[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A09FTDBSMW33ESDA5P9CKK":3,"skill-same:01M7A09FTDBSMW33ESDA5P9CKK":71},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7A09FTDBSMW33ESDA5P9CKK","verify-acceptance-items",null,"Verify a GitHub pull request or GitLab merge request (MR) against the acceptance criteria (验收标准\u002F条件, task-list checkboxes) of the issues it links to, then tick the criteria it proves once the user confirms. Use when asked whether a PR or MR is done or meets its issue, when asked to check off an issue's checkboxes, or right after opening or updating a PR or MR that closes an issue.","meymchen\u002Fskills","meymchen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F86772442?v=4","01M7A07YW1B5X4TFJ0S1SRNM7M","Yuming Chen","01M7A07YX3VNGS7DC687B1P7A1",0,"MIT","https:\u002F\u002Fgithub.com\u002Fmeymchen\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopment\u002Fverify-acceptance-items\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: verify-acceptance-items\ndescription: Verify a GitHub pull request or GitLab merge request (MR) against the acceptance criteria (验收标准\u002F条件, task-list checkboxes) of the issues it links to, then tick the criteria it proves once the user confirms. Use when asked whether a PR or MR is done or meets its issue, when asked to check off an issue's checkboxes, or right after opening or updating a PR or MR that closes an issue.\n---\n\n# Verify Acceptance Items\n\n## Vocabulary\n\n- **Request**: a GitHub pull request or a GitLab merge request. Report it with\n  the platform's own term, such as PR #12 or MR !42; `links` returns it as\n  `request_label`.\n- **Acceptance criterion**: a task-list item in an issue body that states\n  something the work must satisfy. Its section heading varies: `Acceptance\n  criteria`, `验收标准`, `验收条件`, `Definition of done`, a bold line, a `\u003Cdetails>` block.\n- **Item id**: the `L\u003Cline>` id `extract` gives every task-list item. Ids carry\n  each criterion from `extract` through `brief` and the verdicts to `apply`.\n- **Verdict**: `satisfied`, `unsatisfied`, or `undecidable`.\n\nThe script does every deterministic part: detecting the platform, resolving\nlinks, parsing the body, rendering the judging brief, and ticking. You supply\nthe two judgements it cannot make: which items are acceptance criteria, and\nwhat the user decides. Resolve the skill directory from the loaded `SKILL.md`\npath and run\n`uv run --script \u003Cskill-dir>\u002Fscripts\u002Fverify_acceptance_items.py \u003Ccommand>`.\n\nThe script detects the platform from the current branch's upstream remote, or\n`origin`, and uses `gh` for GitHub and `glab` for GitLab. Exit code 2 with\n\"cannot tell whether ... is GitHub or GitLab\" means the host is ambiguous: ask\nthe user which it is and pass `--platform github` or `--platform gitlab` on\nevery command. Exit code 2 naming `auth login` means the CLI is missing or\nsigned out: tell the user to run the command it names. Every command accepts\n`--repo` (a project path such as `group\u002Fsub\u002Fproject`, or a project URL) and\n`--host`.\n\n## 1. Resolve the issues\n\n```console\nuv run --script \u003Cskill-dir>\u002Fscripts\u002Fverify_acceptance_items.py links [--request \u003Cnumber>]\n```\n\nWithout `--request` it uses the current branch's request. Each candidate\ncarries a `provenance`. Use a `closing_reference` directly. For a\n`body_mention`, `related_issue`, or `branch_name` candidate, name it to the user\nand get agreement before using it. Mention a `rejected` number only if the user\nexpected that issue to be covered.\n\nProcess every accepted candidate, each in its own report section, passing its\n`repo` to the later commands.\n\n## 2. Extract the structure\n\n```console\nuv run --script \u003Cskill-dir>\u002Fscripts\u002Fverify_acceptance_items.py extract --repo \u003Cproject> --issue \u003Cnumber>\n```\n\nEach item comes with `id`, `text` (wrapped lines folded in), `state`\n(`unchecked`, `checked`, or `inapplicable`), `depth`, `parent`, `sub_issue`, and\nits `heading_path`. Keep the `body_sha256` for step 6.\n\nReport every `skipped` entry as detected and not handled: `table` for\ncheckboxes in a table, `comment` for task lists in the issue's comments.\n\n## 3. Choose the acceptance criteria\n\nPick sections from `heading_path` and the wording of their items. When more than\none section plausibly holds acceptance criteria, include them all and say why\neach was included; over-listing costs the user a glance, under-listing hides a\ncriterion for good. Leave out `sub_issue: true` items, which only reference\nanother issue, and `inapplicable` items, which the author marked `[~]`; list\nthe latter in the report as inapplicable. If the body has checkboxes but none\nread like acceptance criteria, say so plainly.\n\nDone when every item is chosen, or excluded with a reason.\n\n## 4. Judge in one subagent\n\n```console\nuv run --script \u003Cskill-dir>\u002Fscripts\u002Fverify_acceptance_items.py brief --repo \u003Crequest-project> --request \u003Cnumber> --items \"#42:L13,L15\" \"group\u002Fsub\u002Fspec#3:L4\"\n```\n\nOne `--items` selection per issue; the project prefix defaults to `--repo`. The\noutput is the complete prompt: the evidence commands for the platform, the\nverdict definitions, the answer format, and the chosen criteria. Hand it\nverbatim to a single subagent with a fresh context, and add nothing. A session\nthat wrote the request knows the intent behind the code, and that intent reads\nas evidence the diff does not hold; one sentence of your own summary carries it\nacross.\n\nOne subagent covers every issue: the fresh context provides the isolation, and\nreading the request dominates the cost. Split the selections across subagents\nonly when one brief is too large to hold, and say so in the report.\n\nReport verdicts as returned. Where you disagree because of something outside\nthe request, carry the criterion as `undecidable` and let the user settle it.\nRe-run `brief` and the subagent only to fix a faulty selection.\n\nWithout subagent support, follow the brief yourself and state that the judging\nwas not isolated.\n\n## 5. Report, then wait\n\n1. A table of every criterion with its id, verdict, and evidence.\n2. A **numbered** queue of `undecidable` criteria, so the user can answer \"1 and\n   3 are satisfied\".\n3. Warnings for criteria already ticked that this request's evidence does not\n   support.\n\nThen stop. Write nothing until the user responds.\n\n## 6. Tick\n\nTick `satisfied` criteria and `undecidable` ones the user adjudicated as\nsatisfied; mark the latter as user-adjudicated in the report. One call per\nissue:\n\n```console\nuv run --script \u003Cskill-dir>\u002Fscripts\u002Fverify_acceptance_items.py apply --repo \u003Cproject> --issue \u003Cnumber> --body-sha256 \u003Cfrom extract> --tick L13 L15\n```\n\n`apply` re-reads the body, aborts with exit code 2 if its hash changed, refuses\nany id that is not a tickable item with exit code 64, flips only `[ ]`\ncharacters, and reads the body back after writing. On exit code 2, re-run from\nstep 2 for that issue and ask the user again if its criteria changed. Exit code\n2 after a permission failure means the account cannot write to that project;\nthe report still stands. Exit code 1 with a read-back difference means the\nplatform stored something other than what was sent: show the user the\ndifference and do not retry.\n\nPost no comment unless the user asks; then comment on the request, not the\nissue.\n\n## Guardrails\n\n- Every write goes through `apply`. A body rebuilt any other way loses images,\n  HTML comments, and trailing whitespace the author may not be able to recover.\n- Ticks only move from `[ ]` to `[x]`. A tick may rest on verification you\n  cannot see, so an unsupported tick earns a warning and stays.\n- `unsatisfied` criteria stay unticked.\n","# Verify Acceptance Items\n\n## Vocabulary\n\n- **Request**: a GitHub pull request or a GitLab merge request. Report it with\n  the platform's own term, such as PR #12 or MR !42; `links` returns it as\n  `request_label`.\n- **Acceptance criterion**: a task-list item in an issue body that states\n  something the work must satisfy. Its section heading varies: `Acceptance\n  criteria`, `验收标准`, `验收条件`, `Definition of done`, a bold line, a `\u003Cdetails>` block.\n- **Item id**: the `L\u003Cline>` id `extract` gives every task-list item. Ids carry\n  each criterion from `extract` through `brief` and the verdicts to `apply`.\n- **Verdict**: `satisfied`, `unsatisfied`, or `undecidable`.\n\nThe script does every deterministic part: detecting the platform, resolving\nlinks, parsing the body, rendering the judging brief, and ticking. You supply\nthe two judgements it cannot make: which items are acceptance criteria, and\nwhat the user decides. Resolve the skill directory from the loaded `SKILL.md`\npath and run\n`uv run --script \u003Cskill-dir>\u002Fscripts\u002Fverify_acceptance_items.py \u003Ccommand>`.\n\nThe script detects the platform from the current branch's upstream remote, or\n`origin`, and uses `gh` for GitHub and `glab` for GitLab. Exit code 2 with\n\"cannot tell whether ... is GitHub or GitLab\" means the host is ambiguous: ask\nthe user which it is and pass `--platform github` or `--platform gitlab` on\nevery command. Exit code 2 naming `auth login` means the CLI is missing or\nsigned out: tell the user to run the command it names. Every command accepts\n`--repo` (a project path such as `group\u002Fsub\u002Fproject`, or a project URL) and\n`--host`.\n\n## 1. Resolve the issues\n\n```console\nuv run --script \u003Cskill-dir>\u002Fscripts\u002Fverify_acceptance_items.py links [--request \u003Cnumber>]\n```\n\nWithout `--request` it uses the current branch's request. Each candidate\ncarries a `provenance`. Use a `closing_reference` directly. For a\n`body_mention`, `related_issue`, or `branch_name` candidate, name it to the user\nand get agreement before using it. Mention a `rejected` number only if the user\nexpected that issue to be covered.\n\nProcess every accepted candidate, each in its own report section, passing its\n`repo` to the later commands.\n\n## 2. Extract the structure\n\n```console\nuv run --script \u003Cskill-dir>\u002Fscripts\u002Fverify_acceptance_items.py extract --repo \u003Cproject> --issue \u003Cnumber>\n```\n\nEach item comes with `id`, `text` (wrapped lines folded in), `state`\n(`unchecked`, `checked`, or `inapplicable`), `depth`, `parent`, `sub_issue`, and\nits `heading_path`. Keep the `body_sha256` for step 6.\n\nReport every `skipped` entry as detected and not handled: `table` for\ncheckboxes in a table, `comment` for task lists in the issue's comments.\n\n## 3. Choose the acceptance criteria\n\nPick sections from `heading_path` and the wording of their items. When more than\none section plausibly holds acceptance criteria, include them all and say why\neach was included; over-listing costs the user a glance, under-listing hides a\ncriterion for good. Leave out `sub_issue: true` items, which only reference\nanother issue, and `inapplicable` items, which the author marked `[~]`; list\nthe latter in the report as inapplicable. If the body has checkboxes but none\nread like acceptance criteria, say so plainly.\n\nDone when every item is chosen, or excluded with a reason.\n\n## 4. Judge in one subagent\n\n```console\nuv run --script \u003Cskill-dir>\u002Fscripts\u002Fverify_acceptance_items.py brief --repo \u003Crequest-project> --request \u003Cnumber> --items \"#42:L13,L15\" \"group\u002Fsub\u002Fspec#3:L4\"\n```\n\nOne `--items` selection per issue; the project prefix defaults to `--repo`. The\noutput is the complete prompt: the evidence commands for the platform, the\nverdict definitions, the answer format, and the chosen criteria. Hand it\nverbatim to a single subagent with a fresh context, and add nothing. A session\nthat wrote the request knows the intent behind the code, and that intent reads\nas evidence the diff does not hold; one sentence of your own summary carries it\nacross.\n\nOne subagent covers every issue: the fresh context provides the isolation, and\nreading the request dominates the cost. Split the selections across subagents\nonly when one brief is too large to hold, and say so in the report.\n\nReport verdicts as returned. Where you disagree because of something outside\nthe request, carry the criterion as `undecidable` and let the user settle it.\nRe-run `brief` and the subagent only to fix a faulty selection.\n\nWithout subagent support, follow the brief yourself and state that the judging\nwas not isolated.\n\n## 5. Report, then wait\n\n1. A table of every criterion with its id, verdict, and evidence.\n2. A **numbered** queue of `undecidable` criteria, so the user can answer \"1 and\n   3 are satisfied\".\n3. Warnings for criteria already ticked that this request's evidence does not\n   support.\n\nThen stop. Write nothing until the user responds.\n\n## 6. Tick\n\nTick `satisfied` criteria and `undecidable` ones the user adjudicated as\nsatisfied; mark the latter as user-adjudicated in the report. One call per\nissue:\n\n```console\nuv run --script \u003Cskill-dir>\u002Fscripts\u002Fverify_acceptance_items.py apply --repo \u003Cproject> --issue \u003Cnumber> --body-sha256 \u003Cfrom extract> --tick L13 L15\n```\n\n`apply` re-reads the body, aborts with exit code 2 if its hash changed, refuses\nany id that is not a tickable item with exit code 64, flips only `[ ]`\ncharacters, and reads the body back after writing. On exit code 2, re-run from\nstep 2 for that issue and ask the user again if its criteria changed. Exit code\n2 after a permission failure means the account cannot write to that project;\nthe report still stands. Exit code 1 with a read-back difference means the\nplatform stored something other than what was sent: show the user the\ndifference and do not retry.\n\nPost no comment unless the user asks; then comment on the request, not the\nissue.\n\n## Guardrails\n\n- Every write goes through `apply`. A body rebuilt any other way loses images,\n  HTML comments, and trailing whitespace the author may not be able to recover.\n- Ticks only move from `[ ]` to `[x]`. A tick may rest on verification you\n  cannot see, so an unsupported tick earns a warning and stays.\n- `unsatisfied` criteria stay unticked.\n",{"name":5,"description":7},"main","034f338e49d8ea376e159fafec7e59bf79f55107","skills\u002Fdevelopment\u002Fverify-acceptance-items","https:\u002F\u002Fgithub.com\u002Fmeymchen\u002Fskills","https:\u002F\u002Fgithub.com\u002Fmeymchen","A full-stack AI & CFD engineer","2026-10-16 09:14:33",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add meymchen\u002Fskills --skill verify-acceptance-items",{"tool":37,"command":38},"bunx","bunx skills add meymchen\u002Fskills --skill verify-acceptance-items",{"tool":40,"command":41},"pnpm","pnpm dlx skills add meymchen\u002Fskills --skill verify-acceptance-items","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmeymchen\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopment\u002Fverify-acceptance-items\u002FSKILL.md",true,[45,51,57,61,67],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",346,"https:\u002F\u002Fgithub.com\u002Fmeymchen\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopment\u002Fverify-acceptance-items\u002Fagents\u002Fopenai.yaml",{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"assets\u002Fjudge-brief.md","ASSET","资产文件",982,"https:\u002F\u002Fgithub.com\u002Fmeymchen\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopment\u002Fverify-acceptance-items\u002Fassets\u002Fjudge-brief.md",{"path":58,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":59,"sourceHtmlUrl":60},"README.md",875,"https:\u002F\u002Fgithub.com\u002Fmeymchen\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopment\u002Fverify-acceptance-items\u002FREADME.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fverify_acceptance_items.py","SCRIPT","脚本",45447,"https:\u002F\u002Fgithub.com\u002Fmeymchen\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopment\u002Fverify-acceptance-items\u002Fscripts\u002Fverify_acceptance_items.py",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"tests\u002Ftest_verify_acceptance_items.py",54482,"https:\u002F\u002Fgithub.com\u002Fmeymchen\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopment\u002Fverify-acceptance-items\u002Ftests\u002Ftest_verify_acceptance_items.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7A09PZZAC1V90F8PXN278KS","cleanup-merged-branch","Safely clean a merged local branch, reproducible worktree caches, and stale local branches before updating the repository default branch.","https:\u002F\u002Fgithub.com\u002Fmeymchen\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Froutine\u002Fcleanup-merged-branch\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7A09CYZ6M8F4PC8QEBQ4Y1E","update-request-body","Update the title and body of one or more GitHub pull requests or GitLab merge requests (MRs).","https:\u002F\u002Fgithub.com\u002Fmeymchen\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fgit-workflows\u002Fskills\u002Fupdate-request-body\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7A099Q7HVH5ZWCJ76MTFB3V","commit","Create a Git commit from the current changes.","https:\u002F\u002Fgithub.com\u002Fmeymchen\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fgit-workflows\u002Fskills\u002Fcommit\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7A095EK8QKEP2RJHBQZM3W3","commit-push-request","Commit current changes, push the branch, and open a GitHub pull request or GitLab merge request (MR).","https:\u002F\u002Fgithub.com\u002Fmeymchen\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fgit-workflows\u002Fskills\u002Fcommit-push-request\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7A093GR1VP5X5NQQVBAD5RZ","clean-gone","Remove local Git branches whose upstreams are gone, including associated worktrees.","https:\u002F\u002Fgithub.com\u002Fmeymchen\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fgit-workflows\u002Fskills\u002Fclean-gone\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7A0909AS6VQ73MVN088PCX9","testing-strategy","Design test strategies and test plans. Trigger with \"how should we test\", \"test strategy for\", \"write tests for\", \"test plan\", \"what tests do we need\", or when the user needs help with testing approaches, coverage, or test architecture.","https:\u002F\u002Fgithub.com\u002Fmeymchen\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fengineering\u002Fskills\u002Ftesting-strategy\u002FSKILL.md",[],[]]