← ClaudeAtlas

reportlisted

Write the final summary of an autoresearch run to `./.ar/final_report.md` — trajectory, best commit and its diff, what worked, what failed, and what to try next. Use for `/ar:report`, "write up the autoresearch results", or "summarise the experiment loop". Reads `./.ar/ar.jsonl` from disk, so it works in a fresh session. Writes only the report; never iterates, commits, or reverts, and leaves the loop able to continue.
emaballarin/ccplugins · ★ 3 · Data & Documents · score 77
Install: claude install-skill emaballarin/ccplugins
# /ar:report — write the run up Turn the record into something a person can read. Do not iterate. ## Steps 1. Read state (`cat ./.ar/ar.jsonl | tail -50`, plus `worklog.md` and `results.tsv` if present). No `ar.jsonl` means nothing to report — say so and stop. 2. Reconstruct the run per `${CLAUDE_PLUGIN_ROOT}/references/resume-loop.md` §1, across **all** segments, not just the last: a segment boundary marks a harness or baseline change, so metrics either side of it are not comparable and the report must say where the boundaries fell rather than plotting through them. 3. Pull the winner chain from git — it is an independent record of the same run: ```bash git log --format='%h %s' --grep='"status":"keep"' <config.branch> git diff <config.snapshotCommit>..<bestCommit> --stat ``` 4. Write `./.ar/final_report.md`: - **Goal and setup** — objective, metric, direction, harness, budget. - **Result** — baseline → best, absolute and relative, with the confidence tier. State plainly whether the total gain clears the noise floor; a run that ended inside its own scatter did not find anything, and the report says so rather than dressing it up. - **Trajectory** — the keep chain, each with commit, metric, delta and the one-line description of the change. - **What worked** — the winning changes and, where the record supports it, why they worked. Distinguish an explanation from a guess. - **What failed** — dis