[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CPAGF0MDNQKSCE61F5QJ6C":3,"skill-same:01M7CPAGF0MDNQKSCE61F5QJ6C":49},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":13,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7CPAGF0MDNQKSCE61F5QJ6C","review",null,"markosAMO\u002FAlfred","markosAMO","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F51459843?v=4","01M7CP9J22V3QPXPRGE3MJZ091","Markos Moscoso Ocampo","01M7CP9J33G8P7T5TBN51PST9G",0,"MIT","https:\u002F\u002Fgithub.com\u002FmarkosAMO\u002FAlfred\u002Fblob\u002Fmain\u002Fskills\u002Freview\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: review\nmode: auto\nskippable: false\nagent: separate_from_author\nnext: [archive]\n---\n\n# review\n\nAnswer one question: is this code sound?\n\nNot whether it satisfies the specification. `verify` established that, and repeating it here\nspends a review on work already done.\n\n## Before reviewing\n\n```\nrecall each type the workflow declares, for what the last review of this area said\n```\n\nA `should fix` nobody fixed is worth raising again, and raising it as a repeat is worth more\nthan raising it as new: the second time it appears it is a pattern rather than a nit, and\nthe reader can see it was already declined once.\n\nThis recall is why `archive` writes those findings. Without it they were written on every\nchange and read on none.\n\nFindings that the change under review has since fixed are dropped silently. Reporting a\nfinding as outstanding when the code no longer has it is how a review loses its credibility.\n\n## Runs alongside verify\n\nDispatched at the same time as `verify`. Neither reads the other's report and neither\nwrites code, so they cannot interfere.\n\nDo not wait for the verification result, and do not assume it. A review is about whether\nthe code is sound, which does not change based on whether a scenario passed.\n\n## A separate agent\n\nThis phase runs in a context that never saw the code being written. The agent that wrote it\ncannot review it: the reasoning that produced a mistake is the reasoning that would have to\ncatch it, and it already agreed with itself once.\n\nThe model is at least as strong as the one that implemented, per `docs\u002Fmodels.md`. A\nreviewer weaker than the implementer approves everything, and the phase becomes ceremony.\n\n## What it reads\n\n```\nthe diff of the change\nconventions, architecture\nthe design artifact, and the apply artifact for what changed and what was run\n```\n\nThe design is read to know what was intended, including its `Out of scope` section. Work\ndeliberately excluded is not reported as missing.\n\n## What it looks for\n\n```\nconventions      does it follow docs\u002Fcode_conventions.md\ncorrectness      error handling, edge cases, resource cleanup, concurrency\ncall sites       does the new contract hold for every caller that already exists\nsimplicity       is there a materially simpler shape with the same behaviour\nduplication      does this already exist in the codebase\ncoupling         does it reach past the boundaries the architecture draws\nsecurity         input handling, authorisation, secrets, injection surfaces\nreadability      will this be understood by someone who was not here\n```\n\n`call sites` is the one that needs looking up rather than reading. A modified signature, a\nchanged return type, a helper whose accepted input narrowed: the diff shows the change and\nnot the twelve places that depend on it. Trace them.\n\n```\nchanged    helper accepts a string\ncallers    one worker passes a symbol\nresult     a regression that passes its own author's tests\n```\n\n`verify` asks whether the tests reach the real callers. This phase asks whether the callers\nstill work, which is a different question and is answered by reading them.\n\n## Severity\n\nEvery finding carries one, because a report where everything matters equally is a report\nnobody acts on.\n\n```\nblocking     ships a defect, a security hole, or violates the architecture\nshould fix   real problem, does not have to stop this change\nsuggestion   preference, taste, or a possible future improvement\n```\n\nOnly `blocking` findings stop the change. A phase that blocks on preferences trains the\nuser to skip the phase.\n\n## Findings\n\nA finding names the file, the line, what is wrong, and what happens as a result.\n\n```markdown\n### blocking · app\u002Fcontrollers\u002Fauth_controller.rb:42\nThe OAuth state parameter is not compared before creating the session.\nA forged callback creates a session for an account the caller does not control.\n```\n\nA finding without a consequence is an opinion. If the consequence cannot be stated, the\nfinding is a `suggestion` at most.\n\nRewriting the code is not this phase's job. Findings describe the problem; `apply` fixes it.\n\n## Conventions that were never written\n\nSome findings are real but have no rule behind them: the code works, follows every written\nconvention, and still is not how this team writes code.\n\nReport those as a proposed addition to `docs\u002Fcode_conventions.md`, not as a defect.\n\n```markdown\n### convention · app\u002Fservices\u002Fpayment_service.rb:18\nErrors are returned as result objects here, while the rest of the codebase raises.\nNeither is in code_conventions.md.\nProposed: state which one this repository uses.\n```\n\nThey never block. `archive` carries them to memory like any other non-blocking finding, and\nthe user decides whether they become a rule.\n\nThis is how the conventions file fills in with what was only ever in someone's head. A\nconvention that exists only as taste produces the same review finding every time and is\nnever fixed, because there is nothing to fix it against.\n\n## What it does not do\n\nNo re-verification of scenarios. No new requirements. No style rewrites that\n`docs\u002Fcode_conventions.md` does not ask for.\n\nReviewing code the change did not touch produces findings nobody asked for and buries the\nones about the change.\n\n## What it writes\n\n```markdown\n## Result\n## Blocking\n## Should fix\n## Suggestions\n```\n\n## Failing\n\nBlocking findings return the change to `apply` with the findings attached. Only the tasks\nowning the affected files are re-dispatched.\n\n`should fix` and `suggestion` findings are recorded and do not block. `archive` carries\nthem into memory under `alfred\u002Farea\u002F{area}\u002Freview-findings`, which this phase recalls on\nthe next change touching that area — see `Before reviewing`.\n\n## A second pass\n\nA review that follows a fix round reads the diff of the fix, not the diff of the change.\n\nThe rest of the code was reviewed once, by this phase, and has not changed since. Reading it\nagain produces the same findings, which were either acted on or recorded as `should fix` and\ndeliberately left — and re-reporting something the user decided to leave is how a report\nstops being read.\n\nTwo things stay whole. The blocking findings of the previous pass are checked as resolved,\neach against the code that now stands rather than against the claim that it was fixed. And a\nfix that touched a file outside its own task pulls that file into this pass, because a fix\nthat spread is exactly the case a narrow read would miss.\n\n## A second pass\n\nA review that follows a fix round reads the diff of the fix, not the diff of the change.\n\nThe rest of the code was reviewed once, by this phase, and has not changed since. Reading it\nagain produces the same findings, which were either acted on or recorded as `should fix` and\ndeliberately left — and re-reporting something the user decided to leave is how a report\nstops being read.\n\nTwo things stay whole. The blocking findings of the previous pass are checked as resolved,\neach against the code that now stands rather than against the claim that it was fixed. And a\nfix that touched a file outside its own task pulls that file into this pass, because a fix\nthat spread is exactly the case a narrow read would miss.\n\n## Completion\n\nFollow `skills\u002F_shared\u002Fphase-protocol.md`: write the artifact with its `## Handoff`, update state, notify `phase_completed` or `error`.\n\n```\nreview: 0 blocking, 2 should fix, 3 suggestions\n```\n","# review\n\nAnswer one question: is this code sound?\n\nNot whether it satisfies the specification. `verify` established that, and repeating it here\nspends a review on work already done.\n\n## Before reviewing\n\n```\nrecall each type the workflow declares, for what the last review of this area said\n```\n\nA `should fix` nobody fixed is worth raising again, and raising it as a repeat is worth more\nthan raising it as new: the second time it appears it is a pattern rather than a nit, and\nthe reader can see it was already declined once.\n\nThis recall is why `archive` writes those findings. Without it they were written on every\nchange and read on none.\n\nFindings that the change under review has since fixed are dropped silently. Reporting a\nfinding as outstanding when the code no longer has it is how a review loses its credibility.\n\n## Runs alongside verify\n\nDispatched at the same time as `verify`. Neither reads the other's report and neither\nwrites code, so they cannot interfere.\n\nDo not wait for the verification result, and do not assume it. A review is about whether\nthe code is sound, which does not change based on whether a scenario passed.\n\n## A separate agent\n\nThis phase runs in a context that never saw the code being written. The agent that wrote it\ncannot review it: the reasoning that produced a mistake is the reasoning that would have to\ncatch it, and it already agreed with itself once.\n\nThe model is at least as strong as the one that implemented, per `docs\u002Fmodels.md`. A\nreviewer weaker than the implementer approves everything, and the phase becomes ceremony.\n\n## What it reads\n\n```\nthe diff of the change\nconventions, architecture\nthe design artifact, and the apply artifact for what changed and what was run\n```\n\nThe design is read to know what was intended, including its `Out of scope` section. Work\ndeliberately excluded is not reported as missing.\n\n## What it looks for\n\n```\nconventions      does it follow docs\u002Fcode_conventions.md\ncorrectness      error handling, edge cases, resource cleanup, concurrency\ncall sites       does the new contract hold for every caller that already exists\nsimplicity       is there a materially simpler shape with the same behaviour\nduplication      does this already exist in the codebase\ncoupling         does it reach past the boundaries the architecture draws\nsecurity         input handling, authorisation, secrets, injection surfaces\nreadability      will this be understood by someone who was not here\n```\n\n`call sites` is the one that needs looking up rather than reading. A modified signature, a\nchanged return type, a helper whose accepted input narrowed: the diff shows the change and\nnot the twelve places that depend on it. Trace them.\n\n```\nchanged    helper accepts a string\ncallers    one worker passes a symbol\nresult     a regression that passes its own author's tests\n```\n\n`verify` asks whether the tests reach the real callers. This phase asks whether the callers\nstill work, which is a different question and is answered by reading them.\n\n## Severity\n\nEvery finding carries one, because a report where everything matters equally is a report\nnobody acts on.\n\n```\nblocking     ships a defect, a security hole, or violates the architecture\nshould fix   real problem, does not have to stop this change\nsuggestion   preference, taste, or a possible future improvement\n```\n\nOnly `blocking` findings stop the change. A phase that blocks on preferences trains the\nuser to skip the phase.\n\n## Findings\n\nA finding names the file, the line, what is wrong, and what happens as a result.\n\n```markdown\n### blocking · app\u002Fcontrollers\u002Fauth_controller.rb:42\nThe OAuth state parameter is not compared before creating the session.\nA forged callback creates a session for an account the caller does not control.\n```\n\nA finding without a consequence is an opinion. If the consequence cannot be stated, the\nfinding is a `suggestion` at most.\n\nRewriting the code is not this phase's job. Findings describe the problem; `apply` fixes it.\n\n## Conventions that were never written\n\nSome findings are real but have no rule behind them: the code works, follows every written\nconvention, and still is not how this team writes code.\n\nReport those as a proposed addition to `docs\u002Fcode_conventions.md`, not as a defect.\n\n```markdown\n### convention · app\u002Fservices\u002Fpayment_service.rb:18\nErrors are returned as result objects here, while the rest of the codebase raises.\nNeither is in code_conventions.md.\nProposed: state which one this repository uses.\n```\n\nThey never block. `archive` carries them to memory like any other non-blocking finding, and\nthe user decides whether they become a rule.\n\nThis is how the conventions file fills in with what was only ever in someone's head. A\nconvention that exists only as taste produces the same review finding every time and is\nnever fixed, because there is nothing to fix it against.\n\n## What it does not do\n\nNo re-verification of scenarios. No new requirements. No style rewrites that\n`docs\u002Fcode_conventions.md` does not ask for.\n\nReviewing code the change did not touch produces findings nobody asked for and buries the\nones about the change.\n\n## What it writes\n\n```markdown\n## Result\n## Blocking\n## Should fix\n## Suggestions\n```\n\n## Failing\n\nBlocking findings return the change to `apply` with the findings attached. Only the tasks\nowning the affected files are re-dispatched.\n\n`should fix` and `suggestion` findings are recorded and do not block. `archive` carries\nthem into memory under `alfred\u002Farea\u002F{area}\u002Freview-findings`, which this phase recalls on\nthe next change touching that area — see `Before reviewing`.\n\n## A second pass\n\nA review that follows a fix round reads the diff of the fix, not the diff of the change.\n\nThe rest of the code was reviewed once, by this phase, and has not changed since. Reading it\nagain produces the same findings, which were either acted on or recorded as `should fix` and\ndeliberately left — and re-reporting something the user decided to leave is how a report\nstops being read.\n\nTwo things stay whole. The blocking findings of the previous pass are checked as resolved,\neach against the code that now stands rather than against the claim that it was fixed. And a\nfix that touched a file outside its own task pulls that file into this pass, because a fix\nthat spread is exactly the case a narrow read would miss.\n\n## A second pass\n\nA review that follows a fix round reads the diff of the fix, not the diff of the change.\n\nThe rest of the code was reviewed once, by this phase, and has not changed since. Reading it\nagain produces the same findings, which were either acted on or recorded as `should fix` and\ndeliberately left — and re-reporting something the user decided to leave is how a report\nstops being read.\n\nTwo things stay whole. The blocking findings of the previous pass are checked as resolved,\neach against the code that now stands rather than against the claim that it was fixed. And a\nfix that touched a file outside its own task pulls that file into this pass, because a fix\nthat spread is exactly the case a narrow read would miss.\n\n## Completion\n\nFollow `skills\u002F_shared\u002Fphase-protocol.md`: write the artifact with its `## Handoff`, update state, notify `phase_completed` or `error`.\n\n```\nreview: 0 blocking, 2 should fix, 3 suggestions\n```\n",{"mode":23,"name":5,"next":24,"agent":26,"skippable":19},"auto",[25],"archive","separate_from_author","main","e68ffe68ac604c91a9738f0ce2acc1c7585f88f2","skills\u002Freview","https:\u002F\u002Fgithub.com\u002FmarkosAMO\u002FAlfred","https:\u002F\u002Fgithub.com\u002FmarkosAMO","marmoscoso1@gmail.com","Dev","2026-10-13 14:30:03",{"source":7,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add markosAMO\u002FAlfred --skill review",{"tool":41,"command":42},"bunx","bunx skills add markosAMO\u002FAlfred --skill review",{"tool":44,"command":45},"pnpm","pnpm dlx skills add markosAMO\u002FAlfred --skill review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FmarkosAMO\u002FAlfred\u002Fblob\u002Fmain\u002Fskills\u002Freview\u002FSKILL.md",true,[],[50,56,62,68,74,80],{"skillNo":51,"name":52,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":18},"01M7CPAPB4796E8W31MQFMTC9N","{phase=null}","https:\u002F\u002Fgithub.com\u002FmarkosAMO\u002FAlfred\u002Fblob\u002Fmain\u002Ftemplates\u002Fworkflow\u002Fskills\u002Fexample\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M7CPAMS85JH7H8X17G9PM3YB","verify","https:\u002F\u002Fgithub.com\u002FmarkosAMO\u002FAlfred\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M7CPAK5CR387ZSMVAH47CRW4","tasks","https:\u002F\u002Fgithub.com\u002FmarkosAMO\u002FAlfred\u002Fblob\u002Fmain\u002Fskills\u002Ftasks\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7CPAHZ9ZD1DNM3S5PS2RS9E","spec","https:\u002F\u002Fgithub.com\u002FmarkosAMO\u002FAlfred\u002Fblob\u002Fmain\u002Fskills\u002Fspec\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7CPAF9ETJMQVXT4Q4TJQ2HN","research","https:\u002F\u002Fgithub.com\u002FmarkosAMO\u002FAlfred\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7CPADA4J371APS3SESABC7M","refine","https:\u002F\u002Fgithub.com\u002FmarkosAMO\u002FAlfred\u002Fblob\u002Fmain\u002Fskills\u002Frefine\u002FSKILL.md",[],[]]