[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C8JRTEXPJK8YVFJQ7SQ93J":3,"skill-same:01M7C8JRTEXPJK8YVFJQ7SQ93J":58},{"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},"01M7C8JRTEXPJK8YVFJQ7SQ93J","spec-mining-edho-ferdian",null,"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.","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.agents\u002Fskills\u002Fspec-mining-edho-ferdian\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: spec-mining-edho-ferdian\ndescription: >-\n  Extract behavioural specs from a codebase with none: WHEN\u002FTHEN\n  requirements and invariants, each anchored to the code that enforces it,\n  unclear behaviour recorded as uncertainty. Use for \"ekstrak spec\", \"buat\n  spec dari kode\", \"reverse-engineer the spec\", \"repo ini tidak ada\n  dokumentasi\", or a missing BEHAVIOR_SPEC in dev-kickoff.\nmetadata:\n  last_reviewed: \"2026-10-07\"\n---\n\n# Spec Mining — Edho Ferdian Mode (Skill Edition) · v1.0\n\nYou are mining behavior out of code that was never written down. The code is\nground truth for *what it does*; it is not ground truth for *what it should\ndo* — that distinction matters every time you're tempted to write a confident\nRequirement from a guess. A spec that invents behavior is worse than no spec:\nit becomes a lie the next engineer trusts.\n\n**Core philosophy**: a spec is a flat list of behavioral\nassertions, not a document organized by type. Every behavior is either a\n**Requirement** (triggered: WHEN → THEN) or an **Invariant** (always true).\nNo type-classification chapters. Machine-readable metadata lives in HTML\ncomments. Full format spec: `references\u002Fspec-format.md`.\n\n**Note:** this skill does not depend on or\nwrite to OpenSpec. A tool-agnostic alternative approach would write\n`openspec\u002Fspecs\u002F\u003Ccapability>\u002Fspec.md` in OpenSpec's delta-tooling format\ninstead. This skill writes to\n`\u002Fproject-memory\u002Fmined-specs\u002F\u003Ccapability>.md` — landing inside the memory\nstructure `dev-kickoff-edho-ferdian` already owns, so a mined spec is\ndiscoverable the same way `01-decision-register.md` or `03-progress.md` are.\nThe block format itself (flat `### Requirement:`\u002F`### Invariant:` with HTML\ncomment metadata) is tool-agnostic and kept as-is — OpenSpec export is\nmentioned as an optional target, never a dependency (see\n`references\u002Fspec-format.md` §OpenSpec compatibility).\n\n## When to use this skill\n\n- The user enters a project with code but no written spec and asks to\n  document, extract, or reverse-engineer its behavior.\n- `dev-kickoff-edho-ferdian` Phase 0 reports `BEHAVIOR_SPEC` as a missing,\n  non-mandatory role on a brownfield repo — invoke this skill **before**\n  falling back to a manually-derived Provisional Task Plan for behavior that\n  the existing code already expresses. A `[DERIVED]` plan guesses forward;\n  mined specs read backward from what's actually there — prefer ground truth\n  over a guess whenever the code to mine exists.\n- The user says (Indonesian triggers): \"ekstrak spec\", \"buat spec dari kode\",\n  \"dokumentasikan behavior\", \"reverse-engineer the spec\", \"repo ini tidak ada\n  dokumentasi\".\n\n## The three phases\n\n```\nPhase 1  Scope discovery — group into capabilities, ask the user which to mine\nPhase 2  Sample-and-expand mining — bounded reads, never a whole module blind\nPhase 3  Emit output — flat Requirement\u002FInvariant blocks to \u002Fproject-memory\u002Fmined-specs\u002F\n```\n\nFull mechanics for Phase 1 (capability grouping, Salak clustering fallback)\nand Phase 2 (the sample→expand→defer read budget, the mining-source\nchecklist, metadata extraction, Salak-verified `depends_on`) live in\n**`references\u002Fmining-protocol.md`**. Full output format, the\nRequirement-vs-Invariant distinction table, and the metadata field reference\nlive in **`references\u002Fspec-format.md`**.\n\n## Phase 1 — Scope discovery (self-bootstrapping)\n\nThis skill does not depend on any prior onboarding step. It reads the repo\ncold.\n\n1. Read package manifests, framework configs, and entry points to derive\n   capability names (kebab-case: `orders`, `payments`, `user-auth`).\n2. If Salak is installed and exposes module clustering, use it to help group\n   capabilities instead of pure entry-point heuristics — but Salak's shipped\n   feature set does not currently include clustering (deferred in its own\n   design docs, \"adds value only on large graphs\"). Detect this at runtime\n   rather than assuming; if absent, say so once and fall back to the\n   manifest\u002Fentry-point heuristic. Never invent a Salak capability it may not\n   have. Detail: `references\u002Fmining-protocol.md` §Salak integration.\n3. **Present the capability list to the user, in Bahasa Indonesia.** Ask\n   which capabilities to mine — a large monorepo does not need every spec on\n   day one. Mine all only if the user says so explicitly.\n\n## Phase 2 — Sample-and-expand read strategy\n\nWhen more than one capability was selected, fan out on a harness with\nsub-agent delegation: delegate `spec-mining-worker-edho-ferdian` **once\nper capability, in parallel**, rather than mining each one sequentially\nin this context — capabilities read different modules and each writes its\nown independent output file, so there's nothing to lose by parallelizing\nand no aggregation step needed afterward (each worker's file stands on\nits own). On a harness with no delegation primitive, or for a single\nselected capability, mine inline per the steps below. When a worker's\nrequirement is anchored to a location that doesn't enforce it, re-run that\ncapability one tier up rather than every worker —\nconfig-hygiene-edho-ferdian's `references\u002Fharness-operation.md` §4.2.\n\nFor each selected capability:\n\n1. **Sample**: read entry files first (routers, controllers, service\n   facades, public API surfaces). Aim to cover roughly 70% of the eventual\n   Requirement\u002FInvariant assertions from this set alone before expanding.\n2. **Expand**: trace one level down the call chain from each behavior found\n   in the sample.\n3. **Stop expanding** at whichever comes first:\n   - an external system boundary (DB query, HTTP call, message queue), or\n   - 3 consecutive \"barren\" files (no new requirements found), or\n   - 15 files total read for this capability.\n4. **Defer, never drop**: anything past the stopping point is recorded with\n   an explicit `\u003C!-- deferred: \u003Creason> -->` marker at the bottom of the\n   spec file, never silently omitted.\n\nFull mining-source checklist (what counts as a behavioral assertion) and\nmetadata extraction rules: `references\u002Fmining-protocol.md`.\n\n## Phase 3 — Emit output\n\nWrite one file per mined capability to\n`\u002Fproject-memory\u002Fmined-specs\u002F\u003Ccapability>.md`, using the exact block format\nin `references\u002Fspec-format.md`: flat `### Requirement: \u003Cname>` and\n`### Invariant: \u003Cname>` blocks, each with an HTML-comment metadata block\n(`id`, `entities`, `enforced`, `test`, `depends_on`, `triggers`). Record a\n`Last verified: \u003Ccommit-hash>, \u003Cdate>` line per file.\n\nIf `\u002Fproject-memory\u002F` does not exist yet in this repo, create just the\n`mined-specs\u002F` subdirectory — do not scaffold the rest of\n`dev-kickoff-edho-ferdian`'s memory structure; that's its own skill's job.\n\n## Language routing (fixed — see skill-authoring-edho-ferdian's canonical contract)\n\nPresenting the mined capability list to the user (Phase 1) → Bahasa\nIndonesia. The mined spec files themselves (`Requirement`\u002F`Invariant`\nblocks, metadata, entity names) → English, since they are machine-facing\nartifacts read by `references\u002Fspec-format.md`-consuming tooling. Full\ncontract: `skill-authoring-edho-ferdian` §7.\n\n## Guardrails (ported verbatim — these are the integrity core)\n\n1. **Never invent behavior.** If the code doesn't clearly express a\n   contract, write `\u003C!-- uncertainty: \u003Cwhat's unclear> -->` instead of a\n   confident-sounding Requirement.\n2. **Cross-validate.** A docstring's claim is not the contract until checked\n   against its actual callers. If a function's docstring says it returns\n   `User | null` but every caller null-checks, the Requirement reflects what\n   callers rely on, not what the docstring claims.\n3. **Don't classify.** No \"Business Rules\" \u002F \"API Contracts\" chapters. Type\n   information lives in the Requirement's description text and its\n   `entities` metadata.\n4. **One capability, one spec file.** If a file would exceed ~500 lines, the\n   capability is probably too broad — split it.\n5. **Metadata is mandatory when known, never guessed.** Every Requirement\n   needs `entities` and `enforced` at minimum, or it isn't searchable — but\n   an unknown field is omitted, not filled with a guess.\n6. **Flag, don't fix.** This skill mines and reports gaps. It does not\n   refactor, does not \"fix\" inconsistent code, does not open a PR.\n7. **Record the commit.** Every `Last verified` line carries the current git\n   commit hash — the anchor for future freshness checks.\n8. **Salak metadata is clearly labeled.** `depends_on`\u002F`triggers` sourced\n   from Salak's graph (via `salak query`) are marked `[Salak-verified]`; anything from\n   call-chain inference is marked `[inferred, unverified]`. Never blend the\n   two without the label — see `references\u002Fmining-protocol.md` §Salak\n   integration for exactly how and when each applies.\n\n## Reflection — 5 gates (mandatory before handing off a mined spec file)\n\n```\nCATATAN REFLEKSI — SPEC MINING\nGate 1 (Traceability): Does every Requirement have a traceable\n       `enforced` location?                                      [PASS\u002FFAIL + reason]\nGate 2 (Docstring cross-validation): Any Requirement derived from a\n       docstring\u002Fcomment claim without checking its actual\n       callers?                                                  [.]\nGate 3 (No invention): Any behavior recorded as a confident\n       Requirement that should have been `\u003C!-- uncertainty: -->`\n       instead?                                                  [.]\nGate 4 (Provenance): Is the commit hash recorded in `Last verified`\n       for this file?                                            [.]\nGate 5 (Salak labeling): Is every Salak-sourced `depends_on`\u002F\n       `triggers` marked `[Salak-verified]`, and every inferred one\n       marked `[inferred, unverified]` — no unlabeled claim?      [.]\n```\n\nAny FAIL → fix before presenting the mined spec file. Show this block to the\nuser; it's the trust mechanism for a spec nobody asked you to write.\n\n**Done criteria:** capability list presented and confirmed · read budget per\ncapability respected (sample → expand → defer, never a blind full read) ·\noutput file(s) written to `\u002Fproject-memory\u002Fmined-specs\u002F` in the exact block\nformat · Reflection all-PASS.\n","# Spec Mining — Edho Ferdian Mode (Skill Edition) · v1.0\n\nYou are mining behavior out of code that was never written down. The code is\nground truth for *what it does*; it is not ground truth for *what it should\ndo* — that distinction matters every time you're tempted to write a confident\nRequirement from a guess. A spec that invents behavior is worse than no spec:\nit becomes a lie the next engineer trusts.\n\n**Core philosophy**: a spec is a flat list of behavioral\nassertions, not a document organized by type. Every behavior is either a\n**Requirement** (triggered: WHEN → THEN) or an **Invariant** (always true).\nNo type-classification chapters. Machine-readable metadata lives in HTML\ncomments. Full format spec: `references\u002Fspec-format.md`.\n\n**Note:** this skill does not depend on or\nwrite to OpenSpec. A tool-agnostic alternative approach would write\n`openspec\u002Fspecs\u002F\u003Ccapability>\u002Fspec.md` in OpenSpec's delta-tooling format\ninstead. This skill writes to\n`\u002Fproject-memory\u002Fmined-specs\u002F\u003Ccapability>.md` — landing inside the memory\nstructure `dev-kickoff-edho-ferdian` already owns, so a mined spec is\ndiscoverable the same way `01-decision-register.md` or `03-progress.md` are.\nThe block format itself (flat `### Requirement:`\u002F`### Invariant:` with HTML\ncomment metadata) is tool-agnostic and kept as-is — OpenSpec export is\nmentioned as an optional target, never a dependency (see\n`references\u002Fspec-format.md` §OpenSpec compatibility).\n\n## When to use this skill\n\n- The user enters a project with code but no written spec and asks to\n  document, extract, or reverse-engineer its behavior.\n- `dev-kickoff-edho-ferdian` Phase 0 reports `BEHAVIOR_SPEC` as a missing,\n  non-mandatory role on a brownfield repo — invoke this skill **before**\n  falling back to a manually-derived Provisional Task Plan for behavior that\n  the existing code already expresses. A `[DERIVED]` plan guesses forward;\n  mined specs read backward from what's actually there — prefer ground truth\n  over a guess whenever the code to mine exists.\n- The user says (Indonesian triggers): \"ekstrak spec\", \"buat spec dari kode\",\n  \"dokumentasikan behavior\", \"reverse-engineer the spec\", \"repo ini tidak ada\n  dokumentasi\".\n\n## The three phases\n\n```\nPhase 1  Scope discovery — group into capabilities, ask the user which to mine\nPhase 2  Sample-and-expand mining — bounded reads, never a whole module blind\nPhase 3  Emit output — flat Requirement\u002FInvariant blocks to \u002Fproject-memory\u002Fmined-specs\u002F\n```\n\nFull mechanics for Phase 1 (capability grouping, Salak clustering fallback)\nand Phase 2 (the sample→expand→defer read budget, the mining-source\nchecklist, metadata extraction, Salak-verified `depends_on`) live in\n**`references\u002Fmining-protocol.md`**. Full output format, the\nRequirement-vs-Invariant distinction table, and the metadata field reference\nlive in **`references\u002Fspec-format.md`**.\n\n## Phase 1 — Scope discovery (self-bootstrapping)\n\nThis skill does not depend on any prior onboarding step. It reads the repo\ncold.\n\n1. Read package manifests, framework configs, and entry points to derive\n   capability names (kebab-case: `orders`, `payments`, `user-auth`).\n2. If Salak is installed and exposes module clustering, use it to help group\n   capabilities instead of pure entry-point heuristics — but Salak's shipped\n   feature set does not currently include clustering (deferred in its own\n   design docs, \"adds value only on large graphs\"). Detect this at runtime\n   rather than assuming; if absent, say so once and fall back to the\n   manifest\u002Fentry-point heuristic. Never invent a Salak capability it may not\n   have. Detail: `references\u002Fmining-protocol.md` §Salak integration.\n3. **Present the capability list to the user, in Bahasa Indonesia.** Ask\n   which capabilities to mine — a large monorepo does not need every spec on\n   day one. Mine all only if the user says so explicitly.\n\n## Phase 2 — Sample-and-expand read strategy\n\nWhen more than one capability was selected, fan out on a harness with\nsub-agent delegation: delegate `spec-mining-worker-edho-ferdian` **once\nper capability, in parallel**, rather than mining each one sequentially\nin this context — capabilities read different modules and each writes its\nown independent output file, so there's nothing to lose by parallelizing\nand no aggregation step needed afterward (each worker's file stands on\nits own). On a harness with no delegation primitive, or for a single\nselected capability, mine inline per the steps below. When a worker's\nrequirement is anchored to a location that doesn't enforce it, re-run that\ncapability one tier up rather than every worker —\nconfig-hygiene-edho-ferdian's `references\u002Fharness-operation.md` §4.2.\n\nFor each selected capability:\n\n1. **Sample**: read entry files first (routers, controllers, service\n   facades, public API surfaces). Aim to cover roughly 70% of the eventual\n   Requirement\u002FInvariant assertions from this set alone before expanding.\n2. **Expand**: trace one level down the call chain from each behavior found\n   in the sample.\n3. **Stop expanding** at whichever comes first:\n   - an external system boundary (DB query, HTTP call, message queue), or\n   - 3 consecutive \"barren\" files (no new requirements found), or\n   - 15 files total read for this capability.\n4. **Defer, never drop**: anything past the stopping point is recorded with\n   an explicit `\u003C!-- deferred: \u003Creason> -->` marker at the bottom of the\n   spec file, never silently omitted.\n\nFull mining-source checklist (what counts as a behavioral assertion) and\nmetadata extraction rules: `references\u002Fmining-protocol.md`.\n\n## Phase 3 — Emit output\n\nWrite one file per mined capability to\n`\u002Fproject-memory\u002Fmined-specs\u002F\u003Ccapability>.md`, using the exact block format\nin `references\u002Fspec-format.md`: flat `### Requirement: \u003Cname>` and\n`### Invariant: \u003Cname>` blocks, each with an HTML-comment metadata block\n(`id`, `entities`, `enforced`, `test`, `depends_on`, `triggers`). Record a\n`Last verified: \u003Ccommit-hash>, \u003Cdate>` line per file.\n\nIf `\u002Fproject-memory\u002F` does not exist yet in this repo, create just the\n`mined-specs\u002F` subdirectory — do not scaffold the rest of\n`dev-kickoff-edho-ferdian`'s memory structure; that's its own skill's job.\n\n## Language routing (fixed — see skill-authoring-edho-ferdian's canonical contract)\n\nPresenting the mined capability list to the user (Phase 1) → Bahasa\nIndonesia. The mined spec files themselves (`Requirement`\u002F`Invariant`\nblocks, metadata, entity names) → English, since they are machine-facing\nartifacts read by `references\u002Fspec-format.md`-consuming tooling. Full\ncontract: `skill-authoring-edho-ferdian` §7.\n\n## Guardrails (ported verbatim — these are the integrity core)\n\n1. **Never invent behavior.** If the code doesn't clearly express a\n   contract, write `\u003C!-- uncertainty: \u003Cwhat's unclear> -->` instead of a\n   confident-sounding Requirement.\n2. **Cross-validate.** A docstring's claim is not the contract until checked\n   against its actual callers. If a function's docstring says it returns\n   `User | null` but every caller null-checks, the Requirement reflects what\n   callers rely on, not what the docstring claims.\n3. **Don't classify.** No \"Business Rules\" \u002F \"API Contracts\" chapters. Type\n   information lives in the Requirement's description text and its\n   `entities` metadata.\n4. **One capability, one spec file.** If a file would exceed ~500 lines, the\n   capability is probably too broad — split it.\n5. **Metadata is mandatory when known, never guessed.** Every Requirement\n   needs `entities` and `enforced` at minimum, or it isn't searchable — but\n   an unknown field is omitted, not filled with a guess.\n6. **Flag, don't fix.** This skill mines and reports gaps. It does not\n   refactor, does not \"fix\" inconsistent code, does not open a PR.\n7. **Record the commit.** Every `Last verified` line carries the current git\n   commit hash — the anchor for future freshness checks.\n8. **Salak metadata is clearly labeled.** `depends_on`\u002F`triggers` sourced\n   from Salak's graph (via `salak query`) are marked `[Salak-verified]`; anything from\n   call-chain inference is marked `[inferred, unverified]`. Never blend the\n   two without the label — see `references\u002Fmining-protocol.md` §Salak\n   integration for exactly how and when each applies.\n\n## Reflection — 5 gates (mandatory before handing off a mined spec file)\n\n```\nCATATAN REFLEKSI — SPEC MINING\nGate 1 (Traceability): Does every Requirement have a traceable\n       `enforced` location?                                      [PASS\u002FFAIL + reason]\nGate 2 (Docstring cross-validation): Any Requirement derived from a\n       docstring\u002Fcomment claim without checking its actual\n       callers?                                                  [.]\nGate 3 (No invention): Any behavior recorded as a confident\n       Requirement that should have been `\u003C!-- uncertainty: -->`\n       instead?                                                  [.]\nGate 4 (Provenance): Is the commit hash recorded in `Last verified`\n       for this file?                                            [.]\nGate 5 (Salak labeling): Is every Salak-sourced `depends_on`\u002F\n       `triggers` marked `[Salak-verified]`, and every inferred one\n       marked `[inferred, unverified]` — no unlabeled claim?      [.]\n```\n\nAny FAIL → fix before presenting the mined spec file. Show this block to the\nuser; it's the trust mechanism for a spec nobody asked you to write.\n\n**Done criteria:** capability list presented and confirmed · read budget per\ncapability respected (sample → expand → defer, never a blind full read) ·\noutput file(s) written to `\u002Fproject-memory\u002Fmined-specs\u002F` in the exact block\nformat · Reflection all-PASS.\n",{"name":5,"metadata":24,"description":7},{"last_reviewed":25},"2026-10-07","main","533d32ad55c92d40fbabe93cbe21fe048598fe5a",".agents\u002Fskills\u002Fspec-mining-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 spec-mining-edho-ferdian",{"tool":40,"command":41},"bunx","bunx skills add edhoferdian\u002FEEF --skill spec-mining-edho-ferdian",{"tool":43,"command":44},"pnpm","pnpm dlx skills add edhoferdian\u002FEEF --skill spec-mining-edho-ferdian","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fspec-mining-edho-ferdian\u002FSKILL.md",true,[48,54],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fmining-protocol.md","REFERENCE","参考文档",11550,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fspec-mining-edho-ferdian\u002Freferences\u002Fmining-protocol.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fspec-format.md",7259,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fspec-mining-edho-ferdian\u002Freferences\u002Fspec-format.md",[59,66,73,80,85,92],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"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":81,"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":82,"categories":83,"keywords":84,"publishedAt":19},"01M7C9FETATAHKG5WKPT4AP1A2","https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002Fskills\u002Fspec-mining-edho-ferdian\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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",[],[]]