agent-skillsAgent Skills standard reference guide. Covers SKILL.md specification format, progressive disclosure mechanism, skill discovery and activation, frontmatter me...
Install via ClawdBot CLI:
clawdbot install openlark/agent-skillsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Jul 26, 2026
A legal firm uses the Agent Skills skill to define a pdf-processing skill that extracts text, fills forms, and merges PDFs. This automates routine document handling, reducing manual effort and errors.
An enterprise develops an internal skill for code review checks, and deploys it across multiple AI agents (Claude Code, GitHub Copilot, Cursor) using the standardized directory structure. This ensures consistent behavior and reduces duplication.
An e-commerce company creates a skill for handling returns. The skill's catalog entry is always loaded, but the full instructions and scripts are only loaded when the agent needs to process a return, saving tokens and inference costs.
A QA team uses the skills-ref validate command to validate all skills in a repository, ensuring they conform to the SKILL.md specification. This catches errors early and ensures skills work across supported agents.
A development team bundles a bash script for building and deploying a service as part of an agent skill. The script is referenced in SKILL.md and executed by the agent when needed, streamlining the CI/CD pipeline.
A platform hosts a marketplace where developers publish premium skills. Users subscribe to access skills, and revenue is shared between the platform and skill creators.
A company creates proprietary skills tailored for specific industries (e.g., healthcare compliance) and licenses them to enterprises. The license includes updates and support.
Consulting firms offer services to design, build, and validate custom skills for clients. This includes integration into existing agent workflows and ongoing maintenance.
💬 Integration Tip
Start by creating minimal skills with just a name and description to test discovery, then progressively add instructions and resources while validating with skills-ref validate.
Scored Jul 26, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.