Agent skills

Skills matching “skill”

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
697 found
385432 · page 9 / 15
rag-accuracy-skillMeasure RAG answer quality through three core metrics: Faithfulness (accuracy to context), Relevance (retrieval quality), and…majiayu000RAG Architecture SkillBuild retrieval-augmented generation systems that ground LLMs in your data.majiayu000rag-skillsRAG-specific best practices for LlamaIndex, ChromaDB, and Celery workers. Covers ingestion, retrieval, embeddings, and…majiayu000tech-research-skill-builderResearch latest library documentation, industry best practices, and technical knowledge to automatically generate project-level…majiayu000research-brief-skillLightweight source-backed research and synthesis for normal Reviva agents. Use when the user asks to summarize materials, compare…mingchen666research-report-weizhena-deep-research-skills-2Summarize deep research results into markdown report, cover all fields, skip uncertain values.majiayu000writesresearch-skill调研最佳实践的 Skill。当需要了解某个领域的方法论、工具、最佳实践时触发。触发词:调研、research、了解一下、有什么方法、最佳实践。majiayu000researcher-role-skillProfessional technical solutions research skill for investigating technologies, analyzing best practices, evaluating feasibility…majiayu000risk-assessment-ml-datadrivenconstructi-ddc-skills-for-ai-agApply machine learning for construction project risk assessment. Predict schedule delays, cost overruns, and safety incidents…majiayu000Reinforcement Learning SkillRL training for robot control using simulation with sim-to-real transfera5c-aiwritesReinforcement Learning SkillRL training for robot control using simulation with sim-to-real transfermajiayu000writesrollback-automation-skillAutomate rollback procedures with state snapshots, rollback scripts, and verification automationa5c-aiwritesroot-level-skill-fixtureMinimal fixture skill for regression coverage of root-level SKILL.md discovery. Use when validating that find_skill_files picks…jeremylongshoreros2_control SkillHardware abstraction and controller management using ros2_control frameworka5c-aiwritesrouting-skill-graphUse when routing skill graph is required during kernel work, especially when the result must be traceable, independently…casioreview20-glitchRubber Duck Debugging SkillBe a thinking partner. The answer often emerges when explaining the problem.majiayu000runtime-skillsUniversal Runtime best practices for PyTorch inference, Transformers models, and FastAPI serving. Covers device management, model…majiayu000RViz Visualization SkillRViz configuration and custom visualization for robot development and debugginga5c-aiwritesSafety System SkillRobot safety system design and validation for industrial and collaborative robotsa5c-aiwritessample-skillA sample skill for testing the validator. Helps with greeting generation.dotnetsanctions-screening-legal-analysis-skill-english-gillan-salehSanctions and export control analysis tool for Claude Desktop. Real-time individual screening across 30+ official lists (UN, EU…lawve-aiscientific-skillsScientific research and analysis skills. Use when performing scientific analysis, literature review, or research methodology…majiayu000scientific-skillsComprehensive scientific research toolkit with 139 specialized skills for biology, chemistry, medicine, data science, and…majiayu000platxa-skill-generatorAutonomous skill creator for Claude Code CLI. Uses multi-phase orchestrated workflow with Task tool subagents to research…majiayu000writessec-edgar-skillSEC EDGAR filing analysis using EdgarTools. Use when user asks about SEC filings, company financials, 10-K/10-Q analysis, insider…majiayu000secure-coding-training-skillDeveloper security training and assessment for secure coding practices and vulnerability preventiona5c-aiwritesSim-to-Real Transfer SkillTechniques for minimizing simulation-to-reality gap and validating transfera5c-aiwritesSim-to-Real Transfer SkillTechniques for minimizing simulation-to-reality gap and validating transfermajiayu000writessingle-cell-annotation-skills-with-omicverseGuide Claude through SCSA, MetaTiME, CellVote, CellMatch, GPTAnno, and weighted KNN transfer workflows for annotating single-cell…FreedomIntelligenceskill-authorThe authoring gate for new skills. Routed to when the user invokes /new-skill "<gap>". Five gated phases — gap evidence, scope…arbiterForgeskill-creatorCreate, structure, and package agent skills. Use when designing new skills, updating existing skills, or helping users build…gooseworks-aiskill-developmentThis skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill…anthropicsskill-index-updaterAdd GitHub skill repos to the ASM index: clone, audit, eval, regenerate index, rebuild catalog, open PR. Use when given GitHub…luongnv89writesskill-injection-defenseAudits legal AI skills, prompts, workflows, MCP/tool instructions, and agent packages for prompt injection, malicious…lawve-aiskill-installation审查、安装、配置、激活、验证、更新和回滚 AgentDock Skill 时使用;负责来源校验、安全评估、环境配置和已安装版本验收。uvwtskill-installer跨平台智能安装助手:自动检测操作系统,适配Windows/macOS/Linux命令,处理Git/网络/路径问题。当用户说"安装skill"、"帮我安装xxx"、"我下载了skill,路径是xxx"时触发。mingchen666skill-judgeEvaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or…softaworksskill-model-checkerResearch and develop semantic theories using ModelChecker with Z3 SMT solver. Define operators, adjust frame constraints, create…majiayu000writesskill-neovim-researchResearch Neovim APIs, plugin patterns, and Lua development. Invoke for lua-language research tasks.majiayu000skill-portingInstall skills from external ecosystems into this agent's agent_state/skills/ — resolve Claude Code plugin marketplaces, the…Prism-Shadowskill-python-researchResearch Python/Z3 patterns and APIs for semantic theory development. Invoke for Python-language research tasks.majiayu000writesskill-researcherConduct general research using web search, documentation, and codebase exploration. Invoke for general research tasks.majiayu000writesskill-researcherConduct general research using web search, documentation, and codebase exploration. Invoke for non-Lean research tasks.majiayu000writesskill-researcherConduct general research using web search, documentation, and codebase exploration. Invoke for non-Lean research tasks.majiayu000writesskill-suggesterScan prompt history for recurring patterns and unmet needs, then propose new skills or command templatessickn33skillgrade-gradersAuthors deterministic and LLM rubric graders for skillgrade evaluations. Use when creating scoring scripts, writing evaluation…mgechevskills-auditAudit .agents/skills SKILL.md files. Use for recurring checks of duplicate, overlapping, stale, inconsistent, or broken skills…lobehubskillsUse this skill when the user asks "/think" or when you face a complex architectural challenge.majiayu000
← Prev9 / 15Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going