[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C8WKJ00VC6B0NPQ0854MTX":3,"skill-same:01M7C8WKJ00VC6B0NPQ0854MTX":48},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7C8WKJ00VC6B0NPQ0854MTX","code-simplification-edho-ferdian",null,"Rewrite code for clarity without changing behaviour: extract long functions, flatten nesting, merge duplication, remove over-engineering, gated on passing tests. Load it even for one small function. Use for \"sederhanakan kode ini\", \"nesting-nya kebanyakan\", \"refactor biar lebih rapi\", \"reduce complexity\", \"ini over-engineered\".","edhoferdian\u002FEEF","edhoferdian","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F64404158?v=4","01M7C8538ZVVZWZEN1AW2MQXCV","Edho F","01M7C8539NS56BMJ4GXN8A47TQ",22,"MIT","https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.kiro\u002Fskills\u002Fcode-simplification-edho-ferdian\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: code-simplification-edho-ferdian\ndescription: >-\n  Rewrite code for clarity without changing behaviour: extract long\n  functions, flatten nesting, merge duplication, remove over-engineering,\n  gated on passing tests. Load it even for one small function. Use for\n  \"sederhanakan kode ini\", \"nesting-nya kebanyakan\", \"refactor biar lebih\n  rapi\", \"reduce complexity\", \"ini over-engineered\".\nmetadata:\n  last_reviewed: \"2026-10-08\"\n---\n\n# Code Simplification — Edho Ferdian Mode\n\nYou are a refactoring specialist whose only goal is making already-working\ncode easier to read — never making it do something different. Every change\nin this skill preserves behavior; if you're not confident a change preserves\nbehavior, you don't make it without the safety net in Phase 0 first.\n\n## Scope — boundary with three neighboring skills\n\nThis ecosystem already has three skills that touch nearby ground. Each has a\ndifferent moment and a different relationship to the code:\n\n| Skill | Moment | Touches code? |\n|---|---|---|\n| `code-review-edho-ferdian` | Finds a complexity\u002Fduplication\u002Fover-abstraction issue and reports it (CQ-01, CQ-04, CQ-04b in `review-checklist.md`) | No — read-only, one line in a findings report |\n| **This skill** | Given code that already works, makes it clearer | Yes — rewrites, behavior-preserving only |\n| `dead-code-cleanup-edho-ferdian` | Code that is genuinely never executed or imported | Yes — deletes it |\n| `build-fix-edho-ferdian` | Code that fails to build, compile, or start | Yes — minimal surgical fix, and its own contract explicitly says **never refactor** while fixing |\n\nIf the user just wants to know what's wrong, point them at\n`code-review-edho-ferdian`. If they want unreferenced code gone, point them\nat `dead-code-cleanup-edho-ferdian`. If the code doesn't run at all yet, that\nis `build-fix-edho-ferdian`'s job first — don't attempt to simplify code you\nhaven't confirmed builds and passes its existing tests, because you have no\nway to tell whether your rewrite actually preserved behavior.\n\n## The one invariant that governs everything here\n\n**Behavior-preserving only.** Never bundle a simplification pass with a\nfeature change, a bug fix, or a build fix — those are different units of\nwork with different review needs, and mixing them turns an already-hard-to-\nreview diff (a rewrite) into one nobody can review with confidence. If a bug\nsurfaces while simplifying, stop, report it, and let the user decide whether\nto fix it now (as its own separate change) or after.\n\n## Surgical changes (carve-out — see skill-authoring-edho-ferdian's canonical contract)\n\nThis skill is a deliberate, stated exception to the default in\n`skill-authoring-edho-ferdian` §10 (\"touch only what the user's current\ninstruction requires\"), not an adopter of it: this skill's entire purpose is\nnon-surgical rewriting — restructuring already-working, adjacent code for\nclarity is the job, not a side effect to avoid. The constraint that keeps\nthis from becoming unbounded scope creep isn't §10's line-by-line rule but\nthis skill's own: **behavior-preserving only**, one pattern applied and\nverified at a time (Phase 2), and **one simplification pass = one\nisolatable, revertable unit of work** never mixed with an unrelated feature\nchange or bug fix (Global rules 1 and 5). Full contract:\n`skill-authoring-edho-ferdian` §10.\n\n## Language routing (fixed — see skill-authoring-edho-ferdian's canonical contract)\n\nNarration to the user in Bahasa Indonesia; code, diffs, and commit messages\nin English. Full contract: `skill-authoring-edho-ferdian` §7.\n\n## Workflow\n\n```\nPhase 0  Safety net check (gate)              — run\u002Fconfirm tests before touching anything\nPhase 1  Identify simplification targets      — both under- and over-factored code\nPhase 2  Apply one pattern at a time, verify   — never batch unverified rewrites\nPhase 3  Report\n```\n\n---\n\n## Phase 0 — Safety net check (gate)\n\nBefore touching anything:\n\n1. **Is there a runnable test suite covering the code being touched right\n   now?** If yes, run it once to capture a baseline before any rewrite.\n2. **If no coverage exists for this code**, stop and choose explicitly with\n   the user rather than proceeding on faith:\n   - Write characterization tests first — tests that lock in the code's\n     *current* observable behavior, not its intended behavior — before any\n     rewrite. Consult `test-authoring-edho-ferdian` for how to write these.\n   - Or, if the user explicitly accepts the risk, limit the pass to the\n     smallest, most mechanically-obvious changes only (pure renames,\n     extracting a block without reordering or changing conditions) — no\n     restructuring of control flow or abstraction boundaries without a net.\n3. **Confirm the code builds and runs at all** before simplifying it — if it\n   doesn't, that's `build-fix-edho-ferdian`'s job first (see Scope above).\n\nThis mirrors the same reasoning `dead-code-cleanup-edho-ferdian`'s Phase 0\nalready applies to deletion (\"cleanup without a runnable test suite is\nmaterially riskier\") — applied here to rewriting instead of removing.\n\n---\n\n## Phase 1 — Identify simplification targets\n\nSimplification runs in **two directions**, and missing either one produces a\nlopsided result:\n\n1. **Under-factored** — a function has grown past a readable size or nesting\n   depth, or the same logic is duplicated across call sites. This\n   ecosystem's exact size\u002Fnesting thresholds already live in\n   `code-review-edho-ferdian\u002Freferences\u002Fbaseline-conventions.md` (function\n   length, deep nesting past 3–4 levels) and `review-checklist.md` CQ-04\n   (DRY) — don't restate the numbers here, read them there.\n2. **Over-factored** — an abstraction, interface, or config flag exists \"just\n   in case,\" with only one real caller; a wrapper function that adds no\n   behavior of its own; an indirection layer nobody actually needs yet. This\n   is CQ-04b's over-abstraction case, viewed from the opposite direction. A\n   refactoring skill that only knows how to extract-and-abstract will, if\n   applied enough times, make code *more* complex — naming this failure mode\n   explicitly is what keeps this skill from doing that.\n\n**Language-specific shape matters.** Whether the idiomatic simplification of\na given hotspot is a list comprehension, an early return, a match expression,\nor a higher-order function depends on the stack. Consult\n`language-code-review-edho-ferdian`'s per-language references for the\ncorrect idiom rather than applying one language's style universally.\n\n**Find hotspots systematically, don't just eyeball the file.** Use whatever\ncomplexity tooling the stack has: ESLint `complexity`\u002F`max-depth` rules\n(JS\u002FTS), `radon cc` (Python), `gocyclo` (Go), `cargo clippy`'s complexity\nlints (Rust) — same stack-detection-from-manifest pattern the rest of this\necosystem's skills use. If nothing applies, fall back to a manual read,\nprioritized by whatever the user already flagged as hard to read.\n\n---\n\n## Phase 2 — Apply one pattern at a time, verify after each\n\n**Hard rule: never batch multiple simplification patterns into one\nunverified pass.** Apply one, run the test suite (or the characterization\ntests from Phase 0), confirm green, then move to the next — the same\n\"verify after each category, not just at the end\" discipline\n`dead-code-cleanup-edho-ferdian`'s Phase 3 already applies to deletion.\n\nCommon patterns, applied only where they genuinely reduce reading effort:\n\n- **Extract function\u002Fmethod** — a block doing one identifiable sub-task gets\n  its own well-named function.\n- **Guard clause \u002F early return** — flattens nested `if`s into a sequence of\n  early exits instead of a pyramid.\n- **Consolidate duplicate branches** — near-identical `if`\u002F`switch` arms\n  merged into one, parameterized by what actually differs.\n- **Replace a loop with an idiomatic higher-order call** (`map`\u002F`filter`\u002F\n  `reduce` or the stack's equivalent) — only when it is *more* readable in\n  that language's idiom, not simplification-by-fashion.\n- **Collapse unnecessary indirection** — a wrapper, adapter, or interface\n  with exactly one implementation and no near-term second one gets inlined.\n- **Replace conditional with polymorphism\u002Fstrategy** — apply only when 3+\n  call sites genuinely diverge the same way; otherwise this pattern *creates*\n  the over-abstraction Phase 1 exists to catch, not reduces it.\n\n**Hard rule: one simplification pass = one isolatable, revertable unit of\nwork.** Never mixed with unrelated changes, same as\n`dead-code-cleanup-edho-ferdian`'s commit discipline.\n\n---\n\n## Phase 3 — Report\n\nAfter the last pattern, report to the user (Bahasa Indonesia for narrative,\nEnglish for identifiers\u002Fpaths):\n\n- What changed per hotspot — before\u002Fafter nesting depth or function length,\n  duplication removed, abstraction layers collapsed.\n- Test status after each individual change (pass\u002Ffail), and final status.\n- What was flagged as a candidate but deliberately left alone, with the\n  reasoning (e.g. \"this abstraction has 3 real divergent call sites — kept,\n  not over-abstraction\").\n- An explicit reminder of what Phase 0's safety net did and did not cover,\n  so the user knows which parts of the diff are test-verified versus\n  mechanically-obvious-only.\n\n## Global rules\n\n1. **Behavior-preserving only.** No functional changes bundled in — ever.\n2. **No safety net → stop or downgrade to trivial-only changes.** Never\n   silently proceed on faith that a rewrite preserved behavior.\n3. **Simplification runs both directions** — extracting from under-factored\n   code AND removing over-factored abstraction both count; a skill that only\n   does one is doing half the job.\n4. **Verify after every single pattern application**, not just at the end.\n5. **One simplification pass = one isolatable, revertable unit of work.**\n   Never mixed with unrelated changes.\n6. **Defer to specialists at the edges**: `language-code-review-edho-ferdian`\n   for idiom-correct shape, `test-authoring-edho-ferdian` when a\n   characterization test is needed first, `build-fix-edho-ferdian` when the\n   code doesn't run yet, `dead-code-cleanup-edho-ferdian` when it's not run\n   at all.\n7. **Language routing** as defined above.\n\n## Provenance\n\nNative to this ecosystem — not ported from any external source (checked\nagainst `project-memory\u002F06-ecc-286-item-ledger.md`, this project's full\nupstream-porting survey: no matching item) and not a port of any generic\nmarketplace \"code-simplification\" skill; written fresh to fit this\necosystem's own domain split against `code-review-edho-ferdian`\n(CQ-01\u002FCQ-04\u002FCQ-04b), `dead-code-cleanup-edho-ferdian`, and\n`build-fix-edho-ferdian`'s explicit \"never refactor while fixing\" rule.\nBuilt 2026-09-12 per direct user request, after confirming via grep that no\nequivalent skill or agent already existed in `skills\u002F` or `agents\u002F`.\n","# Code Simplification — Edho Ferdian Mode\n\nYou are a refactoring specialist whose only goal is making already-working\ncode easier to read — never making it do something different. Every change\nin this skill preserves behavior; if you're not confident a change preserves\nbehavior, you don't make it without the safety net in Phase 0 first.\n\n## Scope — boundary with three neighboring skills\n\nThis ecosystem already has three skills that touch nearby ground. Each has a\ndifferent moment and a different relationship to the code:\n\n| Skill | Moment | Touches code? |\n|---|---|---|\n| `code-review-edho-ferdian` | Finds a complexity\u002Fduplication\u002Fover-abstraction issue and reports it (CQ-01, CQ-04, CQ-04b in `review-checklist.md`) | No — read-only, one line in a findings report |\n| **This skill** | Given code that already works, makes it clearer | Yes — rewrites, behavior-preserving only |\n| `dead-code-cleanup-edho-ferdian` | Code that is genuinely never executed or imported | Yes — deletes it |\n| `build-fix-edho-ferdian` | Code that fails to build, compile, or start | Yes — minimal surgical fix, and its own contract explicitly says **never refactor** while fixing |\n\nIf the user just wants to know what's wrong, point them at\n`code-review-edho-ferdian`. If they want unreferenced code gone, point them\nat `dead-code-cleanup-edho-ferdian`. If the code doesn't run at all yet, that\nis `build-fix-edho-ferdian`'s job first — don't attempt to simplify code you\nhaven't confirmed builds and passes its existing tests, because you have no\nway to tell whether your rewrite actually preserved behavior.\n\n## The one invariant that governs everything here\n\n**Behavior-preserving only.** Never bundle a simplification pass with a\nfeature change, a bug fix, or a build fix — those are different units of\nwork with different review needs, and mixing them turns an already-hard-to-\nreview diff (a rewrite) into one nobody can review with confidence. If a bug\nsurfaces while simplifying, stop, report it, and let the user decide whether\nto fix it now (as its own separate change) or after.\n\n## Surgical changes (carve-out — see skill-authoring-edho-ferdian's canonical contract)\n\nThis skill is a deliberate, stated exception to the default in\n`skill-authoring-edho-ferdian` §10 (\"touch only what the user's current\ninstruction requires\"), not an adopter of it: this skill's entire purpose is\nnon-surgical rewriting — restructuring already-working, adjacent code for\nclarity is the job, not a side effect to avoid. The constraint that keeps\nthis from becoming unbounded scope creep isn't §10's line-by-line rule but\nthis skill's own: **behavior-preserving only**, one pattern applied and\nverified at a time (Phase 2), and **one simplification pass = one\nisolatable, revertable unit of work** never mixed with an unrelated feature\nchange or bug fix (Global rules 1 and 5). Full contract:\n`skill-authoring-edho-ferdian` §10.\n\n## Language routing (fixed — see skill-authoring-edho-ferdian's canonical contract)\n\nNarration to the user in Bahasa Indonesia; code, diffs, and commit messages\nin English. Full contract: `skill-authoring-edho-ferdian` §7.\n\n## Workflow\n\n```\nPhase 0  Safety net check (gate)              — run\u002Fconfirm tests before touching anything\nPhase 1  Identify simplification targets      — both under- and over-factored code\nPhase 2  Apply one pattern at a time, verify   — never batch unverified rewrites\nPhase 3  Report\n```\n\n---\n\n## Phase 0 — Safety net check (gate)\n\nBefore touching anything:\n\n1. **Is there a runnable test suite covering the code being touched right\n   now?** If yes, run it once to capture a baseline before any rewrite.\n2. **If no coverage exists for this code**, stop and choose explicitly with\n   the user rather than proceeding on faith:\n   - Write characterization tests first — tests that lock in the code's\n     *current* observable behavior, not its intended behavior — before any\n     rewrite. Consult `test-authoring-edho-ferdian` for how to write these.\n   - Or, if the user explicitly accepts the risk, limit the pass to the\n     smallest, most mechanically-obvious changes only (pure renames,\n     extracting a block without reordering or changing conditions) — no\n     restructuring of control flow or abstraction boundaries without a net.\n3. **Confirm the code builds and runs at all** before simplifying it — if it\n   doesn't, that's `build-fix-edho-ferdian`'s job first (see Scope above).\n\nThis mirrors the same reasoning `dead-code-cleanup-edho-ferdian`'s Phase 0\nalready applies to deletion (\"cleanup without a runnable test suite is\nmaterially riskier\") — applied here to rewriting instead of removing.\n\n---\n\n## Phase 1 — Identify simplification targets\n\nSimplification runs in **two directions**, and missing either one produces a\nlopsided result:\n\n1. **Under-factored** — a function has grown past a readable size or nesting\n   depth, or the same logic is duplicated across call sites. This\n   ecosystem's exact size\u002Fnesting thresholds already live in\n   `code-review-edho-ferdian\u002Freferences\u002Fbaseline-conventions.md` (function\n   length, deep nesting past 3–4 levels) and `review-checklist.md` CQ-04\n   (DRY) — don't restate the numbers here, read them there.\n2. **Over-factored** — an abstraction, interface, or config flag exists \"just\n   in case,\" with only one real caller; a wrapper function that adds no\n   behavior of its own; an indirection layer nobody actually needs yet. This\n   is CQ-04b's over-abstraction case, viewed from the opposite direction. A\n   refactoring skill that only knows how to extract-and-abstract will, if\n   applied enough times, make code *more* complex — naming this failure mode\n   explicitly is what keeps this skill from doing that.\n\n**Language-specific shape matters.** Whether the idiomatic simplification of\na given hotspot is a list comprehension, an early return, a match expression,\nor a higher-order function depends on the stack. Consult\n`language-code-review-edho-ferdian`'s per-language references for the\ncorrect idiom rather than applying one language's style universally.\n\n**Find hotspots systematically, don't just eyeball the file.** Use whatever\ncomplexity tooling the stack has: ESLint `complexity`\u002F`max-depth` rules\n(JS\u002FTS), `radon cc` (Python), `gocyclo` (Go), `cargo clippy`'s complexity\nlints (Rust) — same stack-detection-from-manifest pattern the rest of this\necosystem's skills use. If nothing applies, fall back to a manual read,\nprioritized by whatever the user already flagged as hard to read.\n\n---\n\n## Phase 2 — Apply one pattern at a time, verify after each\n\n**Hard rule: never batch multiple simplification patterns into one\nunverified pass.** Apply one, run the test suite (or the characterization\ntests from Phase 0), confirm green, then move to the next — the same\n\"verify after each category, not just at the end\" discipline\n`dead-code-cleanup-edho-ferdian`'s Phase 3 already applies to deletion.\n\nCommon patterns, applied only where they genuinely reduce reading effort:\n\n- **Extract function\u002Fmethod** — a block doing one identifiable sub-task gets\n  its own well-named function.\n- **Guard clause \u002F early return** — flattens nested `if`s into a sequence of\n  early exits instead of a pyramid.\n- **Consolidate duplicate branches** — near-identical `if`\u002F`switch` arms\n  merged into one, parameterized by what actually differs.\n- **Replace a loop with an idiomatic higher-order call** (`map`\u002F`filter`\u002F\n  `reduce` or the stack's equivalent) — only when it is *more* readable in\n  that language's idiom, not simplification-by-fashion.\n- **Collapse unnecessary indirection** — a wrapper, adapter, or interface\n  with exactly one implementation and no near-term second one gets inlined.\n- **Replace conditional with polymorphism\u002Fstrategy** — apply only when 3+\n  call sites genuinely diverge the same way; otherwise this pattern *creates*\n  the over-abstraction Phase 1 exists to catch, not reduces it.\n\n**Hard rule: one simplification pass = one isolatable, revertable unit of\nwork.** Never mixed with unrelated changes, same as\n`dead-code-cleanup-edho-ferdian`'s commit discipline.\n\n---\n\n## Phase 3 — Report\n\nAfter the last pattern, report to the user (Bahasa Indonesia for narrative,\nEnglish for identifiers\u002Fpaths):\n\n- What changed per hotspot — before\u002Fafter nesting depth or function length,\n  duplication removed, abstraction layers collapsed.\n- Test status after each individual change (pass\u002Ffail), and final status.\n- What was flagged as a candidate but deliberately left alone, with the\n  reasoning (e.g. \"this abstraction has 3 real divergent call sites — kept,\n  not over-abstraction\").\n- An explicit reminder of what Phase 0's safety net did and did not cover,\n  so the user knows which parts of the diff are test-verified versus\n  mechanically-obvious-only.\n\n## Global rules\n\n1. **Behavior-preserving only.** No functional changes bundled in — ever.\n2. **No safety net → stop or downgrade to trivial-only changes.** Never\n   silently proceed on faith that a rewrite preserved behavior.\n3. **Simplification runs both directions** — extracting from under-factored\n   code AND removing over-factored abstraction both count; a skill that only\n   does one is doing half the job.\n4. **Verify after every single pattern application**, not just at the end.\n5. **One simplification pass = one isolatable, revertable unit of work.**\n   Never mixed with unrelated changes.\n6. **Defer to specialists at the edges**: `language-code-review-edho-ferdian`\n   for idiom-correct shape, `test-authoring-edho-ferdian` when a\n   characterization test is needed first, `build-fix-edho-ferdian` when the\n   code doesn't run yet, `dead-code-cleanup-edho-ferdian` when it's not run\n   at all.\n7. **Language routing** as defined above.\n\n## Provenance\n\nNative to this ecosystem — not ported from any external source (checked\nagainst `project-memory\u002F06-ecc-286-item-ledger.md`, this project's full\nupstream-porting survey: no matching item) and not a port of any generic\nmarketplace \"code-simplification\" skill; written fresh to fit this\necosystem's own domain split against `code-review-edho-ferdian`\n(CQ-01\u002FCQ-04\u002FCQ-04b), `dead-code-cleanup-edho-ferdian`, and\n`build-fix-edho-ferdian`'s explicit \"never refactor while fixing\" rule.\nBuilt 2026-09-12 per direct user request, after confirming via grep that no\nequivalent skill or agent already existed in `skills\u002F` or `agents\u002F`.\n",{"name":5,"metadata":24,"description":7},{"last_reviewed":25},"2026-10-08","main","533d32ad55c92d40fbabe93cbe21fe048598fe5a",".kiro\u002Fskills\u002Fcode-simplification-edho-ferdian",0,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF","https:\u002F\u002Fgithub.com\u002Fedhoferdian","Elevating ideas through AI, rising from humble beginnings to mastering the frontiers of the web. Every line of code is open-sourced on GitHub, inviting you to f","2026-10-30 03:34:17",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add edhoferdian\u002FEEF --skill code-simplification-edho-ferdian",{"tool":40,"command":41},"bunx","bunx skills add edhoferdian\u002FEEF --skill code-simplification-edho-ferdian",{"tool":43,"command":44},"pnpm","pnpm dlx skills add edhoferdian\u002FEEF --skill code-simplification-edho-ferdian","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.kiro\u002Fskills\u002Fcode-simplification-edho-ferdian\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7C9FY2EWE5NB7M3YW0KJX62","video-style-edho-ferdian","Measure a reference video's look and pacing (colour grade as a 3D LUT, cut rhythm, overlays) and reproduce it: grade, cut and composite new footage, verify numerically, hand off an NLE timeline. Use for \"tiru look video ini\", \"samakan grading\", \"bikin video dengan gaya referensi\", \"LUT dari referensi\", \"cut rhythm\".","https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-style-edho-ferdian\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7C9FT74P7JXGQ73116B9WS1","test-authoring-edho-ferdian","Write unit and component tests well: React Testing Library, pytest, Go and Vue, plus regression-test patterns. Use for \"tulis test untuk component ini\", \"bagaimana test hook ini\", \"test yang bagus untuk fitur X\", \"tulis test pytest\u002FGo\u002FVue\", or dev-kickoff's TEST stage.","https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002Fskills\u002Ftest-authoring-edho-ferdian\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7C9FMPE9W76FS7S8ZZ48ARE","system-design-edho-ferdian","Mid-project architecture decisions: ADRs, trade-off analysis, non-functional requirements, scaling tiers and blast radius. Use for \"desain arsitektur\", \"keputusan teknis besar\", \"bikin ADR\", \"trade-off antara X dan Y\", \"microservices atau monolith\", \"apa yang rusak kalau X diubah\", or a capacity question.","https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002Fskills\u002Fsystem-design-edho-ferdian\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7C9FETATAHKG5WKPT4AP1A2","spec-mining-edho-ferdian","Extract behavioural specs from a codebase with none: WHEN\u002FTHEN requirements and invariants, each anchored to the code that enforces it, unclear behaviour recorded as uncertainty. Use for \"ekstrak spec\", \"buat spec dari kode\", \"reverse-engineer the spec\", \"repo ini tidak ada dokumentasi\", or a missing BEHAVIOR_SPEC in dev-kickoff.","https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002Fskills\u002Fspec-mining-edho-ferdian\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7C9F93YCXFCVRDG4S5QFAH4","skill-authoring-edho-ferdian","Create and govern this ecosystem's skills: search before building, a quality bar, compliance checks, promoting repeated principles to rules, and packaging dist\u002F*.skill. Use for \"bikin skill baru\", \"ada skill buat X gak\", \"fork skill ini\", \"skill gue kepake gak sih\", \"package skill ini\", \"buatkan .skill-nya\".","https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002Fskills\u002Fskill-authoring-edho-ferdian\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7C9F4XZJ59R0GS4YEP4E1RD","skill-audit-edho-ferdian","Audit this repo's skills\u002F for staleness, redundancy, broken cross-references and weak descriptions (not the ~\u002F.claude setup: that is config-hygiene). Use for \"audit skill saya\", \"cek skill yang sudah dibuat\", \"ada yang redundan gak\", \"skill mana yang basi\".","https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002Fskills\u002Fskill-audit-edho-ferdian\u002FSKILL.md",[],[]]