skill-doctor
warpdotdevSee which skills help and where your agent falls short.
agent evaluation
What it does
Grades an agent setup from local conversations, proposes evidence-based skill edits, and produces a shareable report.
When to use it
Use when the user wants their agent setup graded from conversation history or wants to know which installed skills work.
How to use it
Choose the conversation and skill scopes; it grades the sessions and saves report artifacts in a fresh scratch directory.
What you provide
- conversations to grade
- skills to evaluate
Uses
GB
ZC
Access · 8
This skill
$REPORT_DIR/transcripts/
Write
Copies transcripts to scratch storage
Warp conversation databases
Read
Reads local Warp conversations
Claude Code project-history JSONL
Read
Reads Claude Code history
Codex rollout JSONL
Read
Reads local Codex rollouts
Good to know
- starts one helper agent per item, so the count depends on the work
- advertises something the task does not need
What you need · 1
Python 3 runs the session collector and report renderer.
About this skill
- Visibility
- Public
- Repository
- warpdotdev/common-skills
- Created
- Oct 8, 2026
- Updated
- Oct 8, 2026
- Files
- 14