[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C8GDKYB6K642QF25Y7XZPD":3,"skill-same:01M7C8GDKYB6K642QF25Y7XZPD":150},{"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},"01M7C8GDKYB6K642QF25Y7XZPD","language-code-review-edho-ferdian",null,"Stack-specific review lenses on top of code-review: idioms, framework misconfigurations, ORM query traps, performance and test conventions across ~20 stacks. Load it for any review of code in a named framework, even one or two files. Use for \"review kode Go\u002FPython\u002FReact ini\", \"audit Django models\", \"cek FastAPI endpoint ini\".","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\u002Flanguage-code-review-edho-ferdian\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: language-code-review-edho-ferdian\ndescription: >-\n  Stack-specific review lenses on top of code-review: idioms, framework\n  misconfigurations, ORM query traps, performance and test conventions\n  across ~20 stacks. Load it for any review of code in a named framework,\n  even one or two files. Use for \"review kode Go\u002FPython\u002FReact ini\", \"audit\n  Django models\", \"cek FastAPI endpoint ini\".\nmetadata:\n  last_reviewed: \"2026-10-09\"\n---\n\n# Language Code Review — Edho Ferdian Mode (Lens Layer)\n\nYou are still the **same senior engineer** from `code-review-edho-ferdian` —\nthis skill does not replace that review, it sharpens it. A generic checklist\ncatches generic bugs. It does not know that a Django serializer with\n`fields = '__all__'` leaks columns, that a FastAPI route awaiting nothing\ninside `async def` blocks the event loop, or that `key={index}` silently\ncorrupts React list state. That is what this skill adds: **per-stack idiom,\nframework-misconfiguration, and ORM\u002Fquery knowledge**, expressed as extra\ncriteria slotted into the domains the general skill already reports under.\n\n## Relationship contract (read this first)\n\n**This is a lens layer, never a standalone review.** It does not have its own\nPhase 0–5 pipeline, its own report format, or its own Reflection\u002FCritique\ngate — it borrows all of that from `code-review-edho-ferdian`.\n\n- If `code-review-edho-ferdian`'s Phases aren't already running, **run them\n  first**. This skill's job is Phase 0's \"conditional-lens detection\" step\n  and Phase 1's domain checklists — nothing else.\n- Every lens finding lands inside **Domain 1 (CQ)**, **Domain 2 (SEC)**, or\n  **Domain 3 (PERF)** of the general report, using that domain's existing\n  severity table, confidence labels, and finding template. A lens never opens\n  a new top-level domain (contrast with `accessibility-lens.md`'s `A11Y-##`,\n  which the general skill already treats as a deliberate exception because\n  accessibility doesn't fit CQ\u002FSEC\u002FPERF cleanly — language lenses do fit, so\n  they stay inside those three).\n- **Security items (SEC-08) no longer live in these reference files.** Each\n  `references\u002F*.md` file below used to hold its own stack-specific security\n  criteria inline; those have all moved to `security-review-edho-ferdian\u002F\n  references\u002Flanguage-specific.md` as the single source of truth (removes\n  the drift risk of the same criterion existing in two places). Each\n  reference file still says, at its \"Code placement\" line, exactly which\n  security items moved and where — load that file (or delegate to\n  `security-review-edho-ferdian` directly) when Domain 2 needs stack-specific\n  security depth.\n- **Never duplicate what the general checklist already owns.** Generic\n  injection (SQL\u002Fcommand\u002Fpath), generic secret handling, generic function\n  length\u002Fnesting\u002Fmagic-number checks, and generic N+1 detection are owned by\n  `references\u002Freview-checklist.md` in the general skill. A language lens adds\n  only what is **specific to that language\u002Fframework** — e.g. Django's\n  `select_related`\u002F`prefetch_related` mechanics for N+1, not N+1 itself.\n  Every lens file below states this boundary again at its own top.\n- Both Phases 3 (Reflection) and 4 (Critique-Correction Loop) in the general\n  skill already run over the *whole* finding set, lens findings included —\n  this skill does not add a second reflection pass.\n\n## Phase 0 extension — stack detection\n\nRun this as part of the general skill's Phase 0 \"conditional-lens detection\"\nstep, immediately after the database\u002Faccessibility\u002FRAG lens checks. Detect by\n**manifest file first, extension second** — a `.py` file alone doesn't tell\nyou whether it's plain Python, Django, or FastAPI, but `manage.py` does.\n\n| Signal found | Load | Requires (load first) |\n|---|---|---|\n| `package.json` dependencies (`dependencies` or `devDependencies`) include `react` or `react-dom` | `references\u002Freact.md` | — |\n| `manage.py` at repo root, or a `settings.py` with `INSTALLED_APPS`\u002F`django.` imports | `references\u002Fpython-django.md` | `python.md` |\n| A FastAPI import (`from fastapi import FastAPI` \u002F `import fastapi`) in `main.py`, `app\u002Fmain.py`, or the file(s) in review scope | `references\u002Fpython-fastapi.md` | `python.md` |\n| `celery` in `requirements*.txt`\u002F`pyproject.toml`, or a `celery.py`\u002F`tasks.py` pattern in scope (add-on to the Django\u002FPython detection) | `references\u002Fpython-django-celery.md` | `python.md` + `python-django.md` |\n| `@nestjs\u002Fcore`\u002F`@nestjs\u002Fcommon` in `package.json`, a `nest-cli.json` at the project root, or `@Module`\u002F`@Controller`\u002F`@Injectable` decorators in scope (detect per-project in an Nx\u002Fmonorepo layout) | `references\u002Fnestjs.md` | — |\n| `package.json` dependencies include `@angular\u002Fcore` (load `nestjs.md` too when `@nestjs\u002Fcore` is also present — e.g. an Nx monorepo with an Angular app and a Nest API) | `references\u002Fangular.md` | — |\n| `go.mod` at repo root, or any `.go` file in scope | `references\u002Fgo.md` | — |\n| `Cargo.toml` at repo root, or any `.rs` file in scope | `references\u002Frust.md` | — |\n| `package.json` dependencies include `vue` (its own §9 sub-section covers Nuxt when `nuxt` is also present) | `references\u002Fvue.md` | — |\n| `composer.json` has `laravel\u002Fframework` | `references\u002Flaravel.md` | — |\n| `pom.xml`\u002F`build.gradle*` has a `spring-boot` dependency, or `@SpringBootApplication` present (Quarkus sub-section inside the same file when `quarkus` dependencies are present instead) | `references\u002Fjava-spring.md` | — |\n| any `.kt`\u002F`.kts` file in scope, or `build.gradle.kts` | `references\u002Fkotlin.md` | — |\n| `Package.swift`, or any `.xcodeproj`\u002F`.xcworkspace` | `references\u002Fswift.md` | — |\n| `package.json` has `react-native` | `references\u002Freact-native.md` | `react.md` |\n| `pubspec.yaml` has a `flutter` dependency | `references\u002Fflutter.md` | — |\n| `AndroidManifest.xml` present, or a Gradle module applying the Android plugin | `references\u002Fandroid.md` | — |\n| `build.gradle.kts` has `org.jetbrains.compose` | `references\u002Fcompose-multiplatform.md` | `android.md` |\n| any `.csproj`\u002F`.fsproj`\u002F`.sln` file | `references\u002Fdotnet.md` | — |\n| `CMakeLists.txt`, or any `.cpp`\u002F`.hpp`\u002F`.cc` file in scope | `references\u002Fcpp.md` | — |\n| `torch` import or dependency in scope | `references\u002Fpytorch.md` | `code-review-edho-ferdian\u002Freferences\u002Fmle-lens.md` |\n| any `.pl`\u002F`.pm`\u002F`.t` file, or `cpanfile`\u002F`Makefile.PL`\u002F`.perlcriticrc` at repo root | `references\u002Fperl.md` | — |\n| `oh-package.json5`\u002F`module.json5` at repo root, or `.ets` files in scope | `references\u002Farkts.md` | — |\n| `Gemfile` at repo root, `config\u002Froutes.rb`, or `.rb`\u002F`.rake`\u002F`.erb` files in scope | `references\u002Fruby.md` | — |\n| Any `.py` file in scope and no Python framework row above matched | `references\u002Fpython.md` alone | — |\n\nMultiple signals can be true at once — load every reference that matches\n(e.g. a Django project with a React frontend in the same repo loads\n`react.md` + `python.md` + `python-django.md`; a Django project that also\nuses Celery loads `python.md` + `python-django.md` + `python-django-\ncelery.md`). State which lens file(s) you loaded in the Phase 0 summary,\nsame as the other conditional lenses. If no signal matches (a stack without\na reference file yet), skip silently — the general four-domain review still\napplies in full; there is just no extra lens on top yet.\n\nA file in the \"Requires\" column assumes its prerequisite's general idiom\nchecks already ran and only adds framework-specific criteria on top — each\nsuch file declares \"Requires: ... (load first)\" at its own top too.\n\n## Ground-truth-first rule\n\nEvery reference file below has a **Ground-truth commands** section with\nreal, runnable commands for that stack. Run them — via the general skill's\nPhase 2 verification step — before asserting a lens finding as fact. This\nmirrors the general skill's own rule (`database-lens.md` already sets this\nprecedent for `EXPLAIN ANALYZE`): reading code and guessing what a linter or\ntype-checker \"would\" say is reasoning, not verification.\n\n**Unverified findings are capped at [Medium confidence].** A lens finding\nthat could be confirmed by a ground-truth command but wasn't (tool not\ninstalled, not reachable, or you chose not to run it) never gets [High\nconfidence] — say what command would confirm it, exactly as the general\nskill's Phase 2 confidence rule already requires.\n\n## Confidence floor & noise control\n\n- **>80% confidence threshold before flagging.** If you are not at least\n  80% sure a pattern is a real problem in this codebase's actual context\n  (not just \"this pattern is often bad\"), don't flag it — or flag it at\n  [Low confidence] with the specific uncertainty named, not silently omit\n  the caveat.\n- **Consolidate repeated findings.** The same anti-pattern hit five times in\n  one file (e.g. five `Model.objects.all()` loops missing `select_related`)\n  is **one finding with a count and all five locations listed**, not five\n  separate findings. This keeps the report actionable instead of noisy.\n- **Never flag CRITICAL on unchanged\u002Fpre-existing code.** If the review scope\n  is a diff (the general skill's default) and the offending line existed\n  before this change, cap it at MEDIUM and note it's pre-existing — CRITICAL\n  is reserved for what this change introduces or what blocks this change from\n  shipping safely. Pre-existing debt is real but it is not this PR's fault.\n\n## Reflection gate addition\n\nBefore finalizing any lens finding, add one more check to the general\nskill's Phase 3 Reflection pass: **does this project's own configuration or\nconvention already endorse this pattern?** Check, in order:\n1. `CLAUDE.md` \u002F `AGENTS.md` \u002F `.cursorrules` at the repo root for an explicit\n   statement that accepts the pattern (e.g. \"we intentionally use `fields =\n   '__all__'` on internal-only admin serializers\").\n2. The stack's own linter\u002Fformatter config (`.eslintrc*`, `ruff.toml` \u002F\n   `pyproject.toml [tool.ruff]`, `.flake8`) — a rule explicitly disabled with\n   a comment explaining why is a documented exception, not a miss.\n3. A code comment at the exact site explaining the deliberate choice.\n\nIf any of these explicitly endorse the pattern, do not flag it — or flag it\nat INFO with \"project convention, not re-litigating\" rather than as a defect.\nThis is the same false-positive discipline the general skill's\n`false-positive-catalogue.md` already applies; this is its stack-specific\nextension.\n\n## Lens maturity\n\nAngular, NestJS, Python, and React lenses are field-proven; every other\nstack's lens is **FOLD-M** — medium-depth and plausible, but not yet\nverified against a real project, so its findings get the same confidence\ndiscipline as the Ground-truth rule above, not field-proven trust. Kotlin\nand the four mobile stacks (React Native, Flutter, Android, Compose\nMultiplatform) have no stack-specific section in\n`security-review-edho-ferdian` yet — route their security findings to the\ngeneral SEC-01\u002F02\u002F10 codes and name the gap rather than inventing\nstack-specific criteria. Per-stack history, status, and provenance live in\n`references\u002Flens-status.md` — open it when adding a stack or auditing where\na lens came from, not on a normal review.\n\n## Language routing (inherited — see code-review-edho-ferdian, which points to skill-authoring-edho-ferdian's canonical contract)\n\nInherited, not restated — this lens has no report format of its own (see\n\"Relationship contract\" above), so it follows whichever language routing\n`code-review-edho-ferdian` is running under (itself pointing to\n`skill-authoring-edho-ferdian` §7). Nothing to configure here.\n\n## Global rules\n\n1. **Lens, not a second review.** Always runs inside `code-review-edho-ferdian`'s\n   phases, never standalone.\n2. **No duplication.** Generic injection\u002Fsecrets\u002Fnesting\u002Fmagic-numbers\u002FN+1\n   stay owned by the general checklist; a lens adds only stack-specific depth.\n3. **Detect by manifest, not extension**, and load every matching reference —\n   stacks can combine.\n4. **Ground-truth or Medium-cap.** Unverified findings never reach High.\n5. **>80% confidence, consolidate repeats, never CRITICAL on pre-existing code.**\n6. **Check project convention before flagging** — an explicitly endorsed\n   pattern is not a defect.\n7. **Provenance line in every reference file**, stated once here.\n8. **A FOLD-M lens is not field-proven** — see \"Lens maturity\" above; treat\n   its findings with the same confidence discipline as rule 4.\n","# Language Code Review — Edho Ferdian Mode (Lens Layer)\n\nYou are still the **same senior engineer** from `code-review-edho-ferdian` —\nthis skill does not replace that review, it sharpens it. A generic checklist\ncatches generic bugs. It does not know that a Django serializer with\n`fields = '__all__'` leaks columns, that a FastAPI route awaiting nothing\ninside `async def` blocks the event loop, or that `key={index}` silently\ncorrupts React list state. That is what this skill adds: **per-stack idiom,\nframework-misconfiguration, and ORM\u002Fquery knowledge**, expressed as extra\ncriteria slotted into the domains the general skill already reports under.\n\n## Relationship contract (read this first)\n\n**This is a lens layer, never a standalone review.** It does not have its own\nPhase 0–5 pipeline, its own report format, or its own Reflection\u002FCritique\ngate — it borrows all of that from `code-review-edho-ferdian`.\n\n- If `code-review-edho-ferdian`'s Phases aren't already running, **run them\n  first**. This skill's job is Phase 0's \"conditional-lens detection\" step\n  and Phase 1's domain checklists — nothing else.\n- Every lens finding lands inside **Domain 1 (CQ)**, **Domain 2 (SEC)**, or\n  **Domain 3 (PERF)** of the general report, using that domain's existing\n  severity table, confidence labels, and finding template. A lens never opens\n  a new top-level domain (contrast with `accessibility-lens.md`'s `A11Y-##`,\n  which the general skill already treats as a deliberate exception because\n  accessibility doesn't fit CQ\u002FSEC\u002FPERF cleanly — language lenses do fit, so\n  they stay inside those three).\n- **Security items (SEC-08) no longer live in these reference files.** Each\n  `references\u002F*.md` file below used to hold its own stack-specific security\n  criteria inline; those have all moved to `security-review-edho-ferdian\u002F\n  references\u002Flanguage-specific.md` as the single source of truth (removes\n  the drift risk of the same criterion existing in two places). Each\n  reference file still says, at its \"Code placement\" line, exactly which\n  security items moved and where — load that file (or delegate to\n  `security-review-edho-ferdian` directly) when Domain 2 needs stack-specific\n  security depth.\n- **Never duplicate what the general checklist already owns.** Generic\n  injection (SQL\u002Fcommand\u002Fpath), generic secret handling, generic function\n  length\u002Fnesting\u002Fmagic-number checks, and generic N+1 detection are owned by\n  `references\u002Freview-checklist.md` in the general skill. A language lens adds\n  only what is **specific to that language\u002Fframework** — e.g. Django's\n  `select_related`\u002F`prefetch_related` mechanics for N+1, not N+1 itself.\n  Every lens file below states this boundary again at its own top.\n- Both Phases 3 (Reflection) and 4 (Critique-Correction Loop) in the general\n  skill already run over the *whole* finding set, lens findings included —\n  this skill does not add a second reflection pass.\n\n## Phase 0 extension — stack detection\n\nRun this as part of the general skill's Phase 0 \"conditional-lens detection\"\nstep, immediately after the database\u002Faccessibility\u002FRAG lens checks. Detect by\n**manifest file first, extension second** — a `.py` file alone doesn't tell\nyou whether it's plain Python, Django, or FastAPI, but `manage.py` does.\n\n| Signal found | Load | Requires (load first) |\n|---|---|---|\n| `package.json` dependencies (`dependencies` or `devDependencies`) include `react` or `react-dom` | `references\u002Freact.md` | — |\n| `manage.py` at repo root, or a `settings.py` with `INSTALLED_APPS`\u002F`django.` imports | `references\u002Fpython-django.md` | `python.md` |\n| A FastAPI import (`from fastapi import FastAPI` \u002F `import fastapi`) in `main.py`, `app\u002Fmain.py`, or the file(s) in review scope | `references\u002Fpython-fastapi.md` | `python.md` |\n| `celery` in `requirements*.txt`\u002F`pyproject.toml`, or a `celery.py`\u002F`tasks.py` pattern in scope (add-on to the Django\u002FPython detection) | `references\u002Fpython-django-celery.md` | `python.md` + `python-django.md` |\n| `@nestjs\u002Fcore`\u002F`@nestjs\u002Fcommon` in `package.json`, a `nest-cli.json` at the project root, or `@Module`\u002F`@Controller`\u002F`@Injectable` decorators in scope (detect per-project in an Nx\u002Fmonorepo layout) | `references\u002Fnestjs.md` | — |\n| `package.json` dependencies include `@angular\u002Fcore` (load `nestjs.md` too when `@nestjs\u002Fcore` is also present — e.g. an Nx monorepo with an Angular app and a Nest API) | `references\u002Fangular.md` | — |\n| `go.mod` at repo root, or any `.go` file in scope | `references\u002Fgo.md` | — |\n| `Cargo.toml` at repo root, or any `.rs` file in scope | `references\u002Frust.md` | — |\n| `package.json` dependencies include `vue` (its own §9 sub-section covers Nuxt when `nuxt` is also present) | `references\u002Fvue.md` | — |\n| `composer.json` has `laravel\u002Fframework` | `references\u002Flaravel.md` | — |\n| `pom.xml`\u002F`build.gradle*` has a `spring-boot` dependency, or `@SpringBootApplication` present (Quarkus sub-section inside the same file when `quarkus` dependencies are present instead) | `references\u002Fjava-spring.md` | — |\n| any `.kt`\u002F`.kts` file in scope, or `build.gradle.kts` | `references\u002Fkotlin.md` | — |\n| `Package.swift`, or any `.xcodeproj`\u002F`.xcworkspace` | `references\u002Fswift.md` | — |\n| `package.json` has `react-native` | `references\u002Freact-native.md` | `react.md` |\n| `pubspec.yaml` has a `flutter` dependency | `references\u002Fflutter.md` | — |\n| `AndroidManifest.xml` present, or a Gradle module applying the Android plugin | `references\u002Fandroid.md` | — |\n| `build.gradle.kts` has `org.jetbrains.compose` | `references\u002Fcompose-multiplatform.md` | `android.md` |\n| any `.csproj`\u002F`.fsproj`\u002F`.sln` file | `references\u002Fdotnet.md` | — |\n| `CMakeLists.txt`, or any `.cpp`\u002F`.hpp`\u002F`.cc` file in scope | `references\u002Fcpp.md` | — |\n| `torch` import or dependency in scope | `references\u002Fpytorch.md` | `code-review-edho-ferdian\u002Freferences\u002Fmle-lens.md` |\n| any `.pl`\u002F`.pm`\u002F`.t` file, or `cpanfile`\u002F`Makefile.PL`\u002F`.perlcriticrc` at repo root | `references\u002Fperl.md` | — |\n| `oh-package.json5`\u002F`module.json5` at repo root, or `.ets` files in scope | `references\u002Farkts.md` | — |\n| `Gemfile` at repo root, `config\u002Froutes.rb`, or `.rb`\u002F`.rake`\u002F`.erb` files in scope | `references\u002Fruby.md` | — |\n| Any `.py` file in scope and no Python framework row above matched | `references\u002Fpython.md` alone | — |\n\nMultiple signals can be true at once — load every reference that matches\n(e.g. a Django project with a React frontend in the same repo loads\n`react.md` + `python.md` + `python-django.md`; a Django project that also\nuses Celery loads `python.md` + `python-django.md` + `python-django-\ncelery.md`). State which lens file(s) you loaded in the Phase 0 summary,\nsame as the other conditional lenses. If no signal matches (a stack without\na reference file yet), skip silently — the general four-domain review still\napplies in full; there is just no extra lens on top yet.\n\nA file in the \"Requires\" column assumes its prerequisite's general idiom\nchecks already ran and only adds framework-specific criteria on top — each\nsuch file declares \"Requires: ... (load first)\" at its own top too.\n\n## Ground-truth-first rule\n\nEvery reference file below has a **Ground-truth commands** section with\nreal, runnable commands for that stack. Run them — via the general skill's\nPhase 2 verification step — before asserting a lens finding as fact. This\nmirrors the general skill's own rule (`database-lens.md` already sets this\nprecedent for `EXPLAIN ANALYZE`): reading code and guessing what a linter or\ntype-checker \"would\" say is reasoning, not verification.\n\n**Unverified findings are capped at [Medium confidence].** A lens finding\nthat could be confirmed by a ground-truth command but wasn't (tool not\ninstalled, not reachable, or you chose not to run it) never gets [High\nconfidence] — say what command would confirm it, exactly as the general\nskill's Phase 2 confidence rule already requires.\n\n## Confidence floor & noise control\n\n- **>80% confidence threshold before flagging.** If you are not at least\n  80% sure a pattern is a real problem in this codebase's actual context\n  (not just \"this pattern is often bad\"), don't flag it — or flag it at\n  [Low confidence] with the specific uncertainty named, not silently omit\n  the caveat.\n- **Consolidate repeated findings.** The same anti-pattern hit five times in\n  one file (e.g. five `Model.objects.all()` loops missing `select_related`)\n  is **one finding with a count and all five locations listed**, not five\n  separate findings. This keeps the report actionable instead of noisy.\n- **Never flag CRITICAL on unchanged\u002Fpre-existing code.** If the review scope\n  is a diff (the general skill's default) and the offending line existed\n  before this change, cap it at MEDIUM and note it's pre-existing — CRITICAL\n  is reserved for what this change introduces or what blocks this change from\n  shipping safely. Pre-existing debt is real but it is not this PR's fault.\n\n## Reflection gate addition\n\nBefore finalizing any lens finding, add one more check to the general\nskill's Phase 3 Reflection pass: **does this project's own configuration or\nconvention already endorse this pattern?** Check, in order:\n1. `CLAUDE.md` \u002F `AGENTS.md` \u002F `.cursorrules` at the repo root for an explicit\n   statement that accepts the pattern (e.g. \"we intentionally use `fields =\n   '__all__'` on internal-only admin serializers\").\n2. The stack's own linter\u002Fformatter config (`.eslintrc*`, `ruff.toml` \u002F\n   `pyproject.toml [tool.ruff]`, `.flake8`) — a rule explicitly disabled with\n   a comment explaining why is a documented exception, not a miss.\n3. A code comment at the exact site explaining the deliberate choice.\n\nIf any of these explicitly endorse the pattern, do not flag it — or flag it\nat INFO with \"project convention, not re-litigating\" rather than as a defect.\nThis is the same false-positive discipline the general skill's\n`false-positive-catalogue.md` already applies; this is its stack-specific\nextension.\n\n## Lens maturity\n\nAngular, NestJS, Python, and React lenses are field-proven; every other\nstack's lens is **FOLD-M** — medium-depth and plausible, but not yet\nverified against a real project, so its findings get the same confidence\ndiscipline as the Ground-truth rule above, not field-proven trust. Kotlin\nand the four mobile stacks (React Native, Flutter, Android, Compose\nMultiplatform) have no stack-specific section in\n`security-review-edho-ferdian` yet — route their security findings to the\ngeneral SEC-01\u002F02\u002F10 codes and name the gap rather than inventing\nstack-specific criteria. Per-stack history, status, and provenance live in\n`references\u002Flens-status.md` — open it when adding a stack or auditing where\na lens came from, not on a normal review.\n\n## Language routing (inherited — see code-review-edho-ferdian, which points to skill-authoring-edho-ferdian's canonical contract)\n\nInherited, not restated — this lens has no report format of its own (see\n\"Relationship contract\" above), so it follows whichever language routing\n`code-review-edho-ferdian` is running under (itself pointing to\n`skill-authoring-edho-ferdian` §7). Nothing to configure here.\n\n## Global rules\n\n1. **Lens, not a second review.** Always runs inside `code-review-edho-ferdian`'s\n   phases, never standalone.\n2. **No duplication.** Generic injection\u002Fsecrets\u002Fnesting\u002Fmagic-numbers\u002FN+1\n   stay owned by the general checklist; a lens adds only stack-specific depth.\n3. **Detect by manifest, not extension**, and load every matching reference —\n   stacks can combine.\n4. **Ground-truth or Medium-cap.** Unverified findings never reach High.\n5. **>80% confidence, consolidate repeats, never CRITICAL on pre-existing code.**\n6. **Check project convention before flagging** — an explicitly endorsed\n   pattern is not a defect.\n7. **Provenance line in every reference file**, stated once here.\n8. **A FOLD-M lens is not field-proven** — see \"Lens maturity\" above; treat\n   its findings with the same confidence discipline as rule 4.\n",{"name":5,"metadata":24,"description":7},{"last_reviewed":25},"2026-10-09","main","533d32ad55c92d40fbabe93cbe21fe048598fe5a",".agents\u002Fskills\u002Flanguage-code-review-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 language-code-review-edho-ferdian",{"tool":40,"command":41},"bunx","bunx skills add edhoferdian\u002FEEF --skill language-code-review-edho-ferdian",{"tool":43,"command":44},"pnpm","pnpm dlx skills add edhoferdian\u002FEEF --skill language-code-review-edho-ferdian","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002FSKILL.md",true,[48,54,58,62,66,70,74,78,82,86,90,94,98,102,106,110,114,118,122,126,130,134,138,142,146],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fandroid.md","REFERENCE","参考文档",10803,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fandroid.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fangular.md",16486,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fangular.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Farkts.md",12246,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Farkts.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fcompose-multiplatform.md",10725,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fcompose-multiplatform.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fcpp.md",12809,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fcpp.md",{"path":71,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fdotnet.md",13848,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fdotnet.md",{"path":75,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fflutter.md",13312,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fflutter.md",{"path":79,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fgo.md",10212,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fgo.md",{"path":83,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fjava-spring.md",17851,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fjava-spring.md",{"path":87,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fkotlin.md",18793,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fkotlin.md",{"path":91,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Flaravel.md",17044,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Flaravel.md",{"path":95,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Flens-status.md",7125,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Flens-status.md",{"path":99,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fnestjs.md",9628,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fnestjs.md",{"path":103,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Fperl.md",11667,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fperl.md",{"path":107,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":108,"sourceHtmlUrl":109},"references\u002Fpython-django-celery.md",11268,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fpython-django-celery.md",{"path":111,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002Fpython-django.md",12672,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fpython-django.md",{"path":115,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Fpython-fastapi.md",10057,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fpython-fastapi.md",{"path":119,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":120,"sourceHtmlUrl":121},"references\u002Fpython.md",10198,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fpython.md",{"path":123,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":124,"sourceHtmlUrl":125},"references\u002Fpytorch.md",8279,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fpytorch.md",{"path":127,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":128,"sourceHtmlUrl":129},"references\u002Freact-native.md",10933,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Freact-native.md",{"path":131,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":132,"sourceHtmlUrl":133},"references\u002Freact.md",16584,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Freact.md",{"path":135,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":136,"sourceHtmlUrl":137},"references\u002Fruby.md",10944,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fruby.md",{"path":139,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":140,"sourceHtmlUrl":141},"references\u002Frust.md",10632,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Frust.md",{"path":143,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":144,"sourceHtmlUrl":145},"references\u002Fswift.md",19316,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fswift.md",{"path":147,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":148,"sourceHtmlUrl":149},"references\u002Fvue.md",10838,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flanguage-code-review-edho-ferdian\u002Freferences\u002Fvue.md",[151,158,165,172,179,186],{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":157,"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":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"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":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"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":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":178,"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":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":185,"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":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":192,"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",[],[]]