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.
49,409 skills from 2,375 repositories · updated 41 minutes ago
6,338 skills
- production-code-quality-reviewdengyie/awesome-skillsUse when reviewing pull requests, diffs, architecture-sensitive changes, reliability risks, production readiness, merge readiness, or requests to review like a senior engineer. Focuses on correctness, robustness, maintainability, observability, tests, security, and production risk rather than style-only review.EngineeringNo warnings★ 75↓ —
- auditcodexsterlingcrispin/claude_slash_commandsSend recent work to OpenAI Codex CLI for an independent audit/reviewEngineeringNo warnings★ 199↓ —
- 27_ATC_DDDBioTender-max/awesome-bio-agent-skillsQuery the WHO ATC/DDD Classification System. Use whenever the user asks about ATC codes, drug classification hierarchy, Defined Daily Doses (DDD), or wants to look up drugs by ATC class or find the ATC code for a drug name.EngineeringNo warnings★ 214↓ —
- faers-queryBioTender-max/awesome-bio-agent-skillsQuery the FDA Adverse Event Reporting System (FAERS) via openFDA API. Use whenever the user asks about adverse drug reactions, side effects, drug safety signals, or wants to look up reported adverse events for one or more drug names.EngineeringNo warnings★ 214↓ —
- patient-education-readability-reviewallinherog-star/ai-skills资料整理助手适合运营、市场营销、healthcare、教育培训在用户提出“这份材料重点是什么”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。EngineeringNo warnings★ 53↓ —
- software-cost-quote-reviewallinherog-star/ai-skills业务诊断助手适合technical、管理者、software、软件成本在用户提出“这件事该怎么做”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。EngineeringNo warnings★ 53↓ —
- self-improvementpskoett/pskoett-ai-skillsCaptures learnings, errors, corrections, and feature requests to enable continuous improvement. Use when: (1) User corrects Claude ('No, that's wrong...', 'Actually...'), (2) User requests a capability that doesn't exist, (3) Claude realizes its knowledge is outdated or incorrect, (4) A better approach is discovered for a recurring task, (5) Receiving a Handoff block from self-healing (a recurring verified heal with Recurrence-Count at least 3) to distill into a memory file or new skill. For ACTIVE runtime failures where the agent needs to apply and verify a fix mid-task, use `self-healing` instead (it files HEAL- entries with proof; self-improvement promotes accumulated patterns). Also review learnings before major tasks. For CI-only/headless learning capture, use self-improvement-ci.EngineeringReview first★ 327↓ —
- testdriver:debugging-with-screenshotstestdriverai/testdriveraiDiagnose failing tests with screenshots, replays, and logsEngineeringReview first★ 462↓ —
- douyin-script-reviewallinherog-star/ai-skills业务诊断助手适合内容创作者、运营、市场营销、内容媒体在用户提出“这件事该怎么做”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。EngineeringNo warnings★ 53↓ —
- ai-visual-prompt-reviewallinherog-star/ai-skills视觉质量诊断助手适合设计、运营、市场营销、内容创作者在用户提出“这张图够发布吗”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。EngineeringNo warnings★ 53↓ —
- google-file-api-expertsaeed-vayghan/gemini-agent-skillsExpert in Google Gemini File API, File Search, and RAG implementation. Capable of handling file uploads, managing File Search Stores, and implementing RAG workflows in Python and JavaScript.EngineeringNo warnings★ 53↓ —
- review-codeserpro69/claude-toolboxCode review of current git changes with an expert senior-engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements. Use when performing code reviews.EngineeringReview first★ 155↓ —
- clinic-service-review-analysisallinherog-star/ai-skills业务诊断助手适合运营、市场营销、healthcare、教育培训在用户提出“这件事该怎么做”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。EngineeringNo warnings★ 53↓ —
- collaborating-with-claudeappautomaton/agent-designerDelegate tasks to Claude Code CLI for prototyping, debugging, and code review. Supports multi-turn sessions via SESSION_ID.EngineeringNo warnings★ 133↓ —
- polars-dovmedBioTender-max/awesome-bio-agent-skillsSearch the PMC Open Access literature with polars-dovmed. Author structured JSON queries directly, then use the hosted API when an API key is available or fall back to local dovmed scan over PMC, bioRxiv, or both parquet corpora.EngineeringNo warnings★ 214↓ —
- bio-single-cell-clusteringBioTender-max/awesome-bio-agent-skillsDimensionality reduction and clustering for single-cell RNA-seq using Seurat (R) and Scanpy (Python). Use for running PCA, computing neighbors, clustering with Leiden/Louvain algorithms, generating UMAP/tSNE embeddings, and visualizing clusters. Use when performing dimensionality reduction and clustering on single-cell data.EngineeringNo warnings★ 214↓ —
- medlineplus-drug-infoBioTender-max/awesome-bio-agent-skillsQuery MedlinePlus for consumer-oriented drug and health-topic information. Accepts drug names, RxCUI codes, NDC codes, or ICD-10-CM diagnosis codes. Uses two free, keyless NLM APIs: the Web Service (keyword search) and MedlinePlus Connect (code-based lookup).EngineeringNo warnings★ 214↓ —
- testdriver:debugging-with-screenshotstestdriverai/testdriveraiView and analyze saved screenshots using MCP commands for test debugging and developmentEngineeringReview first★ 462↓ —
- ai-hr-performance-reviewallinherog-star/ai-skills绩效评语助手适合运营、产品、销售、software在用户提出“绩效反馈怎么写”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成运营诊断、商品/流量优化建议、执行清单。EngineeringNo warnings★ 53↓ —
- ai-customer-review-aggregatorallinherog-star/ai-skills客户评论洞察助手适合运营、产品、销售、software在用户提出“评论里藏着什么”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成评论聚类、痛点归因、运营动作卡。EngineeringNo warnings★ 53↓ —
- iuphar-pharmacologyBioTender-max/awesome-bio-agent-skillsQuery the IUPHAR/BPS Guide to Pharmacology REST API for drug targets, ligands (drugs/compounds), and their interactions. Use whenever the user asks about pharmacological targets, receptor–ligand relationships, drug mechanisms of action, or wants to look up any drug or target name in IUPHAR. Supports single entity or batch queries. No API key required.EngineeringNo warnings★ 214↓ —
- collaborating-with-codexappautomaton/agent-designerDelegate tasks to Codex CLI for prototyping, debugging, code review, implementation handoff, cross-model second opinions, and multi-turn Codex sessions via SESSION_ID.EngineeringNo warnings★ 133↓ —
- claw-shellBioTender-max/awesome-bio-agent-skillsUse this skill whenever any NeuroClaw skill, sub-agent, or model needs to execute shell commands safely (e.g. source environment scripts, run recon-all, git operations, conda commands, ls, cat logs, etc.). Triggers include: 'run shell', 'execute command', 'shell command', 'tmux claw', 'run in claw session', 'safe shell execution', or any request that requires running terminal commands. This skill is the mandatory gatekeeper for all shell execution in NeuroClaw: it ALWAYS routes commands through the dedicated tmux session `claw`, never touches other sessions, and returns captured output to the calling agent.EngineeringNo warnings★ 214↓ —
- Git Smart Commitdeancourse/git-worktree-demo將雜亂的 git 變更，依功能邏輯自動拆分成多個有意義的 conventional commitEngineeringNo warnings★ 101↓ —