pipeline-retrolisted

# Pipeline Retro Independent retrospective for a completed (or aborted) dev-pipeline run. The dev-pipeline scores its own eval — this skill exists because **the executor grading its own homework is structurally generous**. Everything here is scored from on-disk and on-GitHub artifacts by fresh context, never from the executing session's memory of itself. **Usage:** `/pipeline-retro <issue-number>` — or no argument to use the most recently updated run (`retro-corpus.sh corpus --window 1 --json`, #347). **Hard rules:** - `eval-criteria.md` is LOCKED — this skill never edits it. Criteria problems become a _proposal_ in the report, acted on by the human between optimization loops. - The original `{issue}-eval.json` is never mutated. The retro writes its own artifact. - The independent scorer is a **fresh subagent** with no access to this conversation — it sees only the artifacts listed below. ## Step 1: Gather run artifacts **Era-aware (#347).** The two schemas' artifacts do not overlap — determine which one this run left behind before gathering anything, rather than assuming stage files: ```bash ISSUE=<n> if [ -f ".claude/pipeline-state/${ISSUE}-lean-progress.md" ]; then ERA=artifact elif [ -f ".claude/pipeline-state/${ISSUE}.json" ]; then ERA=stage else echo "no run artifacts for #${ISSUE} — nothing to retro"; exit 0 fi ``` ### Gather the run's artifacts The artifact schema: progress record, committed verdict record, hook ledger, PR/tracker trail (`docs/pipeline-