AGENT SKILL

review-plan

WAY 20 — independent review of a test plan before it's approved. Use when the user says "review plan", "review the plan", "review test plan", "plan review", "improve the plan" with a plan ref or path. Scores the plan out of 100 with evidence, proposes test cases to add, remove, merge or modify (each with its reason and technique), applies the ones the user picks without breaking AC coverage, and sends the plan back for approval. `plan it` runs it automatically.

License 许可
MIT
最近更新
2026-11-06
Stars
★ 5
Forks
4

01 前言 Front Matter

name
review-plan
description
WAY 20 — independent review of a test plan before it's approved. Use when the user says "review plan", "review the plan", "review test plan", "plan review", "improve the plan" with a plan ref or path. Scores the plan out of 100 with evidence, proposes test cases to add, remove, merge or modify (each with its reason and technique), applies the ones the user picks without breaking AC coverage, and sends the plan back for approval. `plan it` runs it automatically.

03 SKILL.md 正文

WAY 20 — Review a Test Plan

plan it (WAY 19) designs the plan; this WAY checks it with a second pair of eyes before a human approves it. The reviewer, test-plan-reviewer, is a different agent from the one that wrote the plan, and it only proposes. Nothing changes until the user picks.

Step 1: Gather inputs

Required (ask if missing): Plan: (a test-plan issue ref or a plan path). "The plan" or "the last plan" means the newest file in qa-artifacts/test-plans/: name it back to the user. Optional: budget: <minutes> for the P0+P1 tests that run on every MR/PR (default QA_PLAN_BUDGET_MIN from .env, else 10) · history: off (skip bug and flaky history).

Phase 1: Read

  1. Read the plan per the test-plan skill's Reading a plan (an issue body is authoritative; a body without ## Planned tests isn't a plan: stop and say so)
  2. The requirements: when **Source:** is an issue ref, issue.get it (ACs, Gherkin, Missing Information). Otherwise the plan's own ## Requirements table is the source

Phase 2: Context

  1. node ${CLAUDE_PLUGIN_ROOT}/scripts/plan-check.mjs <plan> --estimate --budget <minutes>. Keep the whole output: errors, warnings and the ⏱ lines
  2. Unless history: off:
    • Bugs: issue.list with label bug, state closed, text = the plan's test folder name, then again with the source ref. Keep those closed in the last 90 days: ref, title, area, root cause if the body states one
    • Flaky: if qa-artifacts/runs/ has ≥ 3 runs, node "${CLAUDE_PLUGIN_ROOT}/.claude/skills/flaky-triage/flaky.mjs" runs 10 . from qa-artifacts/, and keep the scenarios of the plan's test folder with verdict flaky
    • Neither source available: say "no history" in the review, and carry on

Phase 3: Review

Run test-plan-reviewer with the plan, the requirements, the plan-check.mjs output, the history and the plan's ## Review log. It returns a scorecard, proposals (A1 add, R1 remove, G1 merge, M1 modify) and a summary line.

Phase 4: Show and ask

Show the scorecard and the proposals table. If the score is below 70, add one line: "Score <n>/100: read the proposals before approving." It's a warning, never a block. Then ask:

"Apply all, apply by ID (e.g. A1,R2), or none?"

With plan: auto (unattended, from WAY 1/4), don't ask and apply nothing: the proposals go in the review comment for a human to pick later.

Phase 5: Apply

  1. Save a copy of the plan as it is now (qa-artifacts/test-plans/.<plan-name>.before.md)

  2. Apply the picked proposals per the test-plan skill's Changing a plan:

    • ADD: a new Planned tests row with the proposal's ID, fields and priority tag
    • REMOVE: the row moves to ## Retired with the reason
    • MERGE: the lowest ID becomes the Outline row (… (Outline: N rows)), the others move to Retired ("merged into Test#<nn>")
    • MODIFY: change the named field; the tags follow the level and priority
    • Update ## Coverage for every requirement touched
  3. Check the floor: node ${CLAUDE_PLUGIN_ROOT}/scripts/plan-check.mjs <plan> --against <the copy>. For each coverage floor or disappeared error, undo the proposal that caused it, tell the user why ("R2 not applied: AC-02 would have no negative test"), and run the check again until it passes

  4. Append one line to ## Review log (create the section above ## Retired if missing):

    ## Review log
    | Date | Score | Applied | Rejected |
    |---|---|---|---|
    | 2026-11-05 | 74/100 | A1, A2, R1 | M1 (user: the UI message differs from the API's) |
    

    "Rejected" lists what the user didn't pick, with their reason when they gave one. The reviewer reads it next time and doesn't propose those again (convergence)

  5. If anything was applied: **Status:** awaiting-approval, issue.update(ref, body, labels+ [plan-awaiting-approval], labels- [plan-approved, plan-auto-approved]) (a full replace, watermark included). The plan goes back for approval: never mark it approved here

  6. If the user picked none: only the Review log line changes. Status and rows stay as they were (an approved plan stays approved)

  7. issue.comment(plan ref, <scorecard + proposals, then "Applied: … · Rejected: …">). A local-only plan has no issue: save the review as qa-artifacts/test-plans/<plan-name>.review-<YYYY-MM-DD>.md instead

  8. If the plan's test folder already has files, list what write it Plan: <ref> will add, and the retired IDs whose files plan-check.mjs will flag. Never delete test files here

Report

The score, what was applied and refused, the floor result, the run-time line, and the next step: approve the plan (plan it Plan: <ref> approve, or the plan-approved label), then write it Plan: <ref> or e2e it Plan: <ref>.

04 同仓库更多 Skills

GhassenAZZOUZ
GhassenAZZOUZ/claude-qa-agent

write-tests

WAY 4 — write test cases only, no execution. Use when the user says "write it", "write tests", "generate test cases" — an approved test plan (`Plan:`), or requirements (text or a tracker issue) planned and approved first, optional App/Spec/MR or PR → exactly the planned test files.

★ 5
GhassenAZZOUZ
GhassenAZZOUZ/claude-qa-agent

verify-fix

WAY 9 — verify that a bug is fixed by running its regression test. Use when the user says "verify it", "verify fix", "is #142 fixed", "check the fix" with one or more bug refs (#142, SHOP-142), or "verify all" for every open bug that has a regression test.

★ 5
GhassenAZZOUZ
GhassenAZZOUZ/claude-qa-agent

user-story-format

Reference only — the single definition of this project's user-story body (story, Gherkin ACs, Missing Information, DoD) and its AC/scenario rules. Read by user-story-enhancer (WAY 6) and benchmark-gap-story-writer (WAY 8) so stories they write stay identical in shape and WAY 6 can re-score WAY 8's output. Not a workflow on its own.

★ 5
GhassenAZZOUZ
GhassenAZZOUZ/claude-qa-agent

tracker

Provider-neutral contract for every issue-tracker and code-host action (create/update/comment/close issues, attach files, comment on MRs/PRs, read CI runs and logs) plus label conventions and failure handling. Every WAY calls these operations; the matching provider-* skill says how to perform them on GitLab, GitHub, Jira, Azure DevOps, or Bitbucket.

★ 5
GhassenAZZOUZ
GhassenAZZOUZ/claude-qa-agent

traceability

WAY 14 — requirements traceability matrix for a user story (each acceptance criterion) or a test folder written from plain text (each R-NN requirement) → the tests covering it → their latest result → open bugs. Use when the user says "trace it", "traceability", "is #148 covered", "coverage of SHOP-148", "trace it <folder>".

★ 5
GhassenAZZOUZ
GhassenAZZOUZ/claude-qa-agent

test-plan

WAY 19 — design a test plan before any test code. Use when the user says "plan it", "plan tests", "test plan", "design tests" with requirements (text or a tracker issue), optional App/Spec/MR or PR. Output is the test plan (scope, levels, one row per Test#<nn> with category, tags, covers, priority, coverage, entry/exit criteria, risks), reviewed by `review-plan` (WAY 20), filed for approval; `write it Plan:` / `e2e it Plan:` then write exactly that plan. Also holds the plan format every other WAY reads.

★ 5