Agent skills

AI & Agents 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
4,965 found
4,4174,464 · page 93 / 104
recursive-context-pruning-token-budgetingOptimizes AI agent performance by pruning redundant context, managing token usage, and enforcing ultra-concise, direct-to-value…sickn33Redação e Melhoria de Textos sobre Consolidação de Contas com Normas APASkill para reescrever ou melhorar seções específicas sobre consolidação de contas (tipos, métodos, processos), respeitando…ECNU-ICALKredirect-managerManage URL redirects. Use when: creating 301/302 redirects, auditing chains, fixing loops, or deploying via CMS MCP.indranilbanerjeereference-class-forecasterReference class forecasting skill to counter optimism bias using historical analogiesa5c-aiwritesRefine instructions into single-line LLM promptsTransforms raw user instructions into optimized, single-line prompts suitable for LLMs, acting as a prompt engineer.ECNU-ICALKrefiner-automationAutomate Refiner tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQregex / string / thatGeneral SOP for common requests related to charter, canadian, freedoms.ECNU-ICALKregex-vs-llm-structured-textDecision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for…mturacregression-analyzerSkill for comprehensive regression analysis and modelinga5c-aiwritesremarkety-automationAutomate Remarkety tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQrememberTransforms lessons learned into domain-organized memory instructions (global or workspace). Syntax: `/remember [>domain [scope]]…githubrememberStore a learning, pattern, or decision in the memory system for future recallparcadeirememberStore a learning, pattern, or decision in the memory system for future recall.vibeevalreminder-system-creatorCreate reminder system creator operations. Auto-activating skill for Business Automation. Triggers on: reminder system creator…jeremylongshorewritesremote-compute-sshSubmit recoverable SSH-direct research Runs with live progress cards and model-free monitoring.xuzhougengremote-retrieval-automationAutomate Remote Retrieval tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQremove-bg-automationAutomate Remove Bg tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQremove-subUnsubscribe from a skill event. Removes or disables subscriptions with scope-aware options.composio-communityrender-automationAutomate Render tasks via Rube MCP (Composio): services, deployments, projects. Always search tools first for current schemas.davepoonrender-automationAutomate Render tasks via Rube MCP (Composio): services, deployments, projects. Always search tools first for current schemas.sickn33renderform-automationAutomate Renderform tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQrental-applicationWrite a standout rental application / cover letter to a landlord or letting agent. Use when asked to write a rental application…mohitagw15856repairshopr-automationAutomate Repairshopr tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQReplicate AutomationAutomate Replicate AI model operations -- run predictions, upload files, inspect model schemas, list versions, and manage…ComposioHQreplicateBuild and verify replication packages — routes to reproducibility-auditor agentbrycewang-stanfordreplication-feasibility-assessorSkill for assessing feasibility of study replicationa5c-aiwritesreplit-performance-tuningOptimize Replit app performance: cold start, memory, Nix caching, and deployment speed. Use when experiencing slow startup, high…jeremylongshorewritesreplit-webhooks-eventsHandle Replit deployment events, build Replit Extensions, and set up Agents & Automations. Use when integrating with Replit…jeremylongshorewritesreply-automationAutomate Reply tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQreply-io-automationAutomate Reply IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQrepo-scanningInternal process for the repo-scanner agent. Defines the step-by-step procedure for scanning GitHub repos for evidence that…jeremylongshorereport-generatorGenerate report generator operations. Auto-activating skill for Business Automation. Triggers on: report generator, report…jeremylongshorewritesrequirements-flowdownSkill for systematic requirements capture, decomposition, and traceabilitya5c-aiwritesrequirements-verificationSkill for aerospace requirements verification and validation matrix managementa5c-aiwritesresearch-ideaUse this skill whenever the user wants to generate or refine a research idea through literature search and discussion. Triggers…BioTender-maxdeep-researchGOD MODE deep research skill. Multi-phase autonomous research loop: query decomposition → multi-source crawling → claim…shobcoderresearch-paper-kbBuild a persistent cross-session knowledge base from academic papersbrycewang-stanfordresearch-promptTurn vague research needs into one precise deep-research prompt with context and output criteria.sickn33research-synthesizeSynthesize research findings from memory into structured reports with evidence grading, contradiction resolution, and actionable…ruvnetwritesresend-automationAutomate Resend tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQresource-estimatorQuantum resource estimation skill for algorithm feasibility analysisa5c-aiwritesresource-schedulerResource scheduling and assignment optimization skill for personnel and equipment allocationa5c-aiwritesrespond-io-automationAutomate Respond IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQrespond-to-refereeStructure point-by-point referee responses for the sewage-house-prices paper. Classifies each comment (NEW ANALYSIS /…brycewang-stanfordwritesresponse-time-analyzerAnalyze response time analyzer operations. Auto-activating skill for Performance Testing. Triggers on: response time analyzer…jeremylongshorewritesretailed-automationAutomate Retailed tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQretellai-automationAutomate Retellai tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQretellai-hello-worldRetell AI hello world \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents, phone…jeremylongshorewrites
← Prev93 / 104Next →
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