← ClaudeAtlas

address-reviewlisted

Triage external code-review feedback on a merge request and resolve it end-to-end, automatically: decide which comments are valid against the actual diff (line by line), explain why each valid one was missed during coding, defend the correct decisions reviewers got wrong, then implement the fixes, push, and reply to every comment thread — all in one pass, without stopping to ask. Built for the loop where an AI coding agent writes the code, you raise an MR, and reviewer agents comment with less project context than the author has. Invoking the skill is the go-ahead for the whole loop (triage → implement → push → reply); the only hard stop is a red build. Valid comments get marked done on the MR, invalid ones explained. Use when: addressing MR/PR review comments, "address the review", "incorporate review feedback", triaging reviewer-bot comments, deciding which review comments are worth acting on.
ohyesgocool/feature-loop · ★ 0 · Code & Development · score 73
Install: claude install-skill ohyesgocool/feature-loop
# Address Review Take review comments from the agents that reviewed an MR (or any reviewer), check each one against the **actual code you changed**, and decide honestly what holds. The reviewers have less context than you do — your job is to use your fuller context to separate real findings from context-gaps, **without** hiding behind "they didn't have context" to wave away valid bugs. This skill runs the **whole loop end-to-end, without stopping to ask** — invoking it is the go-ahead for all four stages: 1. **Triage report** — every comment addressed in a fixed format: verdict, why, and for valid ones, **why you missed it while coding** (this is the point of the skill — be specific and honest). 2. **Fix plan** — what to change, in priority order, each item tracing back to a comment. 3. **Implement** — code every VALID + PARTIAL comment, per the house rules, running type-check + tests. 4. **Push + reply** — push the commits, then post each verdict back to its MR thread (fixed ones marked done, invalid ones explained) and resolve the fixed/dismissed threads. Print the triage report and fix plan as you go so the user can see the reasoning (and interrupt if they disagree) — but **do not pause for permission**; flow straight through to push + reply. The one hard stop is a **safety abort**: if type-check or tests stay red, do not push — report and wait. If the user provided arguments: `$ARGUMENTS` — see Step 1 for how to interpret them. With no arguments, auto-detect the curre