Capture thumbs up/down feedback into structured memories and prevention rules. Use when user gives explicit quality signals about agent work (e.g. "that worked", "that failed", "thumbs up/down"). Do NOT use for general questions, code generation, file operations, or any task that is not explicit feedback on prior agent output.
Installs into .claude/skills of the current project.
Are you the author of Claude Skill?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/igorganapolsky-claude-skill)
---
name: thumbgate-feedback
description: >
Capture thumbs up/down feedback into structured memories and prevention rules.
Use when user gives explicit quality signals about agent work (e.g. "that worked",
"that failed", "thumbs up/down"). Do NOT use for general questions, code generation,
file operations, or any task that is not explicit feedback on prior agent output.
triggers:
- thumbs up
- thumbs down
- that worked
- that failed
negative_triggers:
- generate code
- search files
- explain this
- run tests
---
# ThumbGate Feedback Skill
When user provides feedback, execute:
```bash
# negative
npx thumbgate capture \
--feedback=down \
--context="<what failed>" \
--what-went-wrong="<specific failure>" \
--what-to-change="<prevention action>" \
--tags="<domain>,regression"
# positive
npx thumbgate capture \
--feedback=up \
--context="<what succeeded>" \
--what-worked="<repeatable pattern>" \
--tags="<domain>,fix"
```
At session start, run:
```bash
npx thumbgate stats
npx thumbgate lessons
```
