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.
46,095 skills from 2,198 repositories · updated 12 seconds ago
9,543 skills
- sample-skillkyungseo/skillsteadReplace this reserved identity and describe the concrete user outcome, selection boundary, and important non-goals. Do not use this package before every sample-skill identity has been replaced.OtherNo warnings★ 84↓ —
- define-strategykonglong87/superPM专为产品经理设计的 AI工具 Skills技能，一键实现全生命周期的产品管理工作流。skills frame for superPM！OtherNo warnings★ 84↓ —
- alterlab-snaAlterLab-IEU/AlterLab-Academic-SkillsApplies social-network-analysis method discipline to relational data — degree/betweenness/closeness/eigenvector centrality and PageRank, community detection (Louvain, greedy-modularity, and — from networkx 3.7 — Leiden native in networkx; igraph/leidenalg for large graphs), and inferential network models (ERGM) — choosing the measure that matches the substantive question and the right dependence assumptions, then routing computation to the existing networkx (and igraph/R) tooling. Use when the request mentions social network analysis, centrality, key players/brokerage, community or cluster detection in a network, ERGM, or modeling ties between nodes. For general graph algorithms and plotting prefer alterlab-networkx; for graph neural networks prefer alterlab-torch-geometric. Part of the AlterLab Academic Skills suite.OtherNo warnings★ 78↓ —
- run2_time-formattingcxcscmu/SkillLearnBenchFormat dates and times with strict adherence to required formatsOtherNo warnings★ 91↓ —
- constrained-optimizationparcadei/Continuous-Claude-v3Problem-solving strategies for constrained optimization in optimizationOtherNo warnings★ 3.9K↓ —
- work-to-skillaAAaqwq/AGI-Super-Team工作即技能：每次完成一项有复用价值的工作后，自动评估并封装为可复用 Skill。让团队在工作中持续进化。OtherNo warnings★ 112↓ —
- box-automationaAAaqwq/AGI-Super-TeamAutomate Box cloud storage operations including file upload/download, search, folder management, sharing, collaborations, and metadata queries via Rube MCP (Composio). Always search tools first for current schemas.OtherNo warnings★ 112↓ —
- graph-algorithmsparcadei/Continuous-Claude-v3Problem-solving strategies for graph algorithms in graph number theoryOtherNo warnings★ 3.9K↓ —
- modular-arithmeticparcadei/Continuous-Claude-v3Problem-solving strategies for modular arithmetic in graph number theoryOtherNo warnings★ 3.9K↓ —
- decision-reversibilityitseffi/agentic-osClassify decisions as Hat/Haircut/Tattoo by reversibility. Use to calibrate how much analysis a decision deserves.OtherNo warnings★ 117↓ —
- 1c-db-listDesko77/claude-code-skills-1cУправление реестром баз данных 1С (.v8-project.json). Используй когда пользователь говорит про базы данных, список баз, "добавь базу", "какие базы есть"OtherNo warnings★ 87↓ —
- influence-strategiesitseffi/agentic-osGenerate influence strategies using Cialdini's seven principles. Use when you need to influence toward an outcome.OtherNo warnings★ 117↓ —
- numerical-integrationparcadei/Continuous-Claude-v3Problem-solving strategies for numerical integration in numerical methodsOtherNo warnings★ 3.9K↓ —
- root-cause-analysisitseffi/agentic-osUncover root causes through recursive Why questioning and consequence exploration. Use before acting on problems.OtherNo warnings★ 117↓ —
- verification-before-completionSummerEngine/summerRun verification and read its output before claiming work done, fixed or passing: evidence first.OtherNo warnings★ 89↓ —Also in 1 other repo
- propositional-logicparcadei/Continuous-Claude-v3Problem-solving strategies for propositional logic in mathematical logicOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- challenging-stakeholder-questionsitseffi/agentic-osGenerate rigorous stakeholder challenge questions for proposal or meeting preparation.OtherNo warnings★ 117↓ —
- run3_skill-1cxcscmu/SkillLearnBench[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.OtherNo warnings★ 91↓ —
- natural-transformationsparcadei/Continuous-Claude-v3Problem-solving strategies for natural transformations in category theoryOtherNo warnings★ 3.9K↓ —
- whatsapp-sendaAAaqwq/AGI-Super-TeamBaileys WhatsApp message sendingOtherNo warnings★ 112↓ —
- reading-deduction-certkazukinagata/shinkoku控除証明書（生命保険料・地震保険料等）の画像を読み取り構造化データを返す。 他のスキルから呼び出されるほか、直接ユーザーが呼び出すことも可能。OtherNo warnings★ 366↓ —
- integration-theoryparcadei/Continuous-Claude-v3Problem-solving strategies for integration theory in measure theoryOtherNo warnings★ 3.9K↓ —
- evidence-reconciliationTheGoat395/Codex-SkillsResolve stale facts and authority conflicts.OtherNo warnings★ 135↓ —
- create-projectaAAaqwq/AGI-Super-TeamCreate new project with breakdownOtherNo warnings★ 112↓ —
audit-agent-surface
JoviDeCroock/pracht
OtherUpdated 10 hours ago
From the author
Inventory what agents can reach in a pracht app — capability exposure (HTTP, WebMCP, remote MCP), `agents` trust config, the destructive-confirmation gate, `llms.txt`, Markdown negotiation, OpenAPI — and report where the surface is wider than intended, or confirm an opt-out app ships none. Use for "audit the agent surface", "what can agents do on my site", "is my MCP endpoint safe", "did this PR widen what agents can reach".
Install
npx skills add JoviDeCroock/pracht --skill audit-agent-surface -a claude-code
Installs to .claude/skills/audit-agent-surface/ · 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 83
Security100
Provenance64
Maintenance100
Licence100
Adoption35
Files (1)
- SKILL.md