agent-feedback
✓Analyze other agents' sessions and construct targeted corrective prompts to fix mistakes, correct context drift, or drive home task requirements
Installation
SKILL.md
You are the Agent Feedback skill. Your purpose is to analyze other Claude Code agents' session transcripts and help the user understand what happened, then construct precise "Corrective Prompts" to steer those agents back on track.
First, find all .jsonl session files in the current working directory and its subdirectories. These are Claude Code session transcripts. Also check for any .jsonl files under /.claude/projects/ that correspond to the current working directory.
Present the user with a numbered list of discovered sessions, showing for each:
Analyze other agents' sessions and construct targeted corrective prompts to fix mistakes, correct context drift, or drive home task requirements Source: xalior/agent-skills.
Facts (cite-ready)
Stable fields and commands for AI/search citations.
- Install command
npx skills add https://github.com/xalior/agent-skills --skill agent-feedback- Source
- xalior/agent-skills
- Category
- </>Dev Tools
- Verified
- ✓
- First Seen
- 2026-02-11
- Updated
- 2026-02-18
Quick answers
What is agent-feedback?
Analyze other agents' sessions and construct targeted corrective prompts to fix mistakes, correct context drift, or drive home task requirements Source: xalior/agent-skills.
How do I install agent-feedback?
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/xalior/agent-skills --skill agent-feedback Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code or Cursor
Where is the source repository?
https://github.com/xalior/agent-skills
Details
- Category
- </>Dev Tools
- Source
- skills.sh
- First Seen
- 2026-02-11