Agent Context Isolation
The English summary is being prepared. Showing the original description.
Meta-skill for creating and managing Claude Code skills
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Meta-skill for creating new Claude Code skills, including skills that wrap MCP pipelines.
Skills live in .claude/skills/<skill-name>/:
.claude/skills/my-skill/
├── SKILL.md # Required: Main skill definition
├── scripts/ # Optional: Supporting scripts
└── templates/ # Optional: Templates, examples
---
name: skill-name
description: Brief description (shown in skill list)
allowed-tools: [Bash, Read, Write] # Optional: restrict tools
---
# Skill Name
## When to Use
[When Claude should discover this skill]
## Instructions
[Step-by-step instructions for Claude to follow]
## Examples
[Usage examples]
To create a new MCP chain script and wrap it as a skill:
Copy the multi-tool-pipeline template:
cp $CLAUDE_PROJECT_DIR/scripts/multi_tool_pipeline.py $CLAUDE_PROJECT_DIR/scripts/my_pipeline.py
Reference the template pattern:
cat $CLAUDE_PROJECT_DIR/.claude/skills/multi-tool-pipeline/SKILL.md
cat $CLAUDE_PROJECT_DIR/scripts/multi_tool_pipeline.py
Edit your new script to chain the MCP tools you need:
async def main():
from runtime.mcp_client import call_mcp_tool
args = parse_args()
# Chain your MCP tools (serverName__toolName)
result1 = await call_mcp_tool("server1__tool1", {"param": args.arg1})
result2 = await call_mcp_tool("server2__tool2", {"input": result1})
print(result2)
Create .claude/skills/my-pipeline/SKILL.md:
---
name: my-pipeline
description: What the pipeline does
allowed-tools: [Bash, Read]
---
# My Pipeline Skill
## When to Use
- [Trigger conditions]
## Instructions
Run the pipeline:
\`\`\`bash
uv run python -m runtime.harness scripts/my_pipeline.py --arg1 "value"
\`\`\`
### Parameters
- `--arg1`: Description
## MCP Servers Required
- server1: For tool1
- server2: For tool2
Add to .claude/skills/skill-rules.json:
{
"skills": {
"my-pipeline": {
"type": "domain",
"enforcement": "suggest",
"priority": "medium",
"description": "What it does",
"promptTriggers": {
"keywords": ["keyword1", "keyword2"],
"intentPatterns": ["(pattern).*?(match)"]
}
}
}
}
For full details, read:
cat $CLAUDE_PROJECT_DIR/.claude/rules/skill-development.md
cat $CLAUDE_PROJECT_DIR/.claude/rules/mcp-scripts.md
Look at existing skills for patterns:
ls $CLAUDE_PROJECT_DIR/.claude/skills/
cat $CLAUDE_PROJECT_DIR/.claude/skills/commit/SKILL.md
cat $CLAUDE_PROJECT_DIR/.claude/skills/firecrawl-scrape/SKILL.md
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Agent Context Isolation
The English summary is being prepared. Showing the original description.
Agent Orchestration Rules
The English summary is being prepared. Showing the original description.
Agentic Workflow Pattern
The English summary is being prepared. Showing the original description.
Guide for integrating Agentica SDK with Claude Code CLI proxy
The English summary is being prepared. Showing the original description.
Reference guide for Agentica multi-agent infrastructure APIs
The English summary is being prepared. Showing the original description.
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
The English summary is being prepared. Showing the original description.