[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75VTS6YN6082J93ASWJKENW":3,"skill-same:01M75VTS6YN6082J93ASWJKENW":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},"01M75VTS6YN6082J93ASWJKENW","simplify",null,"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`.","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\u002Fsimplify\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: simplify\ndescription: 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`.\n---\n\n# Simplify\n\nMake a change simpler and clearer without changing what it does. The bar: readable, explicit code over\nclever, compact code — would a senior engineer call this overcomplicated? Scope is the **recently\nchanged code** — the working diff (e.g. `git diff` against the branch point) unless the caller names\nfiles. This is quality-only: it does not hunt for bugs (that's `review`).\n\n## Step 0 — the invariant\n\n**Preserve functionality. Never change what the code does, only how it does it.** Every original\nfeature, output, and behavior stays intact. If a simplification would alter behavior, it is a `review`\nor implementation concern, not a simplification — stop and surface it.\n\n## Scan — three buckets\n\nLook at the changed code for:\n\n- **Structural** — nesting depth ≥ 3, functions longer than ~50 lines, nested ternaries, boolean-flag\n  parameters that select behavior, indirection that only forwards a call.\n- **Naming** — `data`\u002F`result`\u002F`temp`\u002F`foo`, names that mislead, names that imply something broader or\n  different than the thing actually is.\n- **Redundancy** — duplicated logic, dead\u002Funreachable code, unused parameters\u002Fvariables\u002Ffields,\n  over-abstraction (a helper, wrapper, or interface used in exactly one place), defensive code for\n  states an upstream invariant already makes impossible.\n\n## The deletion test\n\nFor each abstraction or layer of indirection, ask: would removing it **concentrate** complexity\n(then keep it — it's earning its keep) or merely **relocate** it (then remove it — it's not)? A\nsingle-use helper usually relocates; inline it. A wrapper that hides a genuinely complex subsystem\nbehind a small interface usually concentrates; keep it.\n\n## Two-sided guardrail\n\nSimplifying is a balance, not a race to fewer lines. Pair every \"look for\" with a \"don't\":\n\n| Look for | Don't |\n|---|---|\n| reduce nesting and indirection | introduce a nested ternary or a dense one-liner |\n| inline a single-use helper | inline a helper that names a genuinely complex step |\n| remove a redundant abstraction | remove a helpful abstraction that organizes the code |\n| consolidate duplicated logic | merge unrelated concerns into one function |\n| clearer names, fewer obvious comments | make the code harder to debug or extend |\n\nIf the \"simplified\" version is longer or harder to follow, it isn't a simplification — revert it.\n\n## Report mode\n\nWhen the caller asks for **report mode** (for example `review-pr`, reviewing someone else's pull\nrequest), do not edit anything. Run the scan, the deletion test, and the guardrail below against the\ncaller's diff, then return each candidate as a finding: `file:line`, the bucket (structural, naming,\nor redundancy), what to change, and why it is clearer. Mark every finding `Suggestion` unless the\ncomplexity hides a real defect. Skip the Process steps, which only apply when you own the code.\n\n## Process\n\n1. **Establish a baseline.** Run the tests covering the change — or, if there is no suite or it cannot\n   run, the narrowest available behavior check (build, typecheck, or lint) — and confirm it is green\n   before you start. Never fabricate a green result; if the baseline is already red for unrelated\n   reasons, note that and rely on the narrower check.\n2. **Understand before changing (Chesterton's Fence).** Work out *why* the code is shaped the way it\n   is — a guard, retry, or special case may exist for a real reason. Remove a guard only when its\n   premise is verifiable in the code you can see; if confirming it needs reasoning about whether an\n   upstream invariant truly holds, leave it and flag for `review`.\n3. **One simplification at a time** → re-run that check → keep it only if it stays green; revert\n   immediately if not. Tests are necessary but not sufficient: for a change on a path the suite does\n   not exercise, reason explicitly about input\u002Foutput equivalence — error paths, ordering, side\n   effects, short-circuit evaluation — before keeping it.\n4. **Tests are out of scope.** Never edit a test to make it pass — a breaking test means behavior\n   changed, so revert the simplification, not the test. Do not refactor, consolidate, or delete tests\n   or fixtures even when they look redundant; that silently weakens coverage.\n5. **Keep the simplify diff separate** from feature\u002Ffix changes, so a reviewer reads pure refactor.\n6. **Verify functionality preserved** at the end: the baseline check is green and you have reasoned\n   about any untested paths you touched.\n\n## Red flags\n\n- The simplified code is longer, or harder to follow, than before.\n- Editing, consolidating, or deleting a test or fixture (tests are out of scope).\n- Calling behavior \"unchanged\" from a passing suite alone, on code the suite does not exercise.\n- Removing an abstraction or guard without applying the deletion test \u002F Chesterton's Fence.\n- Touching code outside the working diff (\"while I'm here…\").\n- Optimizing for fewer lines at the cost of clarity.\n\n## Verification checklist\n\n- [ ] The baseline check (tests for the changed code, or build\u002Ftypecheck\u002Flint) is green before and after — never a fabricated green.\n- [ ] For any change on a path the suite does not cover, I reasoned about input\u002Foutput equivalence, not just \"tests pass\".\n- [ ] No test or fixture was edited, consolidated, or deleted — tests stayed out of scope.\n- [ ] Every removed abstraction\u002Fguard passed the deletion test (and Chesterton's Fence for guards).\n- [ ] The change stayed within the working diff.\n- [ ] The diff is genuinely clearer — not merely shorter.\n","# Simplify\n\nMake a change simpler and clearer without changing what it does. The bar: readable, explicit code over\nclever, compact code — would a senior engineer call this overcomplicated? Scope is the **recently\nchanged code** — the working diff (e.g. `git diff` against the branch point) unless the caller names\nfiles. This is quality-only: it does not hunt for bugs (that's `review`).\n\n## Step 0 — the invariant\n\n**Preserve functionality. Never change what the code does, only how it does it.** Every original\nfeature, output, and behavior stays intact. If a simplification would alter behavior, it is a `review`\nor implementation concern, not a simplification — stop and surface it.\n\n## Scan — three buckets\n\nLook at the changed code for:\n\n- **Structural** — nesting depth ≥ 3, functions longer than ~50 lines, nested ternaries, boolean-flag\n  parameters that select behavior, indirection that only forwards a call.\n- **Naming** — `data`\u002F`result`\u002F`temp`\u002F`foo`, names that mislead, names that imply something broader or\n  different than the thing actually is.\n- **Redundancy** — duplicated logic, dead\u002Funreachable code, unused parameters\u002Fvariables\u002Ffields,\n  over-abstraction (a helper, wrapper, or interface used in exactly one place), defensive code for\n  states an upstream invariant already makes impossible.\n\n## The deletion test\n\nFor each abstraction or layer of indirection, ask: would removing it **concentrate** complexity\n(then keep it — it's earning its keep) or merely **relocate** it (then remove it — it's not)? A\nsingle-use helper usually relocates; inline it. A wrapper that hides a genuinely complex subsystem\nbehind a small interface usually concentrates; keep it.\n\n## Two-sided guardrail\n\nSimplifying is a balance, not a race to fewer lines. Pair every \"look for\" with a \"don't\":\n\n| Look for | Don't |\n|---|---|\n| reduce nesting and indirection | introduce a nested ternary or a dense one-liner |\n| inline a single-use helper | inline a helper that names a genuinely complex step |\n| remove a redundant abstraction | remove a helpful abstraction that organizes the code |\n| consolidate duplicated logic | merge unrelated concerns into one function |\n| clearer names, fewer obvious comments | make the code harder to debug or extend |\n\nIf the \"simplified\" version is longer or harder to follow, it isn't a simplification — revert it.\n\n## Report mode\n\nWhen the caller asks for **report mode** (for example `review-pr`, reviewing someone else's pull\nrequest), do not edit anything. Run the scan, the deletion test, and the guardrail below against the\ncaller's diff, then return each candidate as a finding: `file:line`, the bucket (structural, naming,\nor redundancy), what to change, and why it is clearer. Mark every finding `Suggestion` unless the\ncomplexity hides a real defect. Skip the Process steps, which only apply when you own the code.\n\n## Process\n\n1. **Establish a baseline.** Run the tests covering the change — or, if there is no suite or it cannot\n   run, the narrowest available behavior check (build, typecheck, or lint) — and confirm it is green\n   before you start. Never fabricate a green result; if the baseline is already red for unrelated\n   reasons, note that and rely on the narrower check.\n2. **Understand before changing (Chesterton's Fence).** Work out *why* the code is shaped the way it\n   is — a guard, retry, or special case may exist for a real reason. Remove a guard only when its\n   premise is verifiable in the code you can see; if confirming it needs reasoning about whether an\n   upstream invariant truly holds, leave it and flag for `review`.\n3. **One simplification at a time** → re-run that check → keep it only if it stays green; revert\n   immediately if not. Tests are necessary but not sufficient: for a change on a path the suite does\n   not exercise, reason explicitly about input\u002Foutput equivalence — error paths, ordering, side\n   effects, short-circuit evaluation — before keeping it.\n4. **Tests are out of scope.** Never edit a test to make it pass — a breaking test means behavior\n   changed, so revert the simplification, not the test. Do not refactor, consolidate, or delete tests\n   or fixtures even when they look redundant; that silently weakens coverage.\n5. **Keep the simplify diff separate** from feature\u002Ffix changes, so a reviewer reads pure refactor.\n6. **Verify functionality preserved** at the end: the baseline check is green and you have reasoned\n   about any untested paths you touched.\n\n## Red flags\n\n- The simplified code is longer, or harder to follow, than before.\n- Editing, consolidating, or deleting a test or fixture (tests are out of scope).\n- Calling behavior \"unchanged\" from a passing suite alone, on code the suite does not exercise.\n- Removing an abstraction or guard without applying the deletion test \u002F Chesterton's Fence.\n- Touching code outside the working diff (\"while I'm here…\").\n- Optimizing for fewer lines at the cost of clarity.\n\n## Verification checklist\n\n- [ ] The baseline check (tests for the changed code, or build\u002Ftypecheck\u002Flint) is green before and after — never a fabricated green.\n- [ ] For any change on a path the suite does not cover, I reasoned about input\u002Foutput equivalence, not just \"tests pass\".\n- [ ] No test or fixture was edited, consolidated, or deleted — tests stayed out of scope.\n- [ ] Every removed abstraction\u002Fguard passed the deletion test (and Chesterton's Fence for guards).\n- [ ] The change stayed within the working diff.\n- [ ] The diff is genuinely clearer — not merely shorter.\n",{"name":5,"description":7},"main","5ab51c2d8af79f04294f91621a5b65e21f39dd53","skills\u002Fsimplify",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 simplify",{"tool":39,"command":40},"bunx","bunx skills add ronaknnathani\u002Frelay --skill simplify",{"tool":42,"command":43},"pnpm","pnpm dlx skills add ronaknnathani\u002Frelay --skill simplify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fronaknnathani\u002Frelay\u002Fblob\u002Fmain\u002Fskills\u002Fsimplify\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},"01M75VTN6XNXD2M1S84ZYTSEXT","review","Review a change for correctness, quality, and guideline compliance using a library of specialized reviewer roles. Use before opening a PR, after finishing a chunk of work, or to review an existing PR. Two output modes — a local severity-ranked report for a fix loop (default), or inline GitHub comments (--comment). Scores every finding for confidence, filters the noise, and delegates each role adversarially.","https:\u002F\u002Fgithub.com\u002Fronaknnathani\u002Frelay\u002Fblob\u002Fmain\u002Fskills\u002Freview\u002FSKILL.md",[],[]]