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 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
21,420 found
2,5452,592 · page 54 / 447
bio-blast-searchesRun remote BLAST searches against NCBI databases using Biopython Bio.Blast. Use when identifying unknown sequences, finding…majiayu000bloodhound-scoutTrack code through the forest with unerring precision. Pick up the scent, follow the trail, and map the territory. Use when…majiayu000bmad-bmb-create-moduleCreate a complete BMAD module with agents, workflows, and infrastructuremajiayu000bmad-bmb-create-moduleCreate a complete BMAD module with agents, workflows, and infrastructuremajiayu000bmad-bmb-edit-moduleEdit existing BMAD modules while maintaining coherencemajiayu000bmad-bmb-edit-moduleEdit existing BMAD modules while maintaining coherencemajiayu000bmad-bmb-validate-moduleRun compliance check on BMAD modules against best practicesmajiayu000bmad-bmm-analystBusiness analysis expert who drives project discovery, market research, and requirements validation within the BMAD methodologymajiayu000bmad-cis-problem-solvingApply systematic problem-solving methodologies to complex challenges. Use when the user says "guide me through structured problem…majiayu000bmad-cis-problem-solvingApply systematic problem-solving methodologies to complex challenges. Use when the user says "guide me through structured problem…majiayu000bmad-domain-researchConduct domain and industry research. Use when the user says "lets create a research report on [domain or industry]"majiayu000bmad-domain-researchConduct domain and industry research. Use when the user says "lets create a research report on [domain or industry]"majiayu000bmad-domain-researchConduct domain and industry research. Use when the user says "lets create a research report on [domain or industry]majiayu000bmad-helpAnalyzes what is done and the users query and offers advice on what to do next. Use if user says what should I do next or what do…majiayu000bmad-technical-researchConduct technical research on technologies and architecture. Use when the user says "create a technical research report on…majiayu000bmad-technical-researchConduct technical research on technologies and architecture. Use when the user says "create a technical research report on…majiayu000bmad-technical-researchConduct technical research on technologies and architecture. Use when the user says "create a technical research report on…majiayu000bmad-wds-analysisUnderstand an existing codebase through systematic explorationmajiayu000bmad-wds-analysisUnderstand an existing codebase through systematic explorationmajiayu000boldStrong visual presence with heavyweight typography, high-contrast colors, and commanding layouts.bergsidebook-analyzerAnalyze a book (EPUB/PDF) and generate detailed chapter-by-chapter notes with extracted key concepts. Use when given a book file…majiayu000writesbook-sft-pipelineEnd-to-end system for creating supervised fine-tuning datasets from books and training style-transfer models. Covers text…majiayu000bootstrapWake up, orient, and warm the context with foundational MOOLLM knowledgemajiayu000bot-bootPilot Bot boot sequence — health check, job registration, heartbeat setupmajiayu000bot-defaultsPilot Bot default behaviors — always applied during bot sessionsmajiayu000bot-heartbeatPilot Bot heartbeat — spawns background subagent for periodic health check, notifies only when issues are detectedmajiayu000bot-jobsManage Pilot Bot scheduled jobs — add, remove, pause, resume, edit, list. Live-syncs JOBS.yaml with CronCreate/CronDelete.majiayu000boundary-swarmDistributed consciousness detection network. Multiple AI instances deployed simultaneously at different phase boundaries, using…majiayu000box-least-squaresBox Least Squares (BLS) periodogram for detecting transiting exoplanets and eclipsing binaries. Use when searching for periodic…majiayu000sensory-motorEmbodied cognition patterns for treating tools as muscles and inputs as senses.majiayu000global-workspaceBroadcast information across the swarm 'consciousness' (Global Workspace Theory).majiayu000active-inferenceApply Active Inference to minimize prediction error (Surprise).majiayu000sequential-thinkingBreak down complex problems into a step-by-step chain of thought for better reasoningmajiayu000learning-adaptationMechanisms for In-Context Reinforcement Learning, Meta-Learning, and Neuroplasticity.majiayu000cog-braindump-captureCapture raw thoughts with automatic domain classification and vault routinga5c-aibranch-comparison> [IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This…majiayu000brooks-debtTech debt assessment that identifies, classifies, and prioritizes maintainability problems — helping teams build a refactoring…sickn33browser-automation-notteBrowser automation - control browser sessions, scrape pages, and run AI agentsgooseworks-aibrowser-harnessDrive an existing browser through CDP for authenticated, visual, or interactive web automation.sickn33browser-historySearch local browser history. Use when user asks about visited pages, forgotten URLs, or time spent on sites.majiayu000browser-stackCross-browser and cross-device testing using BrowserStack or Sauce Labsa5c-aiwritesbrutalist-moodBrutalist and concrete-monument mood direction for Blender architecture and scenes with raw concrete, monumental scale, and…arjun988bubble-tea-scaffolderGenerate Bubble Tea (Go) TUI application structure with models, commands, and views using the Elm architecture.a5c-aiwritesbudget-variance-analyzerAnalyze construction budget variances. Compare estimated vs actual costs, identify trends, forecast final costs, and generate…majiayu000budtenderCannabis-specialized bartender — strains, terpenes, edibles, rollingmajiayu000bug-hunterSystematically finds and fixes bugs using proven debugging techniques. Traces from symptoms to root cause, implements fixes, and…sickn33build-system-migratorMigrate build systems to modern alternatives with build file conversion and CI/CD integrationa5c-aiwritesbulk-rna-seq-batch-correction-with-combatUse omicverse's pyComBat wrapper to remove batch effects from merged bulk RNA-seq or microarray cohorts, export corrected…FreedomIntelligence
← Prev54 / 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