[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M749D45TF2H5XWTG7GHXVCWB":3,"skill-same:01M749D45TF2H5XWTG7GHXVCWB":59},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":15,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":13,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M749D45TF2H5XWTG7GHXVCWB","code-review",null,"Review a branch, PR, work in progress, or changes since a ref against repository standards and the originating requirements.","schola-cantorum\u002Fcantus","schola-cantorum","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F283400993?v=4","01M72671Q6RSVYYFN4JQ8QRSWT","01M72671QTZWY2WZ34AZF9AC3T",0,"MIT","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcode-review\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcode-review\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: code-review\ndescription: Review a branch, PR, work in progress, or changes since a ref against repository standards and the originating requirements.\n---\n\nReview a captured change on two independent axes: **Standards** (repository rules)\nand **Spec** (the originating requirements). Keep their findings separate.\n\n## 1. Capture the requested scope\n\nUse the requested base and scope, including any already established in the task.\nFor a WIP-only review with no base, use HEAD. For a branch or PR, use its known\ntarget; if the target is unknown, ask. Resolve base, HEAD and merge-base to commit IDs.\n\nFollow [review-surface.md](references\u002Freview-surface.md) to capture the review packet.\nA branch\u002FPR review covers committed changes unless pending work was requested;\nan implementation review includes the pending work being implemented. State exclusions.\nAn invalid ref stops capture. An empty committed diff alone does not stop a WIP\nreview. If every requested layer is empty, report no changes without launching\nreviewers or claiming a review pass.\n\n## 2. Find requirements and standards\n\nRead `docs\u002Fagents\u002Fissue-tracker.md` when resolving tracker artifacts. If missing,\nask the user to run `\u002Fsetup-matt-pocock-skills`. Find requirements in this order:\n\n1. The approved spec or maintenance plan already supplied in the task.\n2. A path or issue reference supplied by the user.\n3. Issue references in captured commit messages, using the configured tracker.\n4. A matching spec under the configured tracker paths.\n5. If none is found, ask where the requirements are. If the user confirms there\n   are none, skip Spec and report \"no spec available\"; do not claim compliance.\n\nFind applicable repository standards such as AGENTS.md, CONTRIBUTING.md and\nCODING_STANDARDS.md. For the Standards axis, also load\n[the smell baseline](references\u002Fsmell-baseline.md). These are labeled heuristics;\ndocumented repository standards override them. Skip checks already enforced by tooling.\n\n## 3. Run independent reviews\n\nRun Standards and Spec as parallel read-only subagents: the `Agent` tool with\n`harness-reviewer`, one axis each.\nGive both the same captured diffs, relevant file contents, scope manifest,\nbase\u002FHEAD IDs and commit list. A diff command alone is not a snapshot.\nKeep the checkout stable while they read surrounding context.\n\n**Standards assignment:** Include applicable standards and the loaded smell\nbaseline. Report each documented-standard breach with file:line, the rule and\nevidence. Report smells separately as judgment calls, naming the smell and quoting\nthe relevant hunk. Explain the impact; repository rules override the baseline.\n\n**Spec assignment:** Include the requirements. Report missing or partial behavior,\nunrequested scope, and incorrect implementations. Cite the requirement and the\ncaptured file:line for each finding, explaining the impact.\n\nAsk each reviewer to report every finding, including uncertain or low-severity\nones, with its evidence, confidence and severity (high, medium or low impact).\nAt this stage the job is coverage; the user decides what to act on. If Spec has\nno source, run only Standards.\nIf independent contexts are unavailable, use isolated passes and disclose that limit.\n\n## 4. Report\n\nCheck the snapshot for drift as described in review-surface.md. Present findings\nunder `## Standards` and `## Spec`, verbatim or lightly cleaned; do not merge or\nrerank them across axes. End with finding counts and the worst issue within each\naxis. State the reviewed scope, skipped coverage and evidence limits.\n\nA change can follow standards while implementing the wrong requirement, or match\nrequirements while violating standards. One axis passing does not imply the other.\n","Review a captured change on two independent axes: **Standards** (repository rules)\nand **Spec** (the originating requirements). Keep their findings separate.\n\n## 1. Capture the requested scope\n\nUse the requested base and scope, including any already established in the task.\nFor a WIP-only review with no base, use HEAD. For a branch or PR, use its known\ntarget; if the target is unknown, ask. Resolve base, HEAD and merge-base to commit IDs.\n\nFollow [review-surface.md](references\u002Freview-surface.md) to capture the review packet.\nA branch\u002FPR review covers committed changes unless pending work was requested;\nan implementation review includes the pending work being implemented. State exclusions.\nAn invalid ref stops capture. An empty committed diff alone does not stop a WIP\nreview. If every requested layer is empty, report no changes without launching\nreviewers or claiming a review pass.\n\n## 2. Find requirements and standards\n\nRead `docs\u002Fagents\u002Fissue-tracker.md` when resolving tracker artifacts. If missing,\nask the user to run `\u002Fsetup-matt-pocock-skills`. Find requirements in this order:\n\n1. The approved spec or maintenance plan already supplied in the task.\n2. A path or issue reference supplied by the user.\n3. Issue references in captured commit messages, using the configured tracker.\n4. A matching spec under the configured tracker paths.\n5. If none is found, ask where the requirements are. If the user confirms there\n   are none, skip Spec and report \"no spec available\"; do not claim compliance.\n\nFind applicable repository standards such as AGENTS.md, CONTRIBUTING.md and\nCODING_STANDARDS.md. For the Standards axis, also load\n[the smell baseline](references\u002Fsmell-baseline.md). These are labeled heuristics;\ndocumented repository standards override them. Skip checks already enforced by tooling.\n\n## 3. Run independent reviews\n\nRun Standards and Spec as parallel read-only subagents: the `Agent` tool with\n`harness-reviewer`, one axis each.\nGive both the same captured diffs, relevant file contents, scope manifest,\nbase\u002FHEAD IDs and commit list. A diff command alone is not a snapshot.\nKeep the checkout stable while they read surrounding context.\n\n**Standards assignment:** Include applicable standards and the loaded smell\nbaseline. Report each documented-standard breach with file:line, the rule and\nevidence. Report smells separately as judgment calls, naming the smell and quoting\nthe relevant hunk. Explain the impact; repository rules override the baseline.\n\n**Spec assignment:** Include the requirements. Report missing or partial behavior,\nunrequested scope, and incorrect implementations. Cite the requirement and the\ncaptured file:line for each finding, explaining the impact.\n\nAsk each reviewer to report every finding, including uncertain or low-severity\nones, with its evidence, confidence and severity (high, medium or low impact).\nAt this stage the job is coverage; the user decides what to act on. If Spec has\nno source, run only Standards.\nIf independent contexts are unavailable, use isolated passes and disclose that limit.\n\n## 4. Report\n\nCheck the snapshot for drift as described in review-surface.md. Present findings\nunder `## Standards` and `## Spec`, verbatim or lightly cleaned; do not merge or\nrerank them across axes. End with finding counts and the worst issue within each\naxis. State the reviewed scope, skipped coverage and evidence limits.\n\nA change can follow standards while implementing the wrong requirement, or match\nrequirements while violating standards. One axis passing does not imply the other.\n",{"name":5,"description":7},"main","3adbc786c457728f54420f3e73a321bb7e36bc15",".claude\u002Fskills\u002Fcode-review","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus","https:\u002F\u002Fcantus.rtfm.diy\u002F","https:\u002F\u002Fgithub.com\u002Fschola-cantorum","2026-11-12 21:57:12",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add schola-cantorum\u002Fcantus --skill code-review",{"tool":37,"command":38},"bunx","bunx skills add schola-cantorum\u002Fcantus --skill code-review",{"tool":40,"command":41},"pnpm","pnpm dlx skills add schola-cantorum\u002Fcantus --skill code-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcode-review\u002FSKILL.md",true,[45,49,55],{"path":46,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":15},"LICENSE","许可证",1068,{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Freview-surface.md","REFERENCE","参考文档",2035,"https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcode-review\u002Freferences\u002Freview-surface.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fsmell-baseline.md",1266,"https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcode-review\u002Freferences\u002Fsmell-baseline.md",[60,68,76,84,92,100],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":64,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M749FSZ1CYNNSNXWVK8EGMTV","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-for-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":72,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M749FPQ8PE36Y9TBJ7KJES81","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwizard\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M749FM7AEMTHHC0VY7QTZRAR","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwayfinder\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M749FJE84F5E51DEQZZJZWV1","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwait-what\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M749F6YBDZPACWPC4JGSFSNH","to-tickets","Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fto-tickets\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fto-tickets\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M749F4SYDPQ8NRMWM0RG5HAN","to-spec","Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fto-spec\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fto-spec\u002FSKILL.md",[],[]]