[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75VT17X3D2YV7C2NVR8C4JD":3,"skill-same:01M75VT17X3D2YV7C2NVR8C4JD":47},{"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},"01M75VT17X3D2YV7C2NVR8C4JD","plan",null,"Turn a clarified requirements artifact into a concrete, executable implementation plan — a decisive architecture blueprint and a phased build sequence with exact file paths. Use after requirements are pinned down (e.g. by `clarify`) and before writing code, whenever a multi-step change needs a design and a task breakdown. Its output feeds `implement`.","ronaknnathani\u002Frelay","ronaknnathani","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F7279934?v=4","01M75VS2S5V1DVP31PCWYA7SMA","Ronak Nathani","01M75VS2STNTX5Y5JGYQGRE0NG",44,"MIT","https:\u002F\u002Fgithub.com\u002Fronaknnathani\u002Frelay\u002Fblob\u002Fmain\u002Fskills\u002Fplan\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: plan\ndescription: Turn a clarified requirements artifact into a concrete, executable implementation plan — a decisive architecture blueprint and a phased build sequence with exact file paths. Use after requirements are pinned down (e.g. by `clarify`) and before writing code, whenever a multi-step change needs a design and a task breakdown. Its output feeds `implement`.\n---\n\n# Plan\n\nGiven a clarified requirements artifact, produce an implementation plan concrete enough that someone\nwith no prior context could execute it. The bar: exact file paths and names, one committed\narchitecture decision, and a phased build sequence `implement` consumes step by step — no abstract\nadvice, no \"add appropriate error handling\". This is a peer phase: it grounds itself in the code via\n`explore`, picks ONE approach and commits, then hands a plan to `implement`. It does **not** clarify\nrequirements (that's `clarify`, upstream) and does **not** write production code (that's `implement`,\ndownstream). It does not invoke either.\n\n## Process\n\n1. **Ground in the codebase first.** Read the clarified artifact (`clarify`'s requirements + success\n   criteria), then call `explore` (dispatch a sub-agent when available; otherwise inline) and consume\n   its **essential-files list and `file:line` citations** as the starting set for the existing\n   patterns, conventions, and integration points this work touches. Cite each finding as\n   `path\u002Fto\u002Ffile.ext:line` — the blueprint\n   is built on what's actually there, not what you assume.\n2. **Decide the architecture and commit.** Survey the realistic approaches, then pick **ONE** and\n   write the decision plus a one-paragraph rationale grounded in the patterns from step 1. Do not\n   hedge with \"Option A or B\" — a plan is a decision. Record approaches you rejected in one line each\n   only if a reader would otherwise wonder why; don't relitigate.\n3. **Choose the test seams up front.** Pick where behavior gets verified, preferring a single highest\n   seam (one integration\u002Fend-to-end point) over many low ones. Decide what's tested and what isn't,\n   and capture it in an explicit **Testing Decisions** section. New behavior gets a test; a bug fix\n   gets a test that fails without the fix.\n4. **Design the components.** For each unit of work name the file(s), its single responsibility, and\n   its dependencies on other units. Split by responsibility, not by technical layer; files that change\n   together live together; follow the established structure rather than restructuring it.\n5. **Write the Implementation Map** — every concrete create\u002Fmodify action with its exact path:\n   `Create src\u002Fx.ext` \u002F `Modify src\u002Fy.ext:120-150` \u002F `Test tests\u002Fx_test.ext`. No file is named only\n   in prose; if it changes, it's in the map.\n6. **Sequence the build into phases.** Order the work so each phase produces something verifiable,\n   following dependency order (data\u002Fcontracts → logic → wiring\u002Fconfig). Emit it as the **Build\n   Sequence** checklist below — this is the executable artifact `implement` works through.\n7. **Pin the critical details.** State the concrete error-handling behavior, state\u002Fdata shape, and\n   verification command for each phase. Add an **Out of Scope** section listing what this plan\n   deliberately does not touch, so `implement` doesn't wander.\n8. **Self-review with fresh eyes.** Walk every Success criterion in the clarified artifact and point to\n   the task that satisfies it — list and fix any gap. Scan for placeholders (TBD, TODO, \"handle edge\n   cases\", a test step with no assertion) and remove them. Confirm names\u002Fsignatures used in a later\n   task match what an earlier task defines. Fix inline; don't re-review.\n\n## Task template\n\nEach unit of work in the Build Sequence follows this shape:\n\n```markdown\n### Task N: \u003Cimperative title, no \"and\">\n- **Description:** what this builds and why it's one unit.\n- **Acceptance criteria:** 3–5 testable assertions (each checkable by a test, command, or observation).\n- **Verification:** the exact command(s) to run and the expected result.\n- **Dependencies:** task numbers this needs first (or \"none\").\n- **Files:** Create\u002FModify\u002FTest with exact paths (mirrors the Implementation Map).\n- **Size:** XS · S · M · L · XL.\n- [ ] step(s) — one concrete action each (write failing test, implement, run, commit)\n```\n\n**Break a task down if** it spans more than ~2 hours, needs 4+ acceptance criteria, touches\nindependent subsystems, or has \"and\" in the title — each of those is two tasks wearing one hat.\n\n## Red flags\n\n- Hedging between approaches instead of committing to one decision with a rationale.\n- A file named only in prose, or a path written as a placeholder rather than the real one.\n- \"Add appropriate error handling \u002F validation \u002F edge cases\" — say the concrete behavior instead.\n- A test step with no assertion, or a \"see Task N\" cross-reference instead of the actual content.\n- Missing Testing Decisions or Out of Scope sections, or many low test seams where one high one fits.\n- A Success criterion from the clarified artifact with no task that satisfies it.\n- Clarifying requirements, writing production code, or invoking `clarify`\u002F`implement` — all out of scope.\n\n## Verification checklist\n\n- [ ] Every blueprint finding cites `file:line` from a real `explore` of the codebase.\n- [ ] Exactly one architecture approach is chosen, with a grounded rationale — no hedging.\n- [ ] Test seams are chosen up front and captured in a **Testing Decisions** section.\n- [ ] The Implementation Map lists every create\u002Fmodify\u002Ftest action with an exact path.\n- [ ] The Build Sequence is a phased checklist in dependency order, each phase independently verifiable.\n- [ ] Every task fits the template and the \"break it down if\" thresholds; none has \"and\" in the title.\n- [ ] Each Success criterion in the clarified artifact maps to a task; no placeholders remain.\n- [ ] An **Out of Scope** section bounds what the plan deliberately leaves untouched.\n- [ ] The skill stayed in scope: no requirement clarification, no implementation, no downstream invocation.\n","# Plan\n\nGiven a clarified requirements artifact, produce an implementation plan concrete enough that someone\nwith no prior context could execute it. The bar: exact file paths and names, one committed\narchitecture decision, and a phased build sequence `implement` consumes step by step — no abstract\nadvice, no \"add appropriate error handling\". This is a peer phase: it grounds itself in the code via\n`explore`, picks ONE approach and commits, then hands a plan to `implement`. It does **not** clarify\nrequirements (that's `clarify`, upstream) and does **not** write production code (that's `implement`,\ndownstream). It does not invoke either.\n\n## Process\n\n1. **Ground in the codebase first.** Read the clarified artifact (`clarify`'s requirements + success\n   criteria), then call `explore` (dispatch a sub-agent when available; otherwise inline) and consume\n   its **essential-files list and `file:line` citations** as the starting set for the existing\n   patterns, conventions, and integration points this work touches. Cite each finding as\n   `path\u002Fto\u002Ffile.ext:line` — the blueprint\n   is built on what's actually there, not what you assume.\n2. **Decide the architecture and commit.** Survey the realistic approaches, then pick **ONE** and\n   write the decision plus a one-paragraph rationale grounded in the patterns from step 1. Do not\n   hedge with \"Option A or B\" — a plan is a decision. Record approaches you rejected in one line each\n   only if a reader would otherwise wonder why; don't relitigate.\n3. **Choose the test seams up front.** Pick where behavior gets verified, preferring a single highest\n   seam (one integration\u002Fend-to-end point) over many low ones. Decide what's tested and what isn't,\n   and capture it in an explicit **Testing Decisions** section. New behavior gets a test; a bug fix\n   gets a test that fails without the fix.\n4. **Design the components.** For each unit of work name the file(s), its single responsibility, and\n   its dependencies on other units. Split by responsibility, not by technical layer; files that change\n   together live together; follow the established structure rather than restructuring it.\n5. **Write the Implementation Map** — every concrete create\u002Fmodify action with its exact path:\n   `Create src\u002Fx.ext` \u002F `Modify src\u002Fy.ext:120-150` \u002F `Test tests\u002Fx_test.ext`. No file is named only\n   in prose; if it changes, it's in the map.\n6. **Sequence the build into phases.** Order the work so each phase produces something verifiable,\n   following dependency order (data\u002Fcontracts → logic → wiring\u002Fconfig). Emit it as the **Build\n   Sequence** checklist below — this is the executable artifact `implement` works through.\n7. **Pin the critical details.** State the concrete error-handling behavior, state\u002Fdata shape, and\n   verification command for each phase. Add an **Out of Scope** section listing what this plan\n   deliberately does not touch, so `implement` doesn't wander.\n8. **Self-review with fresh eyes.** Walk every Success criterion in the clarified artifact and point to\n   the task that satisfies it — list and fix any gap. Scan for placeholders (TBD, TODO, \"handle edge\n   cases\", a test step with no assertion) and remove them. Confirm names\u002Fsignatures used in a later\n   task match what an earlier task defines. Fix inline; don't re-review.\n\n## Task template\n\nEach unit of work in the Build Sequence follows this shape:\n\n```markdown\n### Task N: \u003Cimperative title, no \"and\">\n- **Description:** what this builds and why it's one unit.\n- **Acceptance criteria:** 3–5 testable assertions (each checkable by a test, command, or observation).\n- **Verification:** the exact command(s) to run and the expected result.\n- **Dependencies:** task numbers this needs first (or \"none\").\n- **Files:** Create\u002FModify\u002FTest with exact paths (mirrors the Implementation Map).\n- **Size:** XS · S · M · L · XL.\n- [ ] step(s) — one concrete action each (write failing test, implement, run, commit)\n```\n\n**Break a task down if** it spans more than ~2 hours, needs 4+ acceptance criteria, touches\nindependent subsystems, or has \"and\" in the title — each of those is two tasks wearing one hat.\n\n## Red flags\n\n- Hedging between approaches instead of committing to one decision with a rationale.\n- A file named only in prose, or a path written as a placeholder rather than the real one.\n- \"Add appropriate error handling \u002F validation \u002F edge cases\" — say the concrete behavior instead.\n- A test step with no assertion, or a \"see Task N\" cross-reference instead of the actual content.\n- Missing Testing Decisions or Out of Scope sections, or many low test seams where one high one fits.\n- A Success criterion from the clarified artifact with no task that satisfies it.\n- Clarifying requirements, writing production code, or invoking `clarify`\u002F`implement` — all out of scope.\n\n## Verification checklist\n\n- [ ] Every blueprint finding cites `file:line` from a real `explore` of the codebase.\n- [ ] Exactly one architecture approach is chosen, with a grounded rationale — no hedging.\n- [ ] Test seams are chosen up front and captured in a **Testing Decisions** section.\n- [ ] The Implementation Map lists every create\u002Fmodify\u002Ftest action with an exact path.\n- [ ] The Build Sequence is a phased checklist in dependency order, each phase independently verifiable.\n- [ ] Every task fits the template and the \"break it down if\" thresholds; none has \"and\" in the title.\n- [ ] Each Success criterion in the clarified artifact maps to a task; no placeholders remain.\n- [ ] An **Out of Scope** section bounds what the plan deliberately leaves untouched.\n- [ ] The skill stayed in scope: no requirement clarification, no implementation, no downstream invocation.\n",{"name":5,"description":7},"main","5ab51c2d8af79f04294f91621a5b65e21f39dd53","skills\u002Fplan",4,"https:\u002F\u002Fgithub.com\u002Fronaknnathani\u002Frelay","https:\u002F\u002Fgithub.com\u002Fronaknnathani","ronaknathani.com","Compute Infrastructure | Kubernetes @ LinkedIn","2026-11-06 14:25:14",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add ronaknnathani\u002Frelay --skill plan",{"tool":39,"command":40},"bunx","bunx skills add ronaknnathani\u002Frelay --skill plan",{"tool":42,"command":43},"pnpm","pnpm dlx skills add ronaknnathani\u002Frelay --skill plan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fronaknnathani\u002Frelay\u002Fblob\u002Fmain\u002Fskills\u002Fplan\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M75VVBP3R7RHF93R3RFWC3SE","write-like-me","Write or edit prose in author's voice, or check that a draft sounds like them. Use for blog posts, design and strategy docs, PR descriptions, commits and review comments, chat \u002F agent instructions, peer feedback, or any first-person writing on their behalf, and whenever an agent is producing text that will go out under their name and needs to sound like them, not like a generated reply.","https:\u002F\u002Fgithub.com\u002Fronaknnathani\u002Frelay\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-like-me\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M75VV70MDT9DZWQG1ZCA3VH6","validate","Verify a change is ready to ship by checking it against its acceptance criteria and running the repo's own quality gates in order, then report a pass\u002Ffail verdict with the exact failures. Use to decide go\u002Fno-go right before shipping — when you want a pass\u002Ffail verdict against acceptance criteria and the repo's quality gates (lint\u002Fbuild\u002Ftest), not a code critique (use `review` for that). It reports — it does not fix (route failures to `pr-fix`\u002F`implement`) and does not ship.","https:\u002F\u002Fgithub.com\u002Fronaknnathani\u002Frelay\u002Fblob\u002Fmain\u002Fskills\u002Fvalidate\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M75VV5DEBH4ZS4XDY27JGHCF","todo","Capture, list, and complete repo-scoped todos","https:\u002F\u002Fgithub.com\u002Fronaknnathani\u002Frelay\u002Fblob\u002Fmain\u002Fskills\u002Ftodo\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M75VV38NYR4V51C27WPMFG5F","tl","Manage a Relay program as the CEO-facing tech lead: shape goals and contracts, prioritize dependency-aware work, dispatch senior worker agents, and surface every decision without writing production code or merging.","https:\u002F\u002Fgithub.com\u002Fronaknnathani\u002Frelay\u002Fblob\u002Fmain\u002Fskills\u002Ftl\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M75VTY2ZTZYJ09AYP6N46FRT","stack-ship","Use only for a standalone stack explicitly launched with `relay --workflow stack-ship`; never invoke inside a tech-lead-managed Relay program. Decompose one goal into small PRs, delegate build and monitor work, surface author decisions, and auto-merge only after human approval.","https:\u002F\u002Fgithub.com\u002Fronaknnathani\u002Frelay\u002Fblob\u002Fmain\u002Fskills\u002Fstack-ship\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M75VTS6YN6082J93ASWJKENW","simplify","Reduce complexity in recently changed code — cut needless abstraction, dead code, and duplication; improve names and structure — WITHOUT changing behavior. Quality only; it does not hunt for bugs (use review for that). Use after implementing a chunk of work, before review, or whenever a diff feels more complicated than the problem it solves. Triggers on \"clean this up\" \u002F \"tidy this\" \u002F \"refactor this\" when code already exists; for an underspecified goal with no code yet, use `clarify`.","https:\u002F\u002Fgithub.com\u002Fronaknnathani\u002Frelay\u002Fblob\u002Fmain\u002Fskills\u002Fsimplify\u002FSKILL.md",[],[]]