[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79XVC7GZAH8AWKA3FDES4QR":3,"skill-same:01M79XVC7GZAH8AWKA3FDES4QR":53},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M79XVC7GZAH8AWKA3FDES4QR","requesting-code-review",null,"Use after each task in subagent-driven development, after completing a major feature, before merging to main, or when asked to review changes since a commit, branch or tag — pins the range, then reports Standards and Spec separately","Blind-Striker\u002Fagent-skills-and-plugins","Blind-Striker","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1965259?v=4","01M79WFXTE5PH0C1VB7B54ANMN","Deniz İrgin","01M79WFXV5KZ5GST1K8G035DM5",1,"MIT","https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Foverlays\u002Fdeniz-process\u002Frequesting-code-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: requesting-code-review\ndescription: Use after each task in subagent-driven development, after completing a major feature, before merging to main, or when asked to review changes since a commit, branch or tag — pins the range, then reports Standards and Spec separately\n---\n\n# Requesting Code Review\n\nDispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely\ncrafted context for evaluation — never your session's history.\n\n**Core principle:** Review early, review often.\n\nThe review runs on **two axes**, and they are never merged:\n\n- **Standards** — does the code conform to this repo's documented standards, and to the smell\n  baseline the reviewer template carries?\n- **Spec** — does the code faithfully implement what was actually asked for?\n\nA change can pass one and fail the other, which is the whole reason to keep them apart. See\n[Why two axes](#why-two-axes).\n\n## When to Request Review\n\n**Mandatory:**\n- After each task in subagent-driven development\n- After completing major feature\n- Before merge to main\n\n**Optional but valuable:**\n- When stuck (fresh perspective)\n- Before refactoring (baseline check)\n- After fixing complex bug\n\n**On request:** \"review the branch\", \"review since `main`\", \"review what changed since that tag\".\nSame process — the fixed point is whatever the human named.\n\n## 1. Pin the Range\n\nEvery review is a diff between `HEAD` and a fixed point. Get it from the human if they named one,\notherwise derive it:\n\n```bash\nBASE_SHA=$(git merge-base main HEAD)   # a branch; or HEAD~1, a tag, a task's starting commit\nHEAD_SHA=$(git rev-parse HEAD)\ngit log --oneline $BASE_SHA..$HEAD_SHA\n```\n\n**Confirm the range before dispatching anything:** the ref resolves (`git rev-parse`) and the diff\nis non-empty. A bad ref should fail here, in one place, not inside a subagent that has already\nburned its context discovering it.\n\nFor a branch review prefer the three-dot form (`git diff BASE...HEAD`) so the comparison is against\nthe merge-base rather than against whatever `main` has since collected.\n\n## 2. Find the Spec\n\nWhat the change was *supposed* to do, in this order:\n\n1. **The plan or task**, when one is driving the work — in subagent-driven development this is the\n   plan file, and it is the spec. When this session holds the user's own request, pass it word for\n   word beside the plan, so the Spec axis can report where the change meets the plan but not the\n   request. Stop here.\n2. **Issue references in the commit messages** (`#123`, `Closes #45`) — fetch them the way this\n   repo's issue-tracker notes describe. If that convention has not been set up here, tell the human\n   to open `\u002Fmattpocock-skills:setup-matt-pocock-skills` rather than guessing at a tracker.\n3. **A path the human passed.**\n4. **A spec or PRD** under `docs\u002F`, `specs\u002F` or `.scratch\u002F` matching the branch or feature.\n5. **Ask.** If they say there is no spec, the Spec axis reports \"no spec available\" — it does not\n   quietly grade the change against your own assumptions.\n\n## 3. Find the Standards\n\nSearch this repo for every file that documents how code should be written — `CONTRIBUTING.md`,\n`CODING_STANDARDS.md`, the agent contract, a house style file. When `CODING_STANDARDS.md` or\n`CONTRIBUTING.md` exists, it must be on the list. Pass the paths to the reviewer.\n\nYou do **not** need to supply a baseline: [code-reviewer.md](code-reviewer.md) carries a fixed set\nof code smells that applies even when a repo documents nothing. Two rules bind it, and the template\nstates them to the reviewer: **the repo overrides** — a documented standard always wins, and where\nit endorses something the baseline would flag, the smell is suppressed; and **every baseline smell\nis a judgement call**, never a hard violation.\n\n## 4. Dispatch\n\nFill the template at [code-reviewer.md](code-reviewer.md) and dispatch a `general-purpose`\nsubagent. **Placeholders:** `[DESCRIPTION]`, `[SPEC]`, `[STANDARDS_SOURCES]`, `[BASE_SHA]`,\n`[HEAD_SHA]`. Start each reviewer with a fresh context window, never a fork of this conversation.\n\n**One reviewer by default.** It holds both axes and reports them separately.\n\n**Two reviewers when the Spec axis is a genuinely different document** — an issue, a PRD, a spec\nfile that the Standards sources are not. Then send one message with two `Agent` calls, each getting\nthe range and only its own axis's material, and neither seeing the other's brief. Isolation is the\npoint: two long documents in one context is where one axis starts masking the other.\n\nWhen the plan *is* the requirements — the common case, and subagent-driven development's final\nwhole-branch review — a second subagent would read the same document twice for the same range.\nDispatch one.\n\n## 5. Read the Report\n\nWait until every reviewer has reported. Never read, merge, or act on any review while another is\nstill out, and never write your own in place of a missing one.\n\nBoth axes come back under their own headings. **Do not merge or rerank them, and do not pick a\nsingle worst issue across both.** Severity within an axis is the reviewer's job; ordering the two\naxes against each other is exactly the masking this separation exists to prevent.\n\nA merge verdict is still one decision — but it must name what each axis contributed to it.\n\nThe reviewer that holds the spec also returns a **Declined to judge** list: behaviors it set aside\nas outside the spec. Rule on every line — it stands, or it is now a finding — and say which; nothing\non it is dropped silently. Then **re-grade by effect** before acting: a finding's grade is what a\nperson using the software gets if it ships, not whether the spec names its trigger. A Minor that was\nMinor only because the spec was silent is graded again.\n\n## 6. Act on Feedback\n\n- Fix Critical issues immediately\n- Fix Important issues before proceeding\n- Note Minor issues for later\n- Push back if the reviewer is wrong, with technical reasoning\n\nHow to take the feedback — what to accept, what to question, how to push back without\ncapitulating or getting defensive — is the superpowers:receiving-code-review skill's job. It\napplies to a subagent's findings exactly as it applies to a human's, except inside an\nexecuting-plans or subagent-driven-development run, where the executor's ruling rules win.\n\n## Common Rationalizations\n\n| Excuse | Reality |\n|--------|---------|\n| \"I'll just review the diff myself instead of dispatching a reviewer\" | You're the coordinator — reviewing the diff inline burns the context window you need to keep driving the work. Dispatch a reviewer subagent: the diff and the evaluation live in its context, and only the findings come back to you. |\n| \"The reviewer needs my whole session history to understand the change\" | Hand it precisely crafted context, never your session's history. That keeps the reviewer on the work product, not your thought process. |\n| \"There's no written spec, so I'll review against what I think it should do\" | Then you are reviewing your own assumptions and calling it a Spec axis. Say \"no spec available\" and let the Standards axis carry the review. |\n| \"Standards findings are nitpicks next to a missing requirement\" | That ranking is the masking. Report both; a change can follow every standard and implement the wrong thing. |\n\n## Red Flags\n\n**Never:**\n- Skip review because \"it's simple\"\n- Dispatch before confirming the range resolves and is non-empty\n- Ignore Critical issues\n- Proceed with unfixed Important issues\n- Collapse the two axes into one ranked list\n- Argue with valid technical feedback\n\n**If reviewer wrong:**\n- Push back with technical reasoning\n- Show code\u002Ftests that prove it works\n- Request clarification\n\n## Why two axes\n\nA change can pass one axis and fail the other:\n\n- Code that follows every standard but implements the wrong thing → **Standards pass, Spec fail.**\n- Code that does exactly what was asked but breaks the project's conventions → **Spec pass,\n  Standards fail.**\n\nReporting them separately stops one from masking the other.\n\nSee template at: [code-reviewer.md](code-reviewer.md)\n","# Requesting Code Review\n\nDispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely\ncrafted context for evaluation — never your session's history.\n\n**Core principle:** Review early, review often.\n\nThe review runs on **two axes**, and they are never merged:\n\n- **Standards** — does the code conform to this repo's documented standards, and to the smell\n  baseline the reviewer template carries?\n- **Spec** — does the code faithfully implement what was actually asked for?\n\nA change can pass one and fail the other, which is the whole reason to keep them apart. See\n[Why two axes](#why-two-axes).\n\n## When to Request Review\n\n**Mandatory:**\n- After each task in subagent-driven development\n- After completing major feature\n- Before merge to main\n\n**Optional but valuable:**\n- When stuck (fresh perspective)\n- Before refactoring (baseline check)\n- After fixing complex bug\n\n**On request:** \"review the branch\", \"review since `main`\", \"review what changed since that tag\".\nSame process — the fixed point is whatever the human named.\n\n## 1. Pin the Range\n\nEvery review is a diff between `HEAD` and a fixed point. Get it from the human if they named one,\notherwise derive it:\n\n```bash\nBASE_SHA=$(git merge-base main HEAD)   # a branch; or HEAD~1, a tag, a task's starting commit\nHEAD_SHA=$(git rev-parse HEAD)\ngit log --oneline $BASE_SHA..$HEAD_SHA\n```\n\n**Confirm the range before dispatching anything:** the ref resolves (`git rev-parse`) and the diff\nis non-empty. A bad ref should fail here, in one place, not inside a subagent that has already\nburned its context discovering it.\n\nFor a branch review prefer the three-dot form (`git diff BASE...HEAD`) so the comparison is against\nthe merge-base rather than against whatever `main` has since collected.\n\n## 2. Find the Spec\n\nWhat the change was *supposed* to do, in this order:\n\n1. **The plan or task**, when one is driving the work — in subagent-driven development this is the\n   plan file, and it is the spec. When this session holds the user's own request, pass it word for\n   word beside the plan, so the Spec axis can report where the change meets the plan but not the\n   request. Stop here.\n2. **Issue references in the commit messages** (`#123`, `Closes #45`) — fetch them the way this\n   repo's issue-tracker notes describe. If that convention has not been set up here, tell the human\n   to open `\u002Fmattpocock-skills:setup-matt-pocock-skills` rather than guessing at a tracker.\n3. **A path the human passed.**\n4. **A spec or PRD** under `docs\u002F`, `specs\u002F` or `.scratch\u002F` matching the branch or feature.\n5. **Ask.** If they say there is no spec, the Spec axis reports \"no spec available\" — it does not\n   quietly grade the change against your own assumptions.\n\n## 3. Find the Standards\n\nSearch this repo for every file that documents how code should be written — `CONTRIBUTING.md`,\n`CODING_STANDARDS.md`, the agent contract, a house style file. When `CODING_STANDARDS.md` or\n`CONTRIBUTING.md` exists, it must be on the list. Pass the paths to the reviewer.\n\nYou do **not** need to supply a baseline: [code-reviewer.md](code-reviewer.md) carries a fixed set\nof code smells that applies even when a repo documents nothing. Two rules bind it, and the template\nstates them to the reviewer: **the repo overrides** — a documented standard always wins, and where\nit endorses something the baseline would flag, the smell is suppressed; and **every baseline smell\nis a judgement call**, never a hard violation.\n\n## 4. Dispatch\n\nFill the template at [code-reviewer.md](code-reviewer.md) and dispatch a `general-purpose`\nsubagent. **Placeholders:** `[DESCRIPTION]`, `[SPEC]`, `[STANDARDS_SOURCES]`, `[BASE_SHA]`,\n`[HEAD_SHA]`. Start each reviewer with a fresh context window, never a fork of this conversation.\n\n**One reviewer by default.** It holds both axes and reports them separately.\n\n**Two reviewers when the Spec axis is a genuinely different document** — an issue, a PRD, a spec\nfile that the Standards sources are not. Then send one message with two `Agent` calls, each getting\nthe range and only its own axis's material, and neither seeing the other's brief. Isolation is the\npoint: two long documents in one context is where one axis starts masking the other.\n\nWhen the plan *is* the requirements — the common case, and subagent-driven development's final\nwhole-branch review — a second subagent would read the same document twice for the same range.\nDispatch one.\n\n## 5. Read the Report\n\nWait until every reviewer has reported. Never read, merge, or act on any review while another is\nstill out, and never write your own in place of a missing one.\n\nBoth axes come back under their own headings. **Do not merge or rerank them, and do not pick a\nsingle worst issue across both.** Severity within an axis is the reviewer's job; ordering the two\naxes against each other is exactly the masking this separation exists to prevent.\n\nA merge verdict is still one decision — but it must name what each axis contributed to it.\n\nThe reviewer that holds the spec also returns a **Declined to judge** list: behaviors it set aside\nas outside the spec. Rule on every line — it stands, or it is now a finding — and say which; nothing\non it is dropped silently. Then **re-grade by effect** before acting: a finding's grade is what a\nperson using the software gets if it ships, not whether the spec names its trigger. A Minor that was\nMinor only because the spec was silent is graded again.\n\n## 6. Act on Feedback\n\n- Fix Critical issues immediately\n- Fix Important issues before proceeding\n- Note Minor issues for later\n- Push back if the reviewer is wrong, with technical reasoning\n\nHow to take the feedback — what to accept, what to question, how to push back without\ncapitulating or getting defensive — is the superpowers:receiving-code-review skill's job. It\napplies to a subagent's findings exactly as it applies to a human's, except inside an\nexecuting-plans or subagent-driven-development run, where the executor's ruling rules win.\n\n## Common Rationalizations\n\n| Excuse | Reality |\n|--------|---------|\n| \"I'll just review the diff myself instead of dispatching a reviewer\" | You're the coordinator — reviewing the diff inline burns the context window you need to keep driving the work. Dispatch a reviewer subagent: the diff and the evaluation live in its context, and only the findings come back to you. |\n| \"The reviewer needs my whole session history to understand the change\" | Hand it precisely crafted context, never your session's history. That keeps the reviewer on the work product, not your thought process. |\n| \"There's no written spec, so I'll review against what I think it should do\" | Then you are reviewing your own assumptions and calling it a Spec axis. Say \"no spec available\" and let the Standards axis carry the review. |\n| \"Standards findings are nitpicks next to a missing requirement\" | That ranking is the masking. Report both; a change can follow every standard and implement the wrong thing. |\n\n## Red Flags\n\n**Never:**\n- Skip review because \"it's simple\"\n- Dispatch before confirming the range resolves and is non-empty\n- Ignore Critical issues\n- Proceed with unfixed Important issues\n- Collapse the two axes into one ranked list\n- Argue with valid technical feedback\n\n**If reviewer wrong:**\n- Push back with technical reasoning\n- Show code\u002Ftests that prove it works\n- Request clarification\n\n## Why two axes\n\nA change can pass one axis and fail the other:\n\n- Code that follows every standard but implements the wrong thing → **Standards pass, Spec fail.**\n- Code that does exactly what was asked but breaks the project's conventions → **Spec pass,\n  Standards fail.**\n\nReporting them separately stops one from masking the other.\n\nSee template at: [code-reviewer.md](code-reviewer.md)\n",{"name":5,"description":7},"master","b30b1c1908dbc56a8184128f18803053d762ccb5","overlays\u002Fdeniz-process\u002Frequesting-code-review",0,"https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins","https:\u002F\u002Fgithub.com\u002FBlind-Striker","denizirgin.com","VP of Engineering - \r\n@armutcom @homeruntech @prontopro\r\n |  Speaker \r\n@CodeFiction\r\n, http:\u002F\u002Fcodefiction.tech | Developer, gamer, blogger, maiden iron fan","2026-11-13 00:23:18",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Blind-Striker\u002Fagent-skills-and-plugins --skill requesting-code-review",{"tool":39,"command":40},"bunx","bunx skills add Blind-Striker\u002Fagent-skills-and-plugins --skill requesting-code-review",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Blind-Striker\u002Fagent-skills-and-plugins --skill requesting-code-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Foverlays\u002Fdeniz-process\u002Frequesting-code-review\u002FSKILL.md",true,[47],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"code-reviewer.md","REFERENCE","参考文档",11633,"https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Foverlays\u002Fdeniz-process\u002Frequesting-code-review\u002Fcode-reviewer.md",[54,61,68,75,82,89],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M79YGWBJ52PHMSTKJ3RJ3AWR","writing-tunit-tests","Write tests in TUnit — the attributes, the async assertion model, data-driven cases, lifecycle hooks, and the parallelism rules. USE FOR writing or fixing a test in a TUnit project, translating a test idea into TUnit syntax, or reviewing TUnit test code for API mistakes. DO NOT USE FOR deciding what to test, judging whether a test is any good, or running tests.","https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Fskills\u002Fdeniz-dotnet-general\u002Fwriting-tunit-tests\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M79YGR3Y9RCRS6TD71D0KKP8","dotnet-walls","Walls for a .NET change in a repository without its own quality gates — pinned, ephemeral analyzer, format, clone and scanner commands for the verify step, their identity ratchet, and the build traps. Use during a walls preflight, or when a worker's verify step needs .NET quality gates.","https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Fskills\u002Fdeniz-dotnet-general\u002Fdotnet-walls\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M79YGFNJBST7D803NQW3SBYM","csharp-15","Write, review and modernize C# 15 (.NET 11) code correctly. Covers every C# 15 feature - collection expression arguments (`[with(...), ...]`), union types (`union`, `[Union]`, `IUnion`, custom unions), closed class hierarchies (`closed`), extension indexers, labeled `break`\u002F`continue`, non-virtual static interface members on runtimes without default interface methods, and the preview memory-safety model (`unsafe(expr)`, `safe`, requires-unsafe members). Use when code targets net11.0 or LangVersion 15\u002Fpreview, when the user mentions any of these features, when replacing marker interfaces, OneOf-style results, `goto`\u002Fflag loop exits or capacity\u002Fcomparer boilerplate, or when the build reports CS8121, CS8509, CS8655, CS8510, CS0121\u002FCS0411 on a `with(...)` element, CS9370, CS9380 or CS9363.","https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Fskills\u002Fdeniz-dotnet-general\u002Fcsharp-15\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M79YGAV031473HSX6FN87ENH","verified-waves","Run one task as verified multi-agent waves. Plans the fan-out, sends findings to fresh skeptics, keeps a ledger, and reports N of M done; small tasks stay solo.","https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Fskills\u002Fdeniz-coordination\u002Fverified-waves\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M79YG6QXNND4WRPP3GATSY8J","harness","The bundled dispatch harness, which runs a task file on worker models through OpenCode or Codex, fences their writes, escalates their asks to the operator, settles each result from git and its verify commands, and records every step in a ledger. Its commands, task file, modes and write fence, configuration, runs and their recovery, ledger and exit codes.","https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Fskills\u002Fdeniz-coordination\u002Fharness\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M79YG2P5S91SDTA5912XJ4FV","delegating-to-worker-models","Use when you hand off implementation, a plan, research a decision will rely on, or a review, and you brief the worker and check what comes back. A subagent that searches, reads in parallel, or keeps your context small is ordinary tool use. Covers what stays with you, the mechanism, assigning work by strength, the walls preflight, prompts without contradictions, the worker contract and model profiles, evidence from your own run, review, and the fix-up loop.","https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Fskills\u002Fdeniz-coordination\u002Fdelegating-to-worker-models\u002FSKILL.md",[],[]]