Requires a base model to already be selected (via model-selection skill).
Install
npx skills add awslabs/agent-plugins --skill finetuning-technique -a claude-code
Installs to .claude/skills/finetuning-technique/ · 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: APACHE-2.0
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 81
Security85
Provenance76
Maintenance100
Licence100
Adoption48
Files (3)
- SKILL.md
- references/finetune_technique_selection_guide.md
- scripts/get_recipes.py