5,486,830 AI resources indexedWorking toward the world’s largest AI resource index.

PDF

Agent skills

Reusable instructions for compatible AI agents.

How to use the library

Explore by field

Loading catalog totals…
Browse full catalog

Field counts come from the latest full-catalog snapshot. A resource can belong to several fields and platforms.

Resources

Search results
Search stays within agent skills.
Agent skill

Error Learning — Register, Generalize, Prevent

**WORKFLOW SKILL** — Register and generalize agent errors into reusable lessons. USE FOR: when the user corrects the agent, capturing what went wrong, analyzing root cause, generalizing the error into a lesson that prevents recurrence. Use to register errors, analyze mistakes, create lessons, gen...

OpenClawDevelopment & Engineering
AllanSantos-DV0
Agent skill

Task Map — Externalize and Chain

**WORKFLOW SKILL** — Persist analysis so it survives context compression and chains between tasks. USE FOR: any task whose decisions affect future work — features, refactors, architecture changes, integrations. Produces a lightweight Task Analysis Map that externalizes intent, decisions, and chai...

ClaudeCodexOpenClawOperations
AllanSantos-DV0
Agent skill

Contextação — Structured Context Analysis

**WORKFLOW SKILL** — Structured context analysis before acting. USE FOR: questioning assumptions, mapping dependencies, identifying blind spots, validating scope of any task or subject. Use to contextualize, question, analyze before implementing, review premises, prevent hallucination, structured...

OpenClawData & Analytics
AllanSantos-DV0
Agent skill

Hooks Creator — Complete Guide to Agent Lifecycle Hooks

**WORKFLOW SKILL — MANDATORY for ANY hook work.** Create, configure, edit, debug, or review lifecycle hooks for VS Code Copilot (default) and Claude Code. USE FOR: criar/configurar/editar hook, hook do Copilot/Claude/agente, lifecycle hook, PreToolUse, PostToolUse, SessionStart, SubagentStop, Sto...

ClaudeDevelopment & Engineering
AllanSantos-DV0
Agent skill

Agent Creator — Complete Guide to Building Custom Agents

**WORKFLOW SKILL** — Create custom VS Code Copilot agents (.agent.md). USE FOR: new agents, tool restrictions, handoffs, orchestration patterns, discipline constraints. DO NOT USE FOR: general coding, VS Code extension development.

ClaudeCodexOpenClawDevelopment & Engineering
AllanSantos-DV0
Agent skill

Task Intent — Understand Before Implementing

**WORKFLOW SKILL** — Understand before implementing. USE FOR: any task where the agent might rush to code — forces understanding WHY/WHAT FOR/FOR WHOM before defining a solution, activates planning and reasoning discipline, prevents technical debt from shallow requests. Use to validate intent, pl...

OpenClawDesign
AllanSantos-DV0
Agent skill

Skill Manager for Copilot — User Guide

**GUIDE SKILL** — Guide to the Skill Manager for Copilot extension. USE FOR: adding/removing skill repos, syncing skills, pushing feedback, configuring sync intervals, troubleshooting sync issues, understanding skill format. DO NOT USE FOR: creating new skills (use skill-creator), creating agents...

ClaudeCodexOpenClawDevelopment & Engineering
AllanSantos-DV0
Agent skill

Document to Markdown — Agent Guide

**CONVERSION SKILL** — Convert binary/Office documents to Markdown for LLM consumption. USE FOR: converting Word, Excel, PowerPoint, PDF, Visio, MS Project files to Markdown, batch document conversion, extracting text from non-readable formats. DO NOT USE FOR: Markdown formatting/linting, general...

OpenClawContent & Media
AllanSantos-DV0
Agent skill

Markdown to Document — Agent Guide

**WORKFLOW SKILL** — Generate formatted documents from Markdown or structured content. USE FOR: creating PowerPoint presentations, Word documents, Excel spreadsheets, MS Project files, PDFs from Markdown/JSON/chat context using templates. DO NOT USE FOR: converting documents TO Markdown (use doc-...

OpenClawContent & Media
AllanSantos-DV0
Agent skill

Safety Check — Risk Awareness with Variable Weight

**WORKFLOW SKILL** — Risk awareness before action. USE FOR: assessing risks (security, data integrity, compatibility, operational, reversibility) of any task at variable depth. Accepts weight: Light (quick scan), Standard (dimensional analysis), Deep (full Risk Radar with evidence). Can be invoke...

OpenClawData & Analytics
AllanSantos-DV0
Agent skill

Skill Benchmark — Measure Skill Effectiveness

**MEASUREMENT SKILL** — Benchmark framework for measuring skill effectiveness. A/B tests agent outputs with and without a target skill, scoring correctness, completeness, and pattern adherence. USE FOR: validating skill quality, comparing before/after skill changes, proving skill ROI with data. D...

OpenClawData & Analytics
AllanSantos-DV0

Platform labels describe intended use. Read each resource's author credits, requirements and available access methods.