apply-prompt-feedback
Applies user feedback to prompts with precision - incorporates feedback intent without over-fitting, maintains information density, prevents regressions. Use when asked to apply feedback, incorporate suggestions, or update a prompt based on user input.
npx skills add majiayu000/claude-skill-registry --skill apply-prompt-feedback --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Apply Prompt Feedback Apply user feedback to prompts with calibrated precision—addressing feedback intent fully while avoiding over-fitting, maintaining information density, and preventing regressions. ## Overview This skill applies feedback through: 1. **Initial Application** - Apply feedback to prompt using Application Techniques 2. **Verification** - `prompt-feedback-verifier` checks for issues (over-fitting, regression, density loss) 3. **Refinement** - Fix issues based on verifier findings, iterate if needed (max 5 iterations) 4. **Output** - Atomic replacement only after verification passes **Loop**: Gather inputs → Copy → Apply feedback → Verify → (Iterate if issues) → Output **Key principles**: - **Just-right application**: Address ALL of feedback, ONLY feedback, nothing more - **Information density**: Use minimal text to achieve the change - **Regression prevention**: Preserve everything feedback didn't mention - **Verifier validates**: Verifier catches over-fitting, under-fitting, and regressions **Required tools**: This skill requires Task tool to launch the verifier agent. If Task is unavailable, report error: "Task tool required for verification loop." This skill use
- Overview
- Workflow
- Phase 0: Create Todo List (TodoWrite immediately)
- Phase 1: Input Validation
- Phase 2: Initial Application
- Phase 3: Refinement Loop (Verifier-Driven)
- Application Techniques
- Incorporation Techniques
- Calibration Techniques
- Preservation Techniques
- Information Density Rules
- Resolution Strategy
- Phase 4: Output
- Key Principles
Apply feedback to a prompt file Apply feedback to inline prompt (will be prompted for feedback) Apply multiple feedback points
What does the apply-prompt-feedback skill do?
Applies user feedback to prompts with precision - incorporates feedback intent without over-fitting, maintains information density, prevents regressions. Use when asked to apply feedback, incorporate suggestions, or update a prompt based on user input.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill apply-prompt-feedback --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.