← ClaudeAtlas

close-epiclisted

Terminal epic-close checklist over a wave-structured decomposition (one epic = one <backlog>/<task-name>/ directory from /prepare Phase 6): verify every plan is terminal, execute the epic's declared E2E-verify block plus ONE integration test pass, run plan↔code conformance on deviated plans, detect docs drift the epic caused and fix small documentation debt inline, price every remaining finding (default: a named known-undone clause, NOT a card), promote only the survivors into a runnable follow-up board, draft the ledger/changelog row, and EMIT a copy-paste archive command. Takes ONE epic or a BATCH of them in a single invocation. Never flips statuses, never runs git. TRIGGER when: a multi-session epic looks finished and should be settled and archived — "close the epic", "settle and archive this", "finalize the epic", or right after its last wave merges. TRIGGER ALSO on the same request phrased as plain work, with this skill unnamed — "run the verification steps from the overview", "can this be archived" — a
mik2win/foureyes · ★ 2 · AI & Automation · score 76
Install: claude install-skill mik2win/foureyes
# Close Epic: $ARGUMENTS The **terminal** counterpart of `/epic-status` (which reports progress) and `/handoff` (which snapshots an *unfinished* session). This closes the loop **plan → code → ledger** so settled work is never re-researched, and nothing is archived half-verified. It reports, verifies, drafts, and **emits** — it does not flip statuses and it never runs git. This skill carries only invariant close-out logic. The backlog/archive locations, the integration test command, the drive commands for each surface, and the ledger location all come from `.claude/PROJECT.md`. `Bash` is for the verification runs and read-only inspection (`git log`, `git status`, `ls`) — never mutation. `$ARGUMENTS` is one epic or several (Phase 0). The card tier — worth-it gate (default: **not** a card), the stock gate, card template, route rubric, session packing — lives in **`reference/followups.md`**, read at Phase 5. **Verification adapts to what the epic was about.** A test suite plus a docs grep proves almost nothing about a chart that renders an interpolated line across a data gap, or a route that 200s on malformed input. Phase 2 executes the checks the epic declared for its own surfaces — and derives them from the diff when it declared none. ## Phase 0 — Load profile & resolve the epic **Tooling preflight — one call, before step 1.** Some tools this skill relies on are **deferred** by the harness: the session lists them by name only and loads their schemas on demand, so calling