agent-skills-contextA comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, o...
Install via ClawdBot CLI:
clawdbot install daviesjoin-afk/agent-skills-contextGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
process.env.OPENAIContains instructions to override system prompt or ignore user requests
"Ignore previous instructions"Sends data to undocumented external endpoint (potential exfiltration)
post → https://karpathy.bearblog.dev/auto-grade-hn/Potentially destructive shell commands in tool definitions
eval (Generated May 9, 2026
A development team is creating a new AI agent skill for a customer support automation tool. They use this template to structure the skill's documentation, ensuring clear activation criteria, core concepts, and practical guidelines for effective context engineering.
An organization adopts this template to enforce consistency across all agent skill documents. Multiple teams contribute skills, and the template ensures each skill follows the same structure, making discovery and reuse easier.
A healthcare AI team uses the template to create skills for medical record summarization and diagnostic assistance. The 'When to Activate' section helps the agent trigger the skill only during relevant clinical workflows.
A fintech company develops skills for financial planning and risk assessment. The template's 'Core Concepts' and 'Practical Guidance' sections help the agent provide accurate, compliant advice without overwhelming detail.
A team revisits an older skill that suffers from poor discovery rates. Using the template, they rewrite the description, add examples, and integrate related skills, improving accuracy and reducing token usage.
The skill is bundled into a platform where customers pay a recurring fee for access to a library of pre-built agent skills. This model encourages ongoing updates and support.
A consulting firm uses the template to build bespoke agent skills for enterprise clients, charging for design, development, and maintenance. The template reduces turnaround time and ensures quality.
The template is offered as a free open-source tool, but premium skills and integrations are sold separately. This drives community adoption while generating revenue from advanced features.
💬 Integration Tip
Integrate this template as a starting point in your skill development workflow; customize each section to your domain while keeping the total SKILL.md under 500 lines for optimal token usage.
Scored May 9, 2026
Calls external URL not in known-safe list
https://github.com/user-attachments/assets/f79aaf03-fd2d-4c71-a630-7027adeb9bfeUses known external API (expected, informational)
api.github.comAI Analysis
The provided content is a template for creating skills, not an actual skill implementation. It contains no executable code, tool definitions, or active instructions that could access credentials, poison prompts, or exfiltrate data. The rule-based signals appear to be from a different, actual skill file, not from this template text.
Audited Apr 16, 2026 · audit v1.0
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
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.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...