Agent skills

Workflow & Productivity 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
11,684 found
817864 · page 18 / 244
Smart Intent DetectionAutomatic workflow suggestion and utility agent routing based on prompt analysis. Trigger keywords: auto-detect, intent, suggest…majiayu000smart-git-automationSmart change detection, auto branch naming, and streamlined commit/PR workflowsickn33smart-routerMulti-tier LLM routing achieving 90% FREE tier processing through intelligent task classification.majiayu000smart-routingComplexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.a5c-aiwritessoulUse when starting any task, thinking through confidence, verifying work, or asking "what could go wrong". Triggers on every…majiayu000spawn-agentSpawn PAI agents via MCP factory tool. Loads identity, injects RAG context, validates spawn chain, and executes via Task(). The…majiayu000spawn-agentSpawn PAI agents via MCP factory tool. Loads identity, injects RAG context, validates spawn chain, and executes via Task(). The…majiayu000speak-core-workflow-aExecute Speak primary workflow: AI Conversation Practice with real-time feedback. Use when implementing conversation practice…jeremylongshorewritesspeak-core-workflow-bExecute Speak secondary workflow: Pronunciation Training with phoneme-level analysis. Use when implementing pronunciation drills…jeremylongshorewritessynapse-specialized-actionsExplains specialized Synapse action classes for specific workflows. Use when the user mentions "BaseTrainAction"…majiayu000statistical-modelingRegression analysis, ANOVA, generalized linear models, Bayesian methods, and model selection. Covers the full modeling workflow…majiayu000statistical-power-calculatorUse when asked to calculate statistical power, determine sample size, or plan experiments for hypothesis testing.majiayu000statusCheck task status in the tracker and local artifacts. Use when the user invokes /status or asks for project/task status.majiayu000stb-liquiditaetsvorschau-3wochenWenn es um Drei-Wochen-Liquiditaetsvorschau in Steuerrecht – Steuerberater und Anwälte geht: prüft Frist, Form, Zuständigkeit…Klotzkettestrategic-investigationProactive recovery using plan mode and subagents. After 1-2 failed attempts, STOP trying variations. Enter plan mode and launch…majiayu000structural-analysisStatics, dynamics, stress-strain analysis, materials selection, failure modes, and finite element analysis concepts for…majiayu000studioSmart router — describe your task and get routed to the right agent or skill. Start here if you don't know which skill to use.majiayu000sub-agent-patternsComprehensive guide to sub-agents in Claude Code: built-in agents (Explore, Plan, general-purpose), custom agent creation…majiayu000sub-agent-patternsComprehensive guide to sub-agents in Claude Code: built-in agents (Explore, Plan, general-purpose), custom agent creation…majiayu000subagent-driven-developmentUse when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent per task.a5c-aisurge-retentionRetention diagnosis + intervention plan — analyze the retention curve, identify the primary drop-off point, and produce a…jeremylongshorewritesswing-researchDeep research with cross-verification and source tiering. Use when investigating technologies, comparing tools, fact-checking…majiayu000writesswing-researchDeep research with cross-verification and source tiering. Use when investigating technologies, comparing tools, fact-checking…majiayu000writesswitch-persona> Note: This skill has been adapted from claude-skillzmajiayu000swot-analysisAnalyze Strengths, Weaknesses, Opportunities, and Threats when you need to make strategic decisions, evaluate positions, or plan…majiayu000systems-thinkingApply systems thinking to leadership decisions and produce a Systems Thinking Pack (system boundary, actors & incentives map…majiayu000t-decisionDecide whether a feature should enter the t-tools workflow before tech research or PRD.timzaakwritestask-analyzerSelects the smallest set of task-execution skills and metacognitive safeguards for standalone task and diagnosis workflows.shinprtask-assignment-problemWhen the user wants to optimize task assignments, match workers to jobs, or solve assignment problems. Also use when the user…majiayu000task-clarifierDeep need-clarification skill. Activates only on explicit invocation: direct reference to $task-clarifier, or trigger phrases…dongshuyantask-completion-focusFocuses on a specific target object to signal task completion. Execute this skill when you have produced the required final…majiayu000task-decompositionConvert technical plans into actionable development tasks with dependency graphs, effort estimates, and parallelization…a5c-aiwritestask-intent-skillAI reasoning skill for detecting user intents from natural language, mapping to MCP tools, handling multi-step workflows, and…majiayu000taxonomic-classificationNaming and classifying organisms through binomial nomenclature, the Linnaean hierarchy, type specimens, and the rules governing…majiayu000team-collaboration-standup-notesYou are an expert team communication specialist focused on async-first standup practices, AI-assisted note generation from commit…sickn33teams-deep-analysisTeam-based deep exploration and synthesis workflow using Agent Teams with dynamic planning and hub-and-spoke coordination. Use…majiayu000writesthesis-outlineBuild a defensible thesis or dissertation outline — argument-first structure, chapter by chapter, with the through-line visible.…mohitagw15856think-scrutinizeGood-faith adversarial scrutiny of an idea or plan. Spawns critical skeptics across relevant lenses, pairs them with an advocate…majiayu000thinking-debiasingSystematic checklist to identify and counteract cognitive biases in decision-making. Use before major decisions, when evaluating…majiayu000timeboxed-iteratingUse when the user specifies a task and a duration, and the work should be done iteratively by subagents over that time periodavtoken-planPort of .claude/commands/token-plan.md for Codex.majiayu000tokenwiseMeasurement-driven model router for Claude Code. Routes Haiku/Sonnet/Opus per task class, logs every routed task with real $…majiayu000tool-selectionUse when selecting between MCP tools based on task complexity and requirements - provides a structured selection workflow and…majiayu000toon-usageTOON format knowledge and usage patterns for agent communication and memory persistence in plan-marshall marketplacemajiayu000transformation-workflowPractical application guide for HUMMBL's 6 transformations (Perspective, Inversion, Composition, Decomposition, Recursion…majiayu000transformation-workflowPractical application guide for HUMMBL's 6 transformations (Perspective, Inversion, Composition, Decomposition, Recursion…majiayu000transport-propertiesThis skill group covers first-principles calculation of electronic transport properties using the Boltzmann transport equation…majiayu000doctor-treatmentProduce a treatment note that combines diagnosis, confidence, supporting evidence, alternative explanations, and proposed…majiayu000
← Prev18 / 244Next →
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