feedback-application — Claude Code skill: what it does, install
The feedback-application skill turns review comments into tracked code changes, tests, and documentation updates. Use it when an agent needs to work through feedback item by item.
LicenseRef-Proprietary 126 installs ★ 50 updated 2026-01-05
npx skills add qodex-ai/ai-agent-skills --skill feedback-application -a claude-codeWhat feedback-application does
feedback-application parses reviewer notes into separate work items, including numbered lists, bullets, and distinct requests. It uses TodoWrite to track progress, keeps one task active at a time, and closes each item after the related change is checked.
For implementation, the skill directs the agent to locate code with Grep and Glob, inspect the current files, and edit them with Edit. It also covers new files, documentation, tests, and refactoring, followed by affected test runs and uv run ruff check. Ambiguous or conflicting feedback must be clarified before implementation. TodoWrite is required for the workflow, so omitting it breaks the skill’s intended process.
What it helps with
- turn review notes into actionable tasks
- apply requested changes across a codebase
- add tests for review-driven changes
- check edited code for regressions
- update documentation after a review
Example prompts for the agent
- Work through these review comments, track each item, and apply the requested changes.
- Fix the feedback in
chain.py, add a test for the edge case, and run the affected checks. - Separate any unclear or conflicting reviewer requests before changing the code.
How to install feedback-application
1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill feedback-application -a claude-code2Manually: put the files in place
~/.claude/skills/feedback-application/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/feedback-application/
1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill feedback-application -a codex2Manually: put the files in place
.agents/skills/feedback-application/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill feedback-application -a cursor2Manually: put the files in place
.cursor/skills/feedback-application/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install qodex-ai/ai-agent-skills skills/feedback-application2Manually: put the files in place
.github/skills/feedback-application/SKILL.md1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill feedback-application -a gemini-cli2Platform CLI
gemini skills install https://github.com/qodex-ai/ai-agent-skills --path skills/feedback-applicationManually: put the files in place
.devin/skills/feedback-application/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill feedback-application -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about feedback-application
How do I install feedback-application in Claude Code?
Run npx skills add qodex-ai/ai-agent-skills --skill feedback-application -a claude-code, then check ~/.claude/skills/feedback-application/SKILL.md.
What does feedback-application do?
It turns review notes into tracked tasks and guides the agent through code, test, and documentation changes. Each item is checked and marked complete before the next one starts.
How does feedback-application handle unclear review comments?
The agent asks for clarification before implementation. If requests conflict, it explains the conflict and waits for guidance.