Agent skill
tool-construction
Dynamically building simple MCP servers or Python scripts to solve unique problems.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/coding-andreibesleaga-gabbe-9
SKILL.md
tool-construction Skill
This skill guides the creation of NEW capabilities for the swarm.
1. Script vs MCP
- Script: One-off task (e.g., "Migrate CSV to JSON").
- MCP Server: Persistent tool needed by LLM (e.g., "Query internal Knowledge Base").
2. Building an MCP Server (Quick-Start)
Use the @modelcontextprotocol/sdk:
- Define Tools (Input Schema).
- Implement Logic.
- Connect to Stdio/SSE.
3. Tool Safety
- Sandboxing: Generated tools should not have root access.
- Review: A generated tool must be reviewed by
ops-security(or human) before execution if it modifies files.
4. The "Toolsmith" Loop
- Identify Pain: "We keep grepping for X manually."
- Spec Tool: "Build a tool that finds X and formats as JSON."
- Implement: Write
tools/find_x.py. - Register: Add to
project_toolsin context configuration.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?