[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7596HM4D07RAB7RS0V4Y97R":3,"skill-same:01M7596HM4D07RAB7RS0V4Y97R":50},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7596HM4D07RAB7RS0V4Y97R","review-verify",null,"Internal run-it verification review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Runs the project's gate and the changed behavior for real — commands, exit codes, observed output — instead of assuming; what cannot be executed goes to the manual checklist. Findings only; never edits code.","gtrabanco\u002Fagentic-workflow","gtrabanco","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1969593?v=4","01M7592KB3BVKCQFTXT94HVMT6","Gabriel Trabanco","01M7592KBTHE8HPQ8V87GJQYV8",23,"MIT","https:\u002F\u002Fgithub.com\u002Fgtrabanco\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Freview-verify\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: review-verify\nuser-invocable: false\nversion: 4.10.0\nauthor: \"Gabriel Trabanco \u003C1969593+gtrabanco@users.noreply.github.com>\"\nlicense: MIT\ndescription: >\n  Internal run-it verification review pass of the agentic-workflow review pack —\n  composed in-turn by review-change and product-audit; not a menu entry. Runs\n  the project's gate and the changed behavior for real — commands, exit codes,\n  observed output — instead of assuming; what cannot be executed goes to the\n  manual checklist. Findings only; never edits code.\n---\n\n# Review Verify (internal)\n> **Runner commands** below are `bunx @gtrabanco\u002Fagentic-workflow@\u003Cpin> …` — read `\u003Cpin>`\n> from [references\u002FRUNNER.md](..\u002Frunner-contract\u002Freferences\u002FRUNNER.md). It is stamped at\n> release and never guessed: a hard-coded version re-opens the per-release sweep the\n> contract removes, and `latest` is not a legal pin.\n\nComposed by `review-change` \u002F `product-audit` within their conversation — on any\nagent, follow this file inline as the routed step. **Findings only; never edits,\nnever refactors.**\n\n**Shift from discoverer to auditor of recorded evidence (S5).** The implementer's\nclaim-evidence loop is the primary verification. This review *audits* the\nrecorded evidence: re-runs a sample of the recorded commands instead of\nre-deriving the whole change. This is the cost-scaling invariant — reviewers\ndig into code only when evidence is absent or contradicts.\n\n## Scope\n\nThe caller's diff or path\u002Fglob — the shape is the finder contract's\n(`skills\u002Freview-implementation\u002Freferences\u002FFINDER_CONTRACT.md`, this section's owner). State the scope at the top of the\nreturned table.\n\n## Checklist (evaluate EVERY item — none is optional; n\u002Fa must be stated)\n\n✓ **Evidence audit.** Sample the unit doc's Evidence rows: re-run ≥ 3 of the\n  recorded commands and compare observed output against what the implementer\n  recorded. Mismatch → finding: \"evidence contradicts observation at \u003Cfile:line>\".\n✓ **Claim-evidence loop verification.** Check the fold's claim table (if\n  present): every row has `status: ✓`. Any `✗` row means the implementer's\n  turn did not complete its claim-evidence loop.\n✓ **Unit-route triage currency.** Re-run `bunx @gtrabanco\u002Fagentic-workflow@\u003Cpin> unit-route --triage\n  \u003Cslug>` and compare the `Steps:` line against the unit doc's Evidence section.\n  Mismatch → stale triage.\n✓ **Gate evidence is consumed, not re-run.** Run `bun scripts\u002Fgate-receipt.mjs verify`; it answers the receipt's state: `current` + `pass` (exit 0) means the\n  declared closure has not moved — cite its `checks[]` ids and `manifest.digest`\n  as the gate evidence; `missing` (3), `stale` (4) or `invalid` (5) is a finding\n  routed to `bun scripts\u002Fgate-receipt.mjs run`, never a prompt to run the gate\n  from this review and never an implicit pass; a current `fail`\u002F`degraded`\n  receipt fails the review with the failing check ids and their fragments\n✓ The change's primary claimed behavior was exercised for real (run the\n  CLI\u002Fendpoint\u002Ffunction; paste the actual observed output) — *in addition to*\n  the evidence audit, verify at least one behavioral claim not covered by\n  recorded evidence\n✓ At least one failure-mode from the SPEC's dev scenarios was reproduced (bad\n  input, missing file, error path) and behaved as specified\n✓ New\u002Fchanged tests actually fail when the implementation is reverted or\n  broken (mutate or stash to prove they assert something — restore after)\n✓ No test was skipped\u002Fdisabled to get green (grep for skip\u002Fonly\u002Ftodo markers\n  in the diff)\n✓ The build artifact\u002Fdev server starts cleanly (no new warnings that indicate\n  breakage)\n✓ Anything that can only be confirmed by a human (visual, device, locale,\n  load) is listed explicitly under \"Manual\" — never silently dropped\n\n## Materiality bar\n\nThe bar is owned by `skills\u002Freview-implementation\u002Freferences\u002FFINDER_CONTRACT.md` —\napply it as written: cite the rule it violates beside the evidence; never pad the table.\n\n## Return exactly\n\n`Sev` and `Impact` are the two published closed sets (`BLOCKER | CRITICAL |\nWARNING | SUGGESTION` and `blocking | docs-only | report-only`); their meanings\nare owned by `review-implementation` (`CLASSIFY.md` §Severity ladder) — assign a\ntoken, never a prose grade.\n\n```\nREVIEW VERIFY — scope: \u003Cscope>\n\n| # | Finding | Sev | Impact | Evidence | Suggested fix |\n|---|---------|-----|--------|----------|---------------|\n| 1 | \u003Cwhat>  | BLOCKER|CRITICAL|WARNING|SUGGESTION | blocking|docs-only|report-only | \u003Cfile:line> | \u003Csmallest action> |\n\nChecklist: \u003Cn> evaluated, \u003Cn> pass, \u003Cn> findings, \u003Cn> n\u002Fa (\u003Cwhich + why>)\nSummary: \u003C1-2 sentences>\nManual (a human must check): \u003Cbullet list, or \"none\">\nDecision: PASS | FAIL\n```\n\nFAIL if any `BLOCKER`, `CRITICAL` or `WARNING` finding is open; PASS otherwise.\n`SUGGESTION` findings never block — they route to the caller's triage step.\n\n## Done when\n\n- Every checklist item was evaluated with evidence (file:line or command output)\n  or explicitly marked n\u002Fa with the reason.\n- The fixed-format block above is returned — nothing more, nothing less — and\n  no code was changed.\n","# Review Verify (internal)\n> **Runner commands** below are `bunx @gtrabanco\u002Fagentic-workflow@\u003Cpin> …` — read `\u003Cpin>`\n> from [references\u002FRUNNER.md](..\u002Frunner-contract\u002Freferences\u002FRUNNER.md). It is stamped at\n> release and never guessed: a hard-coded version re-opens the per-release sweep the\n> contract removes, and `latest` is not a legal pin.\n\nComposed by `review-change` \u002F `product-audit` within their conversation — on any\nagent, follow this file inline as the routed step. **Findings only; never edits,\nnever refactors.**\n\n**Shift from discoverer to auditor of recorded evidence (S5).** The implementer's\nclaim-evidence loop is the primary verification. This review *audits* the\nrecorded evidence: re-runs a sample of the recorded commands instead of\nre-deriving the whole change. This is the cost-scaling invariant — reviewers\ndig into code only when evidence is absent or contradicts.\n\n## Scope\n\nThe caller's diff or path\u002Fglob — the shape is the finder contract's\n(`skills\u002Freview-implementation\u002Freferences\u002FFINDER_CONTRACT.md`, this section's owner). State the scope at the top of the\nreturned table.\n\n## Checklist (evaluate EVERY item — none is optional; n\u002Fa must be stated)\n\n✓ **Evidence audit.** Sample the unit doc's Evidence rows: re-run ≥ 3 of the\n  recorded commands and compare observed output against what the implementer\n  recorded. Mismatch → finding: \"evidence contradicts observation at \u003Cfile:line>\".\n✓ **Claim-evidence loop verification.** Check the fold's claim table (if\n  present): every row has `status: ✓`. Any `✗` row means the implementer's\n  turn did not complete its claim-evidence loop.\n✓ **Unit-route triage currency.** Re-run `bunx @gtrabanco\u002Fagentic-workflow@\u003Cpin> unit-route --triage\n  \u003Cslug>` and compare the `Steps:` line against the unit doc's Evidence section.\n  Mismatch → stale triage.\n✓ **Gate evidence is consumed, not re-run.** Run `bun scripts\u002Fgate-receipt.mjs verify`; it answers the receipt's state: `current` + `pass` (exit 0) means the\n  declared closure has not moved — cite its `checks[]` ids and `manifest.digest`\n  as the gate evidence; `missing` (3), `stale` (4) or `invalid` (5) is a finding\n  routed to `bun scripts\u002Fgate-receipt.mjs run`, never a prompt to run the gate\n  from this review and never an implicit pass; a current `fail`\u002F`degraded`\n  receipt fails the review with the failing check ids and their fragments\n✓ The change's primary claimed behavior was exercised for real (run the\n  CLI\u002Fendpoint\u002Ffunction; paste the actual observed output) — *in addition to*\n  the evidence audit, verify at least one behavioral claim not covered by\n  recorded evidence\n✓ At least one failure-mode from the SPEC's dev scenarios was reproduced (bad\n  input, missing file, error path) and behaved as specified\n✓ New\u002Fchanged tests actually fail when the implementation is reverted or\n  broken (mutate or stash to prove they assert something — restore after)\n✓ No test was skipped\u002Fdisabled to get green (grep for skip\u002Fonly\u002Ftodo markers\n  in the diff)\n✓ The build artifact\u002Fdev server starts cleanly (no new warnings that indicate\n  breakage)\n✓ Anything that can only be confirmed by a human (visual, device, locale,\n  load) is listed explicitly under \"Manual\" — never silently dropped\n\n## Materiality bar\n\nThe bar is owned by `skills\u002Freview-implementation\u002Freferences\u002FFINDER_CONTRACT.md` —\napply it as written: cite the rule it violates beside the evidence; never pad the table.\n\n## Return exactly\n\n`Sev` and `Impact` are the two published closed sets (`BLOCKER | CRITICAL |\nWARNING | SUGGESTION` and `blocking | docs-only | report-only`); their meanings\nare owned by `review-implementation` (`CLASSIFY.md` §Severity ladder) — assign a\ntoken, never a prose grade.\n\n```\nREVIEW VERIFY — scope: \u003Cscope>\n\n| # | Finding | Sev | Impact | Evidence | Suggested fix |\n|---|---------|-----|--------|----------|---------------|\n| 1 | \u003Cwhat>  | BLOCKER|CRITICAL|WARNING|SUGGESTION | blocking|docs-only|report-only | \u003Cfile:line> | \u003Csmallest action> |\n\nChecklist: \u003Cn> evaluated, \u003Cn> pass, \u003Cn> findings, \u003Cn> n\u002Fa (\u003Cwhich + why>)\nSummary: \u003C1-2 sentences>\nManual (a human must check): \u003Cbullet list, or \"none\">\nDecision: PASS | FAIL\n```\n\nFAIL if any `BLOCKER`, `CRITICAL` or `WARNING` finding is open; PASS otherwise.\n`SUGGESTION` findings never block — they route to the caller's triage step.\n\n## Done when\n\n- Every checklist item was evaluated with evidence (file:line or command output)\n  or explicitly marked n\u002Fa with the reason.\n- The fixed-format block above is returned — nothing more, nothing less — and\n  no code was changed.\n",{"name":5,"author":24,"license":15,"version":25,"description":7,"user-invocable":20},"Gabriel Trabanco \u003C1969593+gtrabanco@users.noreply.github.com>","4.10.0","main","22d246afc42afe42e3491400bc5bee35ca595a2e","skills\u002Freview-verify",4,"https:\u002F\u002Fgithub.com\u002Fgtrabanco\u002Fagentic-workflow","https:\u002F\u002Fagwo.party","https:\u002F\u002Fgithub.com\u002Fgtrabanco","https:\u002F\u002Fgtrabanco.com","Sysadmin","2026-11-15 04:21:50",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add gtrabanco\u002Fagentic-workflow --skill review-verify",{"tool":42,"command":43},"bunx","bunx skills add gtrabanco\u002Fagentic-workflow --skill review-verify",{"tool":45,"command":46},"pnpm","pnpm dlx skills add gtrabanco\u002Fagentic-workflow --skill review-verify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgtrabanco\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Freview-verify\u002FSKILL.md",true,[],[51,59,66,73,80,87],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":58},"01M7DY1H34KQK6218MKVHW1H4Z","runner-contract","The distributable runner's invocation contract: one train-stamped pin for every runtime command the workflow's skills cite. Referenced by the skills that run sensors, guards and ceremony operations; never a menu entry.","https:\u002F\u002Fgithub.com\u002Fgtrabanco\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Frunner-contract\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M759762F2G81N8PX96WPC18F","verification-contract","Internal contract: the acceptance artifact per delivery unit — legacy (pre- feature 61) units may carry a frozen `ACCEPTANCE.md` (binding if present); post-feature 61 units use the unit doc's `## Acceptance criteria` section as the canonical acceptance source; the unit doc's evidence carrier — `## Evidence` table, or `## Log` `E` lines for a re-cut unit (#308) — serves as the execution receipt. Consumed by planners, execute-phase, and review-change.","https:\u002F\u002Fgithub.com\u002Fgtrabanco\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fverification-contract\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7596P2HAKP84ZSMJWCPB0S5","skill-lint","Internal agentic-workflow maintenance: after SKILL.md edits, lint the repo's authoring rules, the machine-surface registration rules and the skill-content smell\u002Fsecurity checks. Triggers: \"lint the skill\", \"skill authoring check\", \"check the skill rules\", \"scan skills for smells\".","https:\u002F\u002Fgithub.com\u002Fgtrabanco\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fskill-lint\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7596DTAQ7CTTE64Q9YEMSDE","review-seo","Internal SEO review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks changed web pages\u002Froutes for indexability, metadata, and structured data — applies only to public web surfaces. Findings only; never edits code.","https:\u002F\u002Fgithub.com\u002Fgtrabanco\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Freview-seo\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M75968HW51F81B96J1BWSDKX","review-security","Internal security review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks secrets, input validation, injection, authn\u002Fauthz, PII exposure, and dependency risk on the changed surface. Findings only; never edits code.","https:\u002F\u002Fgithub.com\u002Fgtrabanco\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Freview-security\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M75964GC5PXNKNXVM4RPY081","review-perf","Internal performance review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks the changed paths for algorithmic and resource regressions: N+1s, hot-path allocations, asset weight, and leaks. Findings only; never edits code.","https:\u002F\u002Fgithub.com\u002Fgtrabanco\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Freview-perf\u002FSKILL.md",[],[]]