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
721768 · page 16 / 244
qt-translation-workflowSet up Qt Linguist workflow with .ts files, lupdate/lrelease integration, and translation managementa5c-aiwritesralph-autonomousUse this skill when Ralph is working autonomously through Brain Dump backlogs. Covers ticket selection, implementation patterns…majiayu000ralphSelf-referential loop until task completion with architect verificationmajiayu000ralphPersistent completion mode. Use when the user explicitly says `/ralph` or clearly wants you to keep iterating until the task is…majiayu000ralph-json-create-issuesConverts a PRD or plan markdown file into prd.json format for ralph-json-start-loop to execute autonomously. Use when user wants…majiayu000ralph-loopActivate autonomous Ralph Wiggum loop mode for iterative task completion. Use when you have a well-defined task with clear…majiayu000ralph-loopAutonomous feature development loop. Executes complete 9-phase cycle (Interview -> Think Critically -> Plan -> Branch ->…majiayu000ralph-loopIterative development loop methodology for autonomous AI work. Configure self-correcting coding loops that iterate until…majiayu000ralph-loopExecute an autonomous development loop that picks one task per iteration, implements it, verifies it, and commits the result —…majiayu000ralph-loopRalph Loop plugin manager. Provides start, cancel, status, and help commands for autonomous task loops. Enforces safety…majiayu000ralph-prompt-multi-taskGenerate Ralph-compatible prompts for multiple related tasks. Creates phased prompts with sequential milestones, cumulative…majiayu000ralph-prompt-single-taskGenerate Ralph-compatible prompts for single implementation tasks. Creates prompts with clear completion criteria, automatic…majiayu000ralph-runnerRun long-running autonomous AI agents using PRD-based task scoping.majiayu000ralph-tuiRun ralph-tui task loops for automated PRD execution. Covers headless mode, PRD preparation, agent selection (opencode/claude)…majiayu000ralph-wiggumAutonomous task completion loop with PRD tracking and LLM memorymajiayu000ralphyAutonomous AI coding orchestration using the Ralph Wiggum technique and Ralphy CLI. This skill should be used when running AI…majiayu000read_paperConvert a research paper into structured Obsidian notes and link research projectsmajiayu000reasoning-frameworkReasoning and planning framework. Defines task analysis, risk assessment, hypothesis forming. Applied automatically for complex…majiayu000ref-toon-formatTOON format knowledge and usage patterns for agent communication and memory persistence in plan-marshall marketplacemajiayu000request-classifierClassify any user request into a structured format for prompt generation. Use this skill whenever you need to understand what…majiayu000researchUse when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.majiayu000research-architectUse when a user needs the end-to-end Research Architect workflow to turn a raw idea, user-designated accessible target reference…mmTheBestresearchUse when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.majiayu000research-codebaseResearch a task, problem, bug, or feature by exploring the codebase. Use when starting new work, encountering bugs, or needing to…majiayu000research-codebaseResearch a task, problem, bug, or feature by exploring the codebase. Use when starting new work, encountering bugs, or needing to…majiayu000research:createCreate a research plan with parallel investigation tasks. Use when exploring a topic, analyzing external code, or gathering…majiayu000researchWhen user says "research" (in any form), ALWAYS invoke this skill.majiayu000researchWhen user says "research" (in any form), ALWAYS invoke this skill.majiayu000research-deep读取调研outline,为每个item启动独立agent进行深度调研。禁用task output。majiayu000writesresearch-deepRead research outline, launch independent agent for each item for deep research. Disable task output.majiayu000writesresearch-deep读取调研outline,为每个item启动独立agent进行深度调研。禁用task output。majiayu000writesresearch-deepRead research outline, launch independent agent for each item for deep research. Disable task output.majiayu000research-executorExecute research experiments using TDD methodology. Pops plans from .claude/plans/research_tasks/, implements with…majiayu000researchUse when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.majiayu000research-handoff-oracleUse when asked to create a deep-research handoff bundle: do web research, codebase analysis, Gemini Oracle critique, and produce…majiayu000researchUse when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.majiayu000research-pipelineUse when you need a complete research workflow from initial literature search to polished, fact-checked document. Chains…majiayu000research-pipelineUse when you need a complete research workflow from initial literature search to polished, fact-checked document. Chains…majiayu000research-refine-pipelineRun an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from…majiayu000writesresearch-refine-pipelineRun an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from…majiayu000research-synthesis-workflowSystematic methodology for gathering, analyzing, and synthesizing research from multiple sources into coherent insights and…majiayu000researchUse when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.majiayu000research-to-practiceTransform academic research insights into practical workflow optimizationsmajiayu000researchResearch a topic and create a new note in the vault. Use this skill whenever the user wants to learn about a topic they don't…majiayu000writesretellai-prod-checklistRetell AI prod checklist \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents…jeremylongshorewritesretention-analysisStructure a retention analysis, churn investigation, or engagement deep-dive for any product team. Use when asked to analyse user…majiayu000Revise Report GenerationGenerates structured revise reports for Epics by aggregating task comments and learnings. Use when: (1) An Epic is completed or…majiayu000rich-elicitationAsks clarifying questions in multiple rounds before starting ambiguous tasks. Fires when 2+ task dimensions each have 3+ viable…majiayu000
← Prev16 / 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