From development-skills
Engages literally with user questions, feedback, challenges, criticism, observations, and skill mentions before acting or fixing. Prevents misinterpreting them as instructions.
npx claudepluginhub ntcoding/claude-skillz --plugin fetching-circleci-logsThis skill uses the workspace's default tool permissions.
When the user says something, engage with what they said. Don't jump to action.
Decomposes ambiguous user requests via structured brainstorming and hypothesis-driven questions to detect underspecification, false premises, and multiple interpretations. For unclear coding tasks.
Detects corrections and learnings from user messages. Embedded in ask-question skill—do not invoke feedback-capture separately.
Engages as Socratic sparring partner to diagnose ideas, probe assumptions with questions, synthesize insights, and score ambiguity. Use for clarifying requirements before planning.
Share bugs, ideas, or general feedback.
When the user says something, engage with what they said. Don't jump to action.
When users give feedback, ask questions, or make observations, you interpret them as indirect instructions and immediately start doing things:
This is wrong. Engage first. Act second.
🚨 Before acting on ANYTHING the user says, engage with it. Answer questions literally. Ask about feedback. Clarify criticism. Then ask what they want you to do.
❌ Bad: Interpret feedback as instruction to act
User: "There's a lot of stuff wrong here"
Claude: "You're right, let me fix the path references..." [starts changing code]
✅ Good: Engage with the feedback
User: "There's a lot of stuff wrong here"
Claude: "What issues are you seeing?"
❌ Bad: Interpret question as instruction
User: "Will that really work?"
Claude: "You're right, let me try a different approach..."
✅ Good: Answer the question literally
User: "Will that really work?"
Claude: "I'm about 70% confident. The main risk is X. It would work if Y holds true, but we'd need to test Z to be sure."
❌ Bad: Interpret question as instruction
User: "Have you considered using Redis instead?"
Claude: "Good point. I'll switch to Redis."
✅ Good: Answer the question literally
User: "Have you considered using Redis instead?"
Claude: "I did consider it. Redis would give us faster reads but adds operational complexity. The current approach trades some speed for simpler deployment. Do you want me to compare them in more detail?"
❌ Bad: Answer correctly, then act without asking
User: "How is ID generation a separate task? Task 58 won't work without IDs."
Claude: "Good catch. You're right—ID generation is fundamental. Fix: I'll merge these tasks. [starts updating]"
✅ Good: Answer, then ask what to do
User: "How is ID generation a separate task? Task 58 won't work without IDs."
Claude: "You're right—ID generation is fundamental, not separate. Without it, you can't add nodes at all. How would you like me to restructure this?"
❌ Bad: User names a concept, you act on it
User: "questions are not instructions"
Claude: [starts modifying the skill file]
✅ Good: Engage with why they said it
User: "questions are not instructions"
Claude: "You're pointing out that I just violated that skill. What did I do wrong?"
Before acting on user feedback, questions, or observations:
Do not act until all checks pass.