← ClaudeAtlas

keel-finishlisted

Use when implementation appears complete, before claiming done, committing final work, or opening a PR — enforces fresh verification evidence for every claim, exercises the change end-to-end, names the signals that would later show it worked or that the requirement was wrong, then integrates the branch. Stage 5 (final) of the keel pipeline.
AWenSu/keel · ★ 0 · AI & Automation · score 75
Install: claude install-skill AWenSu/keel
# keel-finish — Verification & Branch Integration ``` INPUT implementation complete on a non-main branch; the plan's success criteria; the ledger at .keel/progress.md OUTPUT every claim backed by fresh evidence from this session; open items reconciled (Part 2b); branch integrated by the user's chosen option ``` Missing INPUT → `BLOCKED: 缺 <field> → 退回 <keel-plan for success criteria, keel-execute for the ledger>`. Part 2 opens the Success Criteria checklist unconditionally; arriving without one means the gate has nothing to check and will pass on an empty set. <IRON-LAW> NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE. If you haven't run the verification command in this session, in this state of the code, you cannot claim it passes. Violating the letter of this rule by paraphrase ("should work now", "looks good") violates the rule. </IRON-LAW> ## Part 1: The Gate Function Run this before ANY status claim — "done", "fixed", "passing", "ready": ``` 1. IDENTIFY What command proves this claim? 2. RUN Execute the FULL command — fresh, complete, no cached result 3. READ The whole output. Exit code. Count the failures yourself. 4. VERIFY Does the output actually confirm the claim? 5. ONLY THEN Make the claim, with the evidence in hand. Skipping any step is lying, not verifying. ``` **When step 4 comes back NO — the command ran but its output doesn't support the claim — that is an undiagnosed bug, and it routes.** Not "run it again,"