[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B3GP7G33BE9QZAD30H4GAS":3,"skill-same:01M7B3GP7G33BE9QZAD30H4GAS":51},{"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},"01M7B3GP7G33BE9QZAD30H4GAS","delegating-work",null,"Use when a change is expected to span multiple files or modules, or when deciding whether to hand work to subagents, run them in parallel, or keep it in the main conversation.","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\u002Fdelegating-work\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: delegating-work\ndescription: Use when a change is expected to span multiple files or modules, or when deciding whether to hand work to subagents, run them in parallel, or keep it in the main conversation.\n---\n\n# Delegating work\n\n**Parallel readers, single writer.** Research fans out. Design decisions and edits never do.\n\n## Gate\n\n- A diff describable in one sentence — a single-file fix, a rename, a log tweak — skips all of this.\n  Test and review rules still apply.\n- **A subagent's main value is isolation, not parallelism.** Early in a session, under ~5 tool calls\n  is cheaper inline. In a large conversation, one subagent that contains verbose output — a test\n  run, a log sweep, a grep-heavy search — pays for itself.\n- **Repetitive mechanical work across many sites:** do one unit by hand, then build the script or\n  tool that matches it for the rest. Check the tool's output against the hand-done unit.\n\n## Single writer is not fresh writer\n\n- **Single writer** is concurrency: never two agents editing at once.\n- **Fresh writer per task** is context: deliberately discarding context between units.\n\n| A fresh writer per task wins | One writer holding full context wins |\n|-|-|\n| Tasks are mechanically independent | Tasks must be **consistent with each other** |\n| Verbose tool output would flood context | Judgment built up earlier still applies |\n| The brief is cheaper to write than the output | Writing the brief ≈ writing the output |\n| Accumulated drift is the risk | Cold-start divergence is the risk |\n\n- The third row decides most cases. A brief that must say what to keep, strip, and how it reads beside\n  its neighbours is already the work. **Never delegate understanding.**\n- Coherent work split across cold starts produces N variants that each restate shared context, then\n  drift.\n\n## Phases\n\n1. **Scope.** The goal, what is affected, what is out of scope.\n2. **Research — fan out.** Every applicable reader in one message, read-only, with an explicit model —\n   `vvkit:choosing-subagent-models`. Usually: prior art — `vvkit:architecture-surveyor`; any contract,\n   schema or interface touched; the spec or ticket. Several independent failures get one read-only\n   investigator each, returning root cause and proposed change — unless one fix might fix the others,\n   then investigate together.\n3. **Plan — never delegated.** Design stays where the full conversation is —\n   `vvkit:designing-changes` — and the plan is written beside it.\n4. **Implement — one writer** at any moment; executing a plan is `vvkit:planning-changes`. Never\n   parallel implementers in one working tree. Tasks the human asks to run side by side get a worktree\n   and branch each — `\u002Fvvkit:worktree` — and merge one at a time.\n5. **Verify, then review.** Build and test first. Then one independent reviewer that never saw your\n   reasoning, reading the diff itself — the one stage always worth delegating.\n\n## The spawn prompt\n\nEvery spawn carries four things; missing one is the usual cause of a useless result.\n\n1. **Objective** — the question, not the procedure. Over-prescribed steps yield shallow work.\n2. **What is ruled out**, so it does not re-derive dead ends.\n3. **Known paths** — files, symbols, line numbers.\n4. **An output contract** — exact shape and a length cap. A `file:line` or verbatim output behind every\n   claim, verified facts apart from inferences.\n\nA subagent gets no conversation history. Anything it needs is in the prompt.\n\n## Accepting a result\n\nA report is a claim about the work, not evidence. It cites locations just as fluently whether or not\nit read them.\n\n- **Read the cited `file:line` yourself** for every claim a decision rests on.\n- **Re-derive counts and outcomes from the machine** — `git diff --stat` for \"changed N places\", a\n  re-run or `vvkit:test-runner`'s exit code for \"tests pass\".\n- **High-risk conclusions need a second opinion that never saw the first** — deletion, security,\n  production config, anything the user will act on. Two independent agents, or one briefed to refute;\n  accept what both agree on or the refuter failed to break.\n\n## Common mistakes\n\n| Mistake | Why it fails |\n|-|-|\n| Fanning out implementers to go faster | Conflicting edits; writes stay serial |\n| Delegating the plan | The planner needs the full conversation |\n| Accepting a subagent's \"done\" | It reports what it intended |\n| Running the pipeline on a one-sentence change | That is what the gate is for |\n| Omitting the output contract | Unstructured results defeat the isolation |\n| Nesting subagents | Subagents cannot spawn subagents; chain from the main conversation |\n| Re-reading a result that timed out | It can double-count or truncate. Raise the timeout instead |\n| Reporting a background agent's result before it lands | You do not know what it found until the notification arrives |\n\nFrontmatter fields, tool restrictions, memory, isolation and anti-patterns:\n`references\u002Fsubagent-reference.md`.\n","# Delegating work\n\n**Parallel readers, single writer.** Research fans out. Design decisions and edits never do.\n\n## Gate\n\n- A diff describable in one sentence — a single-file fix, a rename, a log tweak — skips all of this.\n  Test and review rules still apply.\n- **A subagent's main value is isolation, not parallelism.** Early in a session, under ~5 tool calls\n  is cheaper inline. In a large conversation, one subagent that contains verbose output — a test\n  run, a log sweep, a grep-heavy search — pays for itself.\n- **Repetitive mechanical work across many sites:** do one unit by hand, then build the script or\n  tool that matches it for the rest. Check the tool's output against the hand-done unit.\n\n## Single writer is not fresh writer\n\n- **Single writer** is concurrency: never two agents editing at once.\n- **Fresh writer per task** is context: deliberately discarding context between units.\n\n| A fresh writer per task wins | One writer holding full context wins |\n|-|-|\n| Tasks are mechanically independent | Tasks must be **consistent with each other** |\n| Verbose tool output would flood context | Judgment built up earlier still applies |\n| The brief is cheaper to write than the output | Writing the brief ≈ writing the output |\n| Accumulated drift is the risk | Cold-start divergence is the risk |\n\n- The third row decides most cases. A brief that must say what to keep, strip, and how it reads beside\n  its neighbours is already the work. **Never delegate understanding.**\n- Coherent work split across cold starts produces N variants that each restate shared context, then\n  drift.\n\n## Phases\n\n1. **Scope.** The goal, what is affected, what is out of scope.\n2. **Research — fan out.** Every applicable reader in one message, read-only, with an explicit model —\n   `vvkit:choosing-subagent-models`. Usually: prior art — `vvkit:architecture-surveyor`; any contract,\n   schema or interface touched; the spec or ticket. Several independent failures get one read-only\n   investigator each, returning root cause and proposed change — unless one fix might fix the others,\n   then investigate together.\n3. **Plan — never delegated.** Design stays where the full conversation is —\n   `vvkit:designing-changes` — and the plan is written beside it.\n4. **Implement — one writer** at any moment; executing a plan is `vvkit:planning-changes`. Never\n   parallel implementers in one working tree. Tasks the human asks to run side by side get a worktree\n   and branch each — `\u002Fvvkit:worktree` — and merge one at a time.\n5. **Verify, then review.** Build and test first. Then one independent reviewer that never saw your\n   reasoning, reading the diff itself — the one stage always worth delegating.\n\n## The spawn prompt\n\nEvery spawn carries four things; missing one is the usual cause of a useless result.\n\n1. **Objective** — the question, not the procedure. Over-prescribed steps yield shallow work.\n2. **What is ruled out**, so it does not re-derive dead ends.\n3. **Known paths** — files, symbols, line numbers.\n4. **An output contract** — exact shape and a length cap. A `file:line` or verbatim output behind every\n   claim, verified facts apart from inferences.\n\nA subagent gets no conversation history. Anything it needs is in the prompt.\n\n## Accepting a result\n\nA report is a claim about the work, not evidence. It cites locations just as fluently whether or not\nit read them.\n\n- **Read the cited `file:line` yourself** for every claim a decision rests on.\n- **Re-derive counts and outcomes from the machine** — `git diff --stat` for \"changed N places\", a\n  re-run or `vvkit:test-runner`'s exit code for \"tests pass\".\n- **High-risk conclusions need a second opinion that never saw the first** — deletion, security,\n  production config, anything the user will act on. Two independent agents, or one briefed to refute;\n  accept what both agree on or the refuter failed to break.\n\n## Common mistakes\n\n| Mistake | Why it fails |\n|-|-|\n| Fanning out implementers to go faster | Conflicting edits; writes stay serial |\n| Delegating the plan | The planner needs the full conversation |\n| Accepting a subagent's \"done\" | It reports what it intended |\n| Running the pipeline on a one-sentence change | That is what the gate is for |\n| Omitting the output contract | Unstructured results defeat the isolation |\n| Nesting subagents | Subagents cannot spawn subagents; chain from the main conversation |\n| Re-reading a result that timed out | It can double-count or truncate. Raise the timeout instead |\n| Reporting a background agent's result before it lands | You do not know what it found until the notification arrives |\n\nFrontmatter fields, tool restrictions, memory, isolation and anti-patterns:\n`references\u002Fsubagent-reference.md`.\n",{"name":5,"description":7},"main","cc22a222a76add5759a2df5fadf231a758691db5","skills\u002Fdelegating-work","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 delegating-work",{"tool":37,"command":38},"bunx","bunx skills add vadimvitvickiy\u002Fvv-agent-kit --skill delegating-work",{"tool":40,"command":41},"pnpm","pnpm dlx skills add vadimvitvickiy\u002Fvv-agent-kit --skill delegating-work","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvadimvitvickiy\u002Fvv-agent-kit\u002Fblob\u002Fmain\u002Fskills\u002Fdelegating-work\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fsubagent-reference.md","REFERENCE","参考文档",5784,"https:\u002F\u002Fgithub.com\u002Fvadimvitvickiy\u002Fvv-agent-kit\u002Fblob\u002Fmain\u002Fskills\u002Fdelegating-work\u002Freferences\u002Fsubagent-reference.md",[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"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":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},"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":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},"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":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},"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":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},"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":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},"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",[],[]]