[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EGMMN8A9773XWCREFNQKMY":3,"skill-same:01M7EGMMN8A9773XWCREFNQKMY":46},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EGMMN8A9773XWCREFNQKMY","review-plan",null,"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.","GhassenAZZOUZ\u002Fclaude-qa-agent","GhassenAZZOUZ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F75794579?v=4","01M7EGG6N5NXG9KJJ0KMA7JKBZ","Ghassen AZOUZ","01M7EGG6P7YNY9P555TAPR46XZ",5,"MIT","https:\u002F\u002Fgithub.com\u002FGhassenAZZOUZ\u002Fclaude-qa-agent\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Freview-plan\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: review-plan\ndescription: 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.\n---\n\n# WAY 20 — Review a Test Plan\n\n`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.**\n\n## Step 1: Gather inputs\n**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\u002Ftest-plans\u002F`: name it back to the user.\n**Optional:** `budget: \u003Cminutes>` for the P0+P1 tests that run on every MR\u002FPR (default `QA_PLAN_BUDGET_MIN` from `.env`, else 10) · `history: off` (skip bug and flaky history).\n\n## Phase 1: Read\n1. 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)\n2. 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\n\n## Phase 2: Context\n1. `node ${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fplan-check.mjs \u003Cplan> --estimate --budget \u003Cminutes>`. Keep the whole output: errors, warnings and the `⏱` lines\n2. Unless `history: off`:\n   - **Bugs**: `issue.list` with label `bug`, state closed, text = the plan's test folder name, then again with the source ref. Keep those closed in the last 90 days: ref, title, area, root cause if the body states one\n   - **Flaky**: if `qa-artifacts\u002Fruns\u002F` has ≥ 3 runs, `node \"${CLAUDE_PLUGIN_ROOT}\u002F.claude\u002Fskills\u002Fflaky-triage\u002Fflaky.mjs\" runs 10 .` from `qa-artifacts\u002F`, and keep the scenarios of the plan's test folder with verdict `flaky`\n   - Neither source available: say \"no history\" in the review, and carry on\n\n## Phase 3: Review\nRun `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.\n\n## Phase 4: Show and ask\nShow the scorecard and the proposals table. If the score is below 70, add one line: *\"Score \u003Cn>\u002F100: read the proposals before approving.\"* It's a warning, never a block. Then ask:\n\n*\"Apply all, apply by ID (e.g. A1,R2), or none?\"*\n\nWith `plan: auto` (unattended, from WAY 1\u002F4), don't ask and apply nothing: the proposals go in the review comment for a human to pick later.\n\n## Phase 5: Apply\n1. Save a copy of the plan as it is now (`qa-artifacts\u002Ftest-plans\u002F.\u003Cplan-name>.before.md`)\n2. Apply the picked proposals per the `test-plan` skill's **Changing a plan**:\n   - **ADD**: a new Planned tests row with the proposal's ID, fields and priority tag\n   - **REMOVE**: the row moves to `## Retired` with the reason\n   - **MERGE**: the lowest ID becomes the Outline row (`… (Outline: N rows)`), the others move to Retired (\"merged into Test#\u003Cnn>\")\n   - **MODIFY**: change the named field; the tags follow the level and priority\n   - Update `## Coverage` for every requirement touched\n3. Check the floor: `node ${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fplan-check.mjs \u003Cplan> --against \u003Cthe 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\n4. Append one line to `## Review log` (create the section above `## Retired` if missing):\n\n   ```markdown\n   ## Review log\n   | Date | Score | Applied | Rejected |\n   |---|---|---|---|\n   | 2026-11-05 | 74\u002F100 | A1, A2, R1 | M1 (user: the UI message differs from the API's) |\n   ```\n   \"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)\n5. 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\n6. If the user picked none: only the Review log line changes. Status and rows stay as they were (an approved plan stays approved)\n7. `issue.comment(plan ref, \u003Cscorecard + proposals, then \"Applied: … · Rejected: …\">)`. A local-only plan has no issue: save the review as `qa-artifacts\u002Ftest-plans\u002F\u003Cplan-name>.review-\u003CYYYY-MM-DD>.md` instead\n8. If the plan's test folder already has files, list what `write it Plan: \u003Cref>` will add, and the retired IDs whose files `plan-check.mjs` will flag. Never delete test files here\n\n## Report\nThe score, what was applied and refused, the floor result, the run-time line, and the next step: approve the plan (`plan it Plan: \u003Cref> approve`, or the `plan-approved` label), then `write it Plan: \u003Cref>` or `e2e it Plan: \u003Cref>`.\n","# WAY 20 — Review a Test Plan\n\n`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.**\n\n## Step 1: Gather inputs\n**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\u002Ftest-plans\u002F`: name it back to the user.\n**Optional:** `budget: \u003Cminutes>` for the P0+P1 tests that run on every MR\u002FPR (default `QA_PLAN_BUDGET_MIN` from `.env`, else 10) · `history: off` (skip bug and flaky history).\n\n## Phase 1: Read\n1. 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)\n2. 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\n\n## Phase 2: Context\n1. `node ${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fplan-check.mjs \u003Cplan> --estimate --budget \u003Cminutes>`. Keep the whole output: errors, warnings and the `⏱` lines\n2. Unless `history: off`:\n   - **Bugs**: `issue.list` with label `bug`, state closed, text = the plan's test folder name, then again with the source ref. Keep those closed in the last 90 days: ref, title, area, root cause if the body states one\n   - **Flaky**: if `qa-artifacts\u002Fruns\u002F` has ≥ 3 runs, `node \"${CLAUDE_PLUGIN_ROOT}\u002F.claude\u002Fskills\u002Fflaky-triage\u002Fflaky.mjs\" runs 10 .` from `qa-artifacts\u002F`, and keep the scenarios of the plan's test folder with verdict `flaky`\n   - Neither source available: say \"no history\" in the review, and carry on\n\n## Phase 3: Review\nRun `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.\n\n## Phase 4: Show and ask\nShow the scorecard and the proposals table. If the score is below 70, add one line: *\"Score \u003Cn>\u002F100: read the proposals before approving.\"* It's a warning, never a block. Then ask:\n\n*\"Apply all, apply by ID (e.g. A1,R2), or none?\"*\n\nWith `plan: auto` (unattended, from WAY 1\u002F4), don't ask and apply nothing: the proposals go in the review comment for a human to pick later.\n\n## Phase 5: Apply\n1. Save a copy of the plan as it is now (`qa-artifacts\u002Ftest-plans\u002F.\u003Cplan-name>.before.md`)\n2. Apply the picked proposals per the `test-plan` skill's **Changing a plan**:\n   - **ADD**: a new Planned tests row with the proposal's ID, fields and priority tag\n   - **REMOVE**: the row moves to `## Retired` with the reason\n   - **MERGE**: the lowest ID becomes the Outline row (`… (Outline: N rows)`), the others move to Retired (\"merged into Test#\u003Cnn>\")\n   - **MODIFY**: change the named field; the tags follow the level and priority\n   - Update `## Coverage` for every requirement touched\n3. Check the floor: `node ${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fplan-check.mjs \u003Cplan> --against \u003Cthe 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\n4. Append one line to `## Review log` (create the section above `## Retired` if missing):\n\n   ```markdown\n   ## Review log\n   | Date | Score | Applied | Rejected |\n   |---|---|---|---|\n   | 2026-11-05 | 74\u002F100 | A1, A2, R1 | M1 (user: the UI message differs from the API's) |\n   ```\n   \"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)\n5. 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\n6. If the user picked none: only the Review log line changes. Status and rows stay as they were (an approved plan stays approved)\n7. `issue.comment(plan ref, \u003Cscorecard + proposals, then \"Applied: … · Rejected: …\">)`. A local-only plan has no issue: save the review as `qa-artifacts\u002Ftest-plans\u002F\u003Cplan-name>.review-\u003CYYYY-MM-DD>.md` instead\n8. If the plan's test folder already has files, list what `write it Plan: \u003Cref>` will add, and the retired IDs whose files `plan-check.mjs` will flag. Never delete test files here\n\n## Report\nThe score, what was applied and refused, the floor result, the run-time line, and the next step: approve the plan (`plan it Plan: \u003Cref> approve`, or the `plan-approved` label), then `write it Plan: \u003Cref>` or `e2e it Plan: \u003Cref>`.\n",{"name":5,"description":7},"main","1d5072195baea48c4081624f3d8466179bcabd7d",".claude\u002Fskills\u002Freview-plan",4,"https:\u002F\u002Fgithub.com\u002FGhassenAZZOUZ\u002Fclaude-qa-agent","https:\u002F\u002Fgithub.com\u002FGhassenAZZOUZ","QA automation Engineer ","2026-11-06 18:32:27",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add GhassenAZZOUZ\u002Fclaude-qa-agent --skill review-plan",{"tool":38,"command":39},"bunx","bunx skills add GhassenAZZOUZ\u002Fclaude-qa-agent --skill review-plan",{"tool":41,"command":42},"pnpm","pnpm dlx skills add GhassenAZZOUZ\u002Fclaude-qa-agent --skill review-plan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGhassenAZZOUZ\u002Fclaude-qa-agent\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Freview-plan\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7EGNW6C1N9425A4KW554XWA","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\u002FSpec\u002FMR or PR → exactly the planned test files.","https:\u002F\u002Fgithub.com\u002FGhassenAZZOUZ\u002Fclaude-qa-agent\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwrite-tests\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7EGNNESQM030EFGZD1BKK9P","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.","https:\u002F\u002Fgithub.com\u002FGhassenAZZOUZ\u002Fclaude-qa-agent\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fverify-fix\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7EGNGAYM3WHT9P1JS0KTD2X","user-story-format","Reference only — the single definition of this project's user-story body (story, Gherkin ACs, Missing Information, DoD) and its AC\u002Fscenario 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.","https:\u002F\u002Fgithub.com\u002FGhassenAZZOUZ\u002Fclaude-qa-agent\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fuser-story-format\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7EGNB3MZXAWXX7HQP534T9S","tracker","Provider-neutral contract for every issue-tracker and code-host action (create\u002Fupdate\u002Fcomment\u002Fclose issues, attach files, comment on MRs\u002FPRs, 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.","https:\u002F\u002Fgithub.com\u002FGhassenAZZOUZ\u002Fclaude-qa-agent\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftracker\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7EGN66A9GH5MQQNKJFS8ADP","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 \u003Cfolder>\".","https:\u002F\u002Fgithub.com\u002FGhassenAZZOUZ\u002Fclaude-qa-agent\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftraceability\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7EGMZ8K606CZT7ND3N2YHDV","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\u002FSpec\u002FMR or PR. Output is the test plan (scope, levels, one row per Test#\u003Cnn> with category, tags, covers, priority, coverage, entry\u002Fexit criteria, risks), reviewed by `review-plan` (WAY 20), filed for approval; `write it Plan:` \u002F `e2e it Plan:` then write exactly that plan. Also holds the plan format every other WAY reads.","https:\u002F\u002Fgithub.com\u002FGhassenAZZOUZ\u002Fclaude-qa-agent\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftest-plan\u002FSKILL.md",[],[]]