[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B3HT2S1ZKJ8NH428CCKHDK":3,"skill-same:01M7B3HT2S1ZKJ8NH428CCKHDK":45},{"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":27,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7B3HT2S1ZKJ8NH428CCKHDK","reviewing-code",null,"Use when reading a diff or pull request for defects, when acting as the reviewer on a change you did not write, or when review feedback arrives on your own change.","vadimvitvickiy\u002Fvv-agent-kit","vadimvitvickiy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5019512?v=4","01M7B3ABRYF7KHBCDW6GB2XH0C","Vadim Vitvitskii","01M7B3ABSZYG9MXP1CC7BQYM25",0,"MIT","https:\u002F\u002Fgithub.com\u002Fvadimvitvickiy\u002Fvv-agent-kit\u002Fblob\u002Fmain\u002Fskills\u002Freviewing-code\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: reviewing-code\ndescription: Use when reading a diff or pull request for defects, when acting as the reviewer on a change you did not write, or when review feedback arrives on your own change.\n---\n\n# Reviewing code\n\n**A review exists to catch what the author could not see.** Not to show diligence or produce a list.\nWhat you bring is that you do not share the author's assumptions.\n\n## Ground rules\n\n- **The reviewer does not fix.** A review carrying a patch gets read as a patch, and its findings are\n  never read. Enforce with read-only tools where possible — `vvkit-swift:swift-reviewer` sets `tools`\n  for this reason.\n- **Scope is the diff.** Read whatever context you need; report only on touched lines. Pre-existing\n  problems bury this change's findings. **Exception:** the diff makes an existing defect reachable —\n  a dead path now called, an input no longer validated upstream.\n- An empty diff: say so and stop. Reviewing the whole repo instead is a task nobody asked for.\n\n## Severity is consequence, not confidence\n\n| Bucket | Meaning |\n|-|-|\n| Critical | Ships broken: data loss, a crash on a reachable path, a security or privacy hole |\n| Important | Works today, fails on a plausible input, on another platform, or under concurrency |\n| Minor | Correct but will mislead the next reader, or violates a stated convention |\n| Optional | Taste. Kept under its own heading, never interleaved with the three above |\n\nMixed with taste, the reader calibrates on the weakest item and skims the Critical with it.\n\n## Every finding names a location and a failure\n\n- Cite `file:line`. A finding without a location gets skipped, however right.\n- State **what input or state produces what wrong result**. No breaking input means a preference —\n  Optional. \"Add tests\" or \"add docs\" counts only when it names the uncovered behavior.\n- Two sentences: what breaks and when, then the smallest fix in words, not a patch. Longer only when\n  the evidence needs it; never drop a real finding to stay short.\n\n## What to hunt first\n\nCorrectness before convention:\n\n- **Absence** — a value assumed present: a force-unwrap, a non-null assertion, an assumed index, a\n  default hiding a missing case.\n- **Lifetime** — acquired, not released: a retain cycle, an observer or timer never torn down, a\n  subscription outliving its owner.\n- **Shared state** — non-atomic read-modify-write, initialization reachable from two threads, mutable\n  state crossing an isolation boundary.\n- **Trust boundaries** — outside input reaching a query, shell, path or template unescaped; a handler\n  with no authorization, or one checking who the caller is but not what they own; a secret in code or\n  logs. Confirm the input is attacker-controlled and reachable first — where the framework escapes it,\n  it is noise.\n- **Contracts** — a changed API, schema, wire format, persisted field or event that something deployed\n  still reads. A rename is breaking even when every caller in this repo was updated.\n- **Counterfeit values** — another layer's type hand-built from data that did not come from there, its\n  invented fields read downstream as real. Fix: an entry point taking the data's own type.\n- **Swallowed failure** — an error discarded, a result ignored, a plausible empty value instead of a\n  failure.\n- **Remote calls** — no timeout, a retry around a non-idempotent operation, a retry loop with no cap.\n- **Boundaries** — first, last, empty, maximum, negative.\n- **Behavior changing without a test** — `vvkit:writing-tests` decides whether one is owed.\n\nConvention after, and only where established — `vvkit:writing-comments` for over-commented diffs.\n\n## Review against the requirements\n\n- A plan, design or ticket is input. Check everything it asks for is present; flag every deviation for\n  the author to confirm. A problem in the plan itself: say so.\n- Where the design is silent, judge by what a reasonable user would expect, graded by effect.\n- Before the verdict, list each behavior you set aside as outside the requirements, one line with the\n  reason. The author rules on each.\n\n## Finding nothing is a result\n\n- Say so plainly. Manufactured findings teach the author to skim, and the next Critical gets skimmed.\n- Do not imply a check that never ran. A PR description is context, not proof; a limit on what you\n  could verify gets one sentence.\n\n## Output shape\n\n```\n## Critical\n- path\u002Fto\u002FFile.ext:42 — what breaks, and under what conditions\n\n## Important\n- path\u002Fto\u002FOther.ext:17 — what breaks, and under what conditions\n\n## Minor\n- ...\n\n## Optional\n- ...\n```\n\n- Then which findings block, and a verdict: ready, not ready, or ready with named fixes.\n- That is the whole review: it opens on the first finding — no introduction, praise, recap, checklist\n  or closing summary. Empty buckets are left out; Optional holds at most two. A clean diff gets one\n  line saying so, then the verdict.\n- **On a re-review, update the earlier findings rather than restating them.** A finding fixed or\n  rebutted stays closed without new evidence.\n\n## Asking for a review\n\nRequest one after substantial work, and always before merging to the default branch. Give the\nreviewer what it cannot infer, and none of your reasoning:\n\n- **What was built** and **what it should do** — the plan, design or ticket.\n- **The exact range**: from the start commit or `git merge-base \u003Cbase> HEAD` to `HEAD`. Never\n  `HEAD~1` for multi-commit work.\n- **Read-only.** `git show`, `git diff`, `git log`; never move `HEAD` or touch the working tree.\n- **No sub-reviewers.** One seat; a diff too large for one pass is reviewed in passes, and says so.\n\nThen fix Critical at once, Important before moving on, and record Minor.\n\n## When you are the author\n\nA finding is a claim, and gets the same scrutiny as any claim.\n\n- **Clarify every unclear item before implementing any** — items are often related.\n- **Check each against the code.** Does it break behavior? Does the current form exist for a reason —\n  a platform floor, a compatibility constraint, a decision the human made?\n- **Grep before building it \"properly\".** An unused path gets deleted, not completed.\n- **Push back with evidence** — a test, a call site, a constraint. Wrong pushback: say what you\n  checked, and fix it.\n- **One item at a time, tested each**, blocking first.\n- **A conflict with the human's earlier decision goes to the human.**\n- Acknowledge with the change — \"Fixed: the nil path at `Parser.swift:88`\" — not \"Great catch!\".\n","# Reviewing code\n\n**A review exists to catch what the author could not see.** Not to show diligence or produce a list.\nWhat you bring is that you do not share the author's assumptions.\n\n## Ground rules\n\n- **The reviewer does not fix.** A review carrying a patch gets read as a patch, and its findings are\n  never read. Enforce with read-only tools where possible — `vvkit-swift:swift-reviewer` sets `tools`\n  for this reason.\n- **Scope is the diff.** Read whatever context you need; report only on touched lines. Pre-existing\n  problems bury this change's findings. **Exception:** the diff makes an existing defect reachable —\n  a dead path now called, an input no longer validated upstream.\n- An empty diff: say so and stop. Reviewing the whole repo instead is a task nobody asked for.\n\n## Severity is consequence, not confidence\n\n| Bucket | Meaning |\n|-|-|\n| Critical | Ships broken: data loss, a crash on a reachable path, a security or privacy hole |\n| Important | Works today, fails on a plausible input, on another platform, or under concurrency |\n| Minor | Correct but will mislead the next reader, or violates a stated convention |\n| Optional | Taste. Kept under its own heading, never interleaved with the three above |\n\nMixed with taste, the reader calibrates on the weakest item and skims the Critical with it.\n\n## Every finding names a location and a failure\n\n- Cite `file:line`. A finding without a location gets skipped, however right.\n- State **what input or state produces what wrong result**. No breaking input means a preference —\n  Optional. \"Add tests\" or \"add docs\" counts only when it names the uncovered behavior.\n- Two sentences: what breaks and when, then the smallest fix in words, not a patch. Longer only when\n  the evidence needs it; never drop a real finding to stay short.\n\n## What to hunt first\n\nCorrectness before convention:\n\n- **Absence** — a value assumed present: a force-unwrap, a non-null assertion, an assumed index, a\n  default hiding a missing case.\n- **Lifetime** — acquired, not released: a retain cycle, an observer or timer never torn down, a\n  subscription outliving its owner.\n- **Shared state** — non-atomic read-modify-write, initialization reachable from two threads, mutable\n  state crossing an isolation boundary.\n- **Trust boundaries** — outside input reaching a query, shell, path or template unescaped; a handler\n  with no authorization, or one checking who the caller is but not what they own; a secret in code or\n  logs. Confirm the input is attacker-controlled and reachable first — where the framework escapes it,\n  it is noise.\n- **Contracts** — a changed API, schema, wire format, persisted field or event that something deployed\n  still reads. A rename is breaking even when every caller in this repo was updated.\n- **Counterfeit values** — another layer's type hand-built from data that did not come from there, its\n  invented fields read downstream as real. Fix: an entry point taking the data's own type.\n- **Swallowed failure** — an error discarded, a result ignored, a plausible empty value instead of a\n  failure.\n- **Remote calls** — no timeout, a retry around a non-idempotent operation, a retry loop with no cap.\n- **Boundaries** — first, last, empty, maximum, negative.\n- **Behavior changing without a test** — `vvkit:writing-tests` decides whether one is owed.\n\nConvention after, and only where established — `vvkit:writing-comments` for over-commented diffs.\n\n## Review against the requirements\n\n- A plan, design or ticket is input. Check everything it asks for is present; flag every deviation for\n  the author to confirm. A problem in the plan itself: say so.\n- Where the design is silent, judge by what a reasonable user would expect, graded by effect.\n- Before the verdict, list each behavior you set aside as outside the requirements, one line with the\n  reason. The author rules on each.\n\n## Finding nothing is a result\n\n- Say so plainly. Manufactured findings teach the author to skim, and the next Critical gets skimmed.\n- Do not imply a check that never ran. A PR description is context, not proof; a limit on what you\n  could verify gets one sentence.\n\n## Output shape\n\n```\n## Critical\n- path\u002Fto\u002FFile.ext:42 — what breaks, and under what conditions\n\n## Important\n- path\u002Fto\u002FOther.ext:17 — what breaks, and under what conditions\n\n## Minor\n- ...\n\n## Optional\n- ...\n```\n\n- Then which findings block, and a verdict: ready, not ready, or ready with named fixes.\n- That is the whole review: it opens on the first finding — no introduction, praise, recap, checklist\n  or closing summary. Empty buckets are left out; Optional holds at most two. A clean diff gets one\n  line saying so, then the verdict.\n- **On a re-review, update the earlier findings rather than restating them.** A finding fixed or\n  rebutted stays closed without new evidence.\n\n## Asking for a review\n\nRequest one after substantial work, and always before merging to the default branch. Give the\nreviewer what it cannot infer, and none of your reasoning:\n\n- **What was built** and **what it should do** — the plan, design or ticket.\n- **The exact range**: from the start commit or `git merge-base \u003Cbase> HEAD` to `HEAD`. Never\n  `HEAD~1` for multi-commit work.\n- **Read-only.** `git show`, `git diff`, `git log`; never move `HEAD` or touch the working tree.\n- **No sub-reviewers.** One seat; a diff too large for one pass is reviewed in passes, and says so.\n\nThen fix Critical at once, Important before moving on, and record Minor.\n\n## When you are the author\n\nA finding is a claim, and gets the same scrutiny as any claim.\n\n- **Clarify every unclear item before implementing any** — items are often related.\n- **Check each against the code.** Does it break behavior? Does the current form exist for a reason —\n  a platform floor, a compatibility constraint, a decision the human made?\n- **Grep before building it \"properly\".** An unused path gets deleted, not completed.\n- **Push back with evidence** — a test, a call site, a constraint. Wrong pushback: say what you\n  checked, and fix it.\n- **One item at a time, tested each**, blocking first.\n- **A conflict with the human's earlier decision goes to the human.**\n- Acknowledge with the change — \"Fixed: the nil path at `Parser.swift:88`\" — not \"Great catch!\".\n",{"name":5,"description":7},"main","cc22a222a76add5759a2df5fadf231a758691db5","skills\u002Freviewing-code","https:\u002F\u002Fgithub.com\u002Fvadimvitvickiy\u002Fvv-agent-kit","https:\u002F\u002Fgithub.com\u002Fvadimvitvickiy","Senior iOS engineer. Architecture, SDKs and apps for iOS, tvOS and watchOS.","2026-11-13 19:10:29",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add vadimvitvickiy\u002Fvv-agent-kit --skill reviewing-code",{"tool":37,"command":38},"bunx","bunx skills add vadimvitvickiy\u002Fvv-agent-kit --skill reviewing-code",{"tool":40,"command":41},"pnpm","pnpm dlx skills add vadimvitvickiy\u002Fvv-agent-kit --skill reviewing-code","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvadimvitvickiy\u002Fvv-agent-kit\u002Fblob\u002Fmain\u002Fskills\u002Freviewing-code\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7B3JN7VG0YJ4JB8RP6HYZSJ","no-heading","Use when proving that the validator rejects a body with no H1 and a force-loading @-link.","https:\u002F\u002Fgithub.com\u002Fvadimvitvickiy\u002Fvv-agent-kit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fno-heading\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7B3JJMEW4E710ZG6HYJ7BWV","wrong-name-does-not-match-dir","Dispatches a subagent per task and reviews between each one.","https:\u002F\u002Fgithub.com\u002Fvadimvitvickiy\u002Fvv-agent-kit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fbroken-skill\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7B3JGE9MFT1HRP41YRVKN97","writing-tests","Use when adding or changing behavior, fixing a bug, or judging whether an existing or generated test earns its place.","https:\u002F\u002Fgithub.com\u002Fvadimvitvickiy\u002Fvv-agent-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-tests\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7B3JD5X32VEBDBN7HB8E17Z","writing-skills","Use when authoring or editing a skill, agent, command or hook for this kit, or when deciding whether a piece of guidance belongs in a skill at all.","https:\u002F\u002Fgithub.com\u002Fvadimvitvickiy\u002Fvv-agent-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7B3J992MZH2QVZRED0DRPD9","writing-project-instructions","Use when creating or editing a CLAUDE.md or AGENTS.md, when it has grown long, or when a rule in it also exists in an installed skill.","https:\u002F\u002Fgithub.com\u002Fvadimvitvickiy\u002Fvv-agent-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-project-instructions\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7B3J55C5WPWN20QXP9ET848","writing-logs","Use when adding or reviewing log statements, or when deciding what level a message belongs at.","https:\u002F\u002Fgithub.com\u002Fvadimvitvickiy\u002Fvv-agent-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-logs\u002FSKILL.md",[],[]]