Agent skills

Other skills

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 62,644codex 9,699cursor 6,852copilot 2,269windsurf 126cline 82
CategoryWorkflow & Productivity 11,684AI & Agents 4,965Data & Analytics 4,693Code Review & Quality 2,936Security 2,762Backend & API 2,480Design & Presentation 2,329Documentation 2,157Content & Marketing 2,001Testing & QA 1,723DevOps & Cloud 1,266Databases 1,124Frontend 1,015Business & Finance 706Media & Video 507Other 21,420
21,420 found
4,3694,416 · page 92 / 447
repo-mapGenerate a ranked codebase map showing key files and relationshipsmajiayu000repo-scannerDeep scan repository structure to extract metadata, detect frameworks, and identify domain boundaries. Use when starting…majiayu000repo-scanningScan and document repository structure, patterns, and key components. Use when starting work on unfamiliar codebases.majiayu000reporting-chest-radiographsStructures systematic chest X-ray interpretation with standardized reporting and critical findings communication. Use when…majiayu000representation-ethicsThe question isn't whether we CAN simulate people. It's how we do it with dignity.majiayu000request-debuggerHTTP request/response debugging and inspection toolsa5c-aiwritesrequesthuntGenerate user demand research reports from real user feedback. Scrape and analyze feature requests, complaints, and questions…majiayu000requirements-clarityClarify ambiguous requirements through focused dialogue before implementation. Use when requirements are unclear, features are…softaworksrequirements-interviewInteractive PM interview with expertise-adaptive questioning for requirements elicitationa5c-aiwritesrerank-service文档重排序服务(Reranker)。基于深度学习模型对检索候选结果进行细粒度相关性打分与重新排序,显著提升检索结果的精准度(Top-K 准确率)。majiayu000research-add-fieldsAdd field definitions to existing research outline.majiayu000writesresearch-add-fieldsAdd field definitions to existing research outline.majiayu000writesresearch-add-fieldsAdd field definitions to existing research outline.majiayu000research-add-itemsAdd items (research objects) to existing research outline.majiayu000writesresearch-add-itemsAdd items (research objects) to existing research outline.majiayu000writesresearch-add-itemsAdd items (research objects) to existing research outline.majiayu000researchMulti-source parallel research with confidence-based synthesis.majiayu000research-analystConducts thorough landscape research, competitive analysis, best practices evaluation, and evidence-based recommendations. Expert…majiayu000research-analystConducts thorough landscape research, competitive analysis, best practices evaluation, and evidence-based recommendations. Expert…majiayu000research-architect-brainstormUse when a user needs distinct, feasible Research Architect research-question options from a raw topic, available materials…mmTheBestresearch-architect-citationUse when a Research Architect project or existing draft needs claim-level literature support for background, positioning…mmTheBestresearch-architect-draftUse when a Research Architect project has an evidence-ready spine, evidence and claim trail, citation support, terminology/object…mmTheBestresearch-architect-evidenceUse when executed research materials, results, observations, analyses, or draft claims need to become a Research Architect…mmTheBestresearch-architect-literatureUse when a Research Architect project needs accessible target-reference papers analyzed for transferable research logic, or…mmTheBestresearch_assistantSearch academic papers, find citations, and explore research using Semantic Scholar. Use when user asks about scientific papers…majiayu000research-assistantConducts general research, summarizes information, compares options, provides insightsmajiayu000research-assistantConduct structured research with sourced summaries, confidence ratings, and hierarchical findings.majiayu000researchMulti-source research across code, discourse, and academic channels.majiayu000researchSystematic investigation and root cause analysis. Use when debugging persistent issues, understanding complex systems, or before…majiayu000researchDeep codebase exploration with multi-angle analysis for Codex agents. Output: .agents/research/*.md. Triggers: "research"…majiayu000research-briefing快速梳理调研问题、提炼事实与不确定性、给出后续实验/访谈/数据拉取建议的通用调研简报模板。majiayu000research-cacheCaches research findings to avoid redundant web searches. Stores best practices by topic with sources and dates. Use before…majiayu000writesresearchDocument codebase as-is with thoughts directory for historical contextmajiayu000research-cascadeMulti-source research orchestration. Chains deepwiki, submodules, WebSearch, and codebase search. Defines when to escalate and…majiayu000researchOrchestrate parallel scientist agents for comprehensive research with AUTO modemajiayu000research-cited-report調査→論点整理→出典付きレポート化。ユーザーが「調べて」「比較して」「根拠/出典付きで」等を求めたら使う。majiayu000researchUse when the user asks to research, investigate, compare approaches, or explore a topic in depth. Supports configurable depth and…majiayu000research-codebaseStructured investigation of unfamiliar codebasesmajiayu000research-councilLightweight parallel research orchestration without full council debate. Spawns oracle agents with different queries, collects…majiayu000researchGather external context on a topic. Use when you need industry trends, best practices, evidence base, and recent developments…majiayu000researchBefore executing, check for user customizations at:majiayu000researchBefore executing, check for user customizations at:majiayu000research-directorStrategic research leadership for designing high-impact research agendas, coordinating teams, and translating research into…brycewang-stanfordresearch-engineAutonomous research pipeline — topic to structured documents with HTML/PDF output. Proven at HEL (28 docs, 91K words) and OOPS (9…majiayu000research-engineerAn uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair.…majiayu000research-evaluateEvaluate a research source from report_notes, understand its purpose, and create a Linear issue.majiayu000writesresearch-first-devResearch-first development methodology that investigates existing solutions, brainstorms alternatives, and evaluates trade-offs…a5c-aiwritesresearch-frameworkStructured deep research methodology for complex technical questions, including source evaluation, synthesis, and comprehensive…majiayu000
← Prev92 / 447Next →
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