Menu
Show evaluation results and comparisons
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Compare two eval runs and report what changed. Reads both runs' events, transcripts, and produced artifacts. Writes a short markdown summary classifying differences as regression, improvement, or neutral.
Generalized recursive iteration loop. Runs parallel sub-agents against a target, scores deterministically, diagnoses instruction gaps, applies fixes, and recurses until the stop condition is met or max depth is reached.
Run an evaluation against an eval with a specific config
Write a handoff document so a new chat can continue the work
Test-driven development of a Hono/Bun WebSocket application. Read requirements, read tests, build server, verify, iterate until all tests pass.
Scaffold a new evaluation
| name | report |
| description | Show evaluation results and comparisons |
| argument-hint | ["run_id | --latest | --all | --summarize <eval>"] |
/report or /report --latest — Dashboard summary of the most recent run/report <run_id> — Dashboard summary of a specific run/report --all — Full comparison report across all runs/report --summarize <eval_name> — Generate eval summary (terminal + RESULTS.md)Parse the arguments and dispatch:
If args contain --summarize, extract the eval name and run:
python3 "$CLAUDE_PROJECT_DIR/scripts/summarize.py" <eval_name> --filter-eval
If args contain --all, run:
python3 "$CLAUDE_PROJECT_DIR/scripts/report.py" --all
If --group-by is also present, pass it through.
If args contain a run_id (8+ hex chars), run:
python3 "$CLAUDE_PROJECT_DIR/scripts/dashboard.py" <run_id> --summary
Otherwise (no args or --latest):
python3 "$CLAUDE_PROJECT_DIR/scripts/dashboard.py" --latest --summary