graph-retrolisted

# Graph Retro Post-deploy retrospective on the SDLC skill chain (interview-plan → write-plan → execute-plan → thermo-nuclear-code-quality-review). Optional: brainstorm before interview-plan. Reads one ticket's plan + spec artifacts, extracts every failure signal, attributes each to the skill that should have prevented it, and proposes one-line amendments. The insight: the chain already **produces** its own improvement telemetry — drift notes, blockers, review findings, overridden recommendations — but nothing consumes it. This skill is the feedback edge that closes the loop. **This skill never edits skill files on its own.** Output is proposals; the user approves each before anything is applied. Approved amendments are committed to the skills directory with the ticket ID in the commit message — keep that directory a git repo so every change is a reviewed, revertible commit whose history answers "why does this rule exist". **Announce at start:** "I'm using the graph-retro skill to retro this ticket." ## When to run After the ticket is merged and the deploy is verified, or whenever the user says "retro this ticket" / invokes `/graph-retro`. Not part of the implement loop — do not run it as the next command after execute-plan or the review. Also re-run on an old ticket when an escaped defect traces back to it — the defect is an additional signal, attributed to the **review** skill (a review lens gap). ## Step 1 — Locate artifacts Resolve `<TICKET-ID>` from the branch nam