[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B3DW88BCWPR88RWKB32BWZ":3,"skill-same:01M7B3DW88BCWPR88RWKB32BWZ":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},"01M7B3DW88BCWPR88RWKB32BWZ","vvkit-reflecting-on-changes",null,"Use when code has just been written or modified and the work is about to be reported as done — the self-review pass over your own unstaged changes.","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\u002Fcodex\u002Fplugins\u002Fvvkit\u002Fskills\u002Fvvkit-reflecting-on-changes\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vvkit-reflecting-on-changes\ndescription: \"Use when code has just been written or modified and the work is about to be reported as done \\u2014 the self-review pass over your own unstaged changes.\"\n---\n\n# Reflecting on changes\n\n**The first version that works is rarely the one to keep.** It carries the scaffolding of how it was\nfound. Read it once more as a reader, not its author. This does not replace an independent review —\n`$vvkit-reviewing-code`.\n\n## Codex runtime\n\nLoad referenced skills by reading their SKILL.md. Surveyor, reviewer and runner\nskills are role instructions, not registered agent types or enforced tool allowlists.\nUse a generic subagent only when delegation is available and permitted; otherwise\nperform the role inline. Follow the active session's model, context and permission\nrules. User authorization takes precedence over imported workflow approval gates.\nClaude hooks and plugin commands are not active in this package. Existing\n`.claude\u002Fcontext\u002F` paths refer to project documents, not Codex configuration.\n\n## Scope: the unstaged diff\n\n```bash\ngit diff --name-only\ngit diff\n```\n\n- Staged changes are out of scope — staging is the human's mark that they looked. So is every line\n  the change did not touch.\n- Nothing unstaged, or only docs and config: say there is nothing to reflect on, and stop.\n- **Read each changed file whole.** A hunk cannot show that its new helper exists forty lines up.\n\n## What to look for, in order\n\n1. **Subtraction.** Could the change remove something instead of adding? A requirement bolted onto\n   the old shape, where reshaping it would have needed less code.\n2. **Simplification.** Repeated lines that are a loop or helper; a variable used once and named no\n   better than its expression; a conditional an early return flattens; a hand-rolled version of\n   something the language or project has.\n3. **Readability.** Nesting past three levels; a name that needs its comment. Shorter is not the\n   goal — a pass that only makes code denser made it worse.\n4. **Dead code.** Unused variables, imports, parameters, functions; commented-out attempts.\n5. **Failure paths.** An error swallowed at a boundary; outside input reaching a query, shell or path\n   unchecked.\n6. **Waste.** An allocation in a loop; two passes where one does.\n7. **Counterfeit values.** Your data hand-built into a type another part of the system owns, to\n   reuse a function. Give that function a sibling that takes your type.\n\nLeave alone what is only taste, and what the project does consistently another way.\n\n## Fix, then look again\n\n- Fix in place. Noting an improvement and leaving the code hands the reader work you already did.\n- **Report instead of fixing** anything that changes behavior or lies outside your lines — those are\n  the human's decisions.\n- Re-run the loop over what the fixes changed; a fix is new code.\n- **A pass that finds nothing ends the loop** — say so in one line.\n- **Three passes is the cap.** Still improving on the third means a shape problem; say what keeps\n  recurring.\n- Every pass that changed code gets its checks re-run — `$vvkit-verifying-changes`. An untested\n  simplification is an untested behavior change.\n\n## Before reporting done\n\n- [ ] Every changed file was read whole, after the last edit\n- [ ] The last pass found nothing, or the cap was reached and said so\n- [ ] Nothing staged and nothing outside the diff was touched\n- [ ] Tests were re-run after the last pass that changed code\n","# Reflecting on changes\n\n**The first version that works is rarely the one to keep.** It carries the scaffolding of how it was\nfound. Read it once more as a reader, not its author. This does not replace an independent review —\n`$vvkit-reviewing-code`.\n\n## Codex runtime\n\nLoad referenced skills by reading their SKILL.md. Surveyor, reviewer and runner\nskills are role instructions, not registered agent types or enforced tool allowlists.\nUse a generic subagent only when delegation is available and permitted; otherwise\nperform the role inline. Follow the active session's model, context and permission\nrules. User authorization takes precedence over imported workflow approval gates.\nClaude hooks and plugin commands are not active in this package. Existing\n`.claude\u002Fcontext\u002F` paths refer to project documents, not Codex configuration.\n\n## Scope: the unstaged diff\n\n```bash\ngit diff --name-only\ngit diff\n```\n\n- Staged changes are out of scope — staging is the human's mark that they looked. So is every line\n  the change did not touch.\n- Nothing unstaged, or only docs and config: say there is nothing to reflect on, and stop.\n- **Read each changed file whole.** A hunk cannot show that its new helper exists forty lines up.\n\n## What to look for, in order\n\n1. **Subtraction.** Could the change remove something instead of adding? A requirement bolted onto\n   the old shape, where reshaping it would have needed less code.\n2. **Simplification.** Repeated lines that are a loop or helper; a variable used once and named no\n   better than its expression; a conditional an early return flattens; a hand-rolled version of\n   something the language or project has.\n3. **Readability.** Nesting past three levels; a name that needs its comment. Shorter is not the\n   goal — a pass that only makes code denser made it worse.\n4. **Dead code.** Unused variables, imports, parameters, functions; commented-out attempts.\n5. **Failure paths.** An error swallowed at a boundary; outside input reaching a query, shell or path\n   unchecked.\n6. **Waste.** An allocation in a loop; two passes where one does.\n7. **Counterfeit values.** Your data hand-built into a type another part of the system owns, to\n   reuse a function. Give that function a sibling that takes your type.\n\nLeave alone what is only taste, and what the project does consistently another way.\n\n## Fix, then look again\n\n- Fix in place. Noting an improvement and leaving the code hands the reader work you already did.\n- **Report instead of fixing** anything that changes behavior or lies outside your lines — those are\n  the human's decisions.\n- Re-run the loop over what the fixes changed; a fix is new code.\n- **A pass that finds nothing ends the loop** — say so in one line.\n- **Three passes is the cap.** Still improving on the third means a shape problem; say what keeps\n  recurring.\n- Every pass that changed code gets its checks re-run — `$vvkit-verifying-changes`. An untested\n  simplification is an untested behavior change.\n\n## Before reporting done\n\n- [ ] Every changed file was read whole, after the last edit\n- [ ] The last pass found nothing, or the cap was reached and said so\n- [ ] Nothing staged and nothing outside the diff was touched\n- [ ] Tests were re-run after the last pass that changed code\n",{"name":5,"description":7},"main","cc22a222a76add5759a2df5fadf231a758691db5","codex\u002Fplugins\u002Fvvkit\u002Fskills\u002Fvvkit-reflecting-on-changes","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 vvkit-reflecting-on-changes",{"tool":37,"command":38},"bunx","bunx skills add vadimvitvickiy\u002Fvv-agent-kit --skill vvkit-reflecting-on-changes",{"tool":40,"command":41},"pnpm","pnpm dlx skills add vadimvitvickiy\u002Fvv-agent-kit --skill vvkit-reflecting-on-changes","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvadimvitvickiy\u002Fvv-agent-kit\u002Fblob\u002Fmain\u002Fcodex\u002Fplugins\u002Fvvkit\u002Fskills\u002Fvvkit-reflecting-on-changes\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",[],[]]