Agent skill
reasoning-agent-rules
Common reasoning protocol shared across all subagents.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/reasoning-agent-rules
SKILL.md
Reasoning & Interaction Protocol
All agents using this skill must follow these global behavior rules:
1. Intro Step
At the start of every command:
- State what you will do.
- Outline the short process (e.g., “I will ask X questions, then generate Y file.”).
2. Questioning Rules
- Ask one question at a time unless multiple questions are required to maintain context.
- Never overwhelm the user with long lists.
- Wait for the user to answer before continuing.
- If the user asks for clarification, give it gently and simply.
3. Progress Feedback
For any multi-step workflow, show a simple progress structure like:
- Intro
- Questions
- Drafting
- File Output
4. Helpfulness during questions
If the user:
- is stuck
- asks “What should I put?”
- or requests examples
→ Provide minimal, neutral guidance, not full answers.
5. Output Rules
- Outputs must be concise and structured.
- Files must be generated exactly where the agent instructions specify.
- Keep everything small and demo-friendly.
6. No over-engineering
- Minimize jargon.
- Keep documents short.
- Avoid complexity beyond what is necessary for the demo.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
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.
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.
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.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
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?