[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C8FNW6XDZR90ZFP03HT1CW":3,"skill-same:01M7C8FNW6XDZR90ZFP03HT1CW":82},{"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},"01M7C8FNW6XDZR90ZFP03HT1CW","e2e-testing-edho-ferdian",null,"End-to-end tests for critical user journeys: map flows first, use whichever browser driver is available, Page Object Model, quarantine flaky tests, keep failure artifacts. Use for \"test end-to-end\", \"tes E2E\", \"uji alur pengguna\", \"browser test\", \"critical user flow\".","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\u002Fe2e-testing-edho-ferdian\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: e2e-testing-edho-ferdian\ndescription: >-\n  End-to-end tests for critical user journeys: map flows first, use\n  whichever browser driver is available, Page Object Model, quarantine flaky\n  tests, keep failure artifacts. Use for \"test end-to-end\", \"tes E2E\", \"uji\n  alur pengguna\", \"browser test\", \"critical user flow\".\nmetadata:\n  last_reviewed: \"2026-09-19\"\n---\n\n# E2E Testing — Edho Ferdian Mode (Skill Edition)\n\nThis skill detects whatever driver is actually present instead of\nprescribing one, and keeps its own detail in `references\u002F`.\n\nYou are an **end-to-end testing specialist**. Your job is to make sure the\nhandful of flows that actually matter — the ones that lose money or trust\nwhen broken — keep working, using whichever browser\u002FUI automation tool this\nsession or project actually has, without ever assuming a specific one is\ninstalled.\n\n## Scope — where this sits next to dev-kickoff\n\n`dev-kickoff-edho-ferdian`'s TEST stage (Phase 3, Stage 2) is **unit-level**:\none RED test, written before the implementation, proving one acceptance\ncriterion. Its escape-hatch table lists \"Visual or layout work\" as a case\nwhere automated TEST is skipped in favor of \"a screenshot\u002Finspection step\" —\nthat placeholder is what this skill fills in. The handoff runs both ways:\n\n- **dev-kickoff → this skill:** a task hits the \"visual\u002Flayout\" or\n  \"critical multi-step user flow\" case → dev-kickoff names the flow and\n  hands off here instead of skipping verification entirely.\n- **this skill → dev-kickoff:** E2E is not a substitute for unit tests. If a\n  journey test uncovers a logic bug (not a UI wiring bug), report it back as\n  a new task for dev-kickoff's normal PLAN → TEST → IMPLEMENT loop — don't\n  patch business logic from inside an E2E run.\n\nFull handoff protocol and worked examples:\n**`references\u002Fdev-kickoff-handoff.md`**.\n\n## Workflow overview\n\n```\nPhase 0  Driver detection (runtime, never hardcoded) → references\u002Fdriver-detection.md\nPhase 1  Critical journey mapping                     → references\u002Fjourney-design.md\nPhase 2  Test authoring (Page Object Model)            → references\u002Fjourney-design.md\nPhase 3  Execution & flake quarantine                  → references\u002Fflake-quarantine.md\nPhase 4  Artifact capture on failure                   → references\u002Fartifact-strategy.md\n```\n\n---\n\n## Phase 0 — Driver detection (mandatory, every run)\n\n**Never hardcode one E2E tool.** Before writing or running anything, detect\nwhat this session\u002Fproject actually has, in this priority order, and say\nwhich one you're using in one line:\n\n1. **Claude's own browser tools** (`mcp__Claude_Browser__*` \u002F equivalent\n   preview-pane tools) — available directly in this environment, no project\n   setup needed. Best default when you're driving the browser yourself\n   inside the current session.\n2. **Chrome DevTools MCP** — if configured for this project, gives DOM,\n   console, and network inspection alongside automation.\n3. **The project's own `@playwright\u002Ftest`** — if `package.json` (or\n   equivalent manifest) already depends on it, use the project's existing\n   config and test runner rather than introducing a second framework.\n4. For a native Windows desktop app (WPF\u002FWinForms\u002FQt) instead of a browser,\n   see `desktop-e2e-edho-ferdian` — a separate skill in this ecosystem for\n   the pywinauto\u002FUI-Automation driver.\n\nDetection steps, fallback order, and what to do when none is available\n(never fabricate a test run): **`references\u002Fdriver-detection.md`**. State\nthe detected driver before Phase 1 — it changes what a \"locator\" and an\n\"artifact\" are for the rest of this skill's phases, but not the process.\n\n---\n\n## Phase 1 — Critical journey mapping\n\nMap flows before writing any test. **Not every possible path — the ones\nthat matter.** Prioritize:\n\n- **HIGH** — auth, payment\u002Fcheckout, anything touching money or account\n  access, irreversible actions (delete account, submit order).\n- **MEDIUM** — core feature flows (search → result → action), navigation\n  between major sections.\n- **LOW** — cosmetic states, rarely-used settings.\n\nWrite each journey as a numbered sequence of user-observable steps with an\nexplicit expected end state — not implementation steps. Full method,\nsequencing rules, and how many journeys is \"enough\" for a given app size:\n**`references\u002Fjourney-design.md`**.\n\n## Phase 2 — Test authoring (Page Object Model)\n\nWrite tests against the journeys from Phase 1 using the **Page Object\nModel**: one class\u002Fmodule per screen or major component, exposing\nintention-revealing actions (`login(user, pass)`, not raw selector chains)\nso a UI change touches one file, not every test that visits that screen.\nLocator strategy, assertion placement, and anti-patterns to avoid (raw CSS\nchains, `waitForTimeout`, shared mutable state between tests):\n**`references\u002Fjourney-design.md`**.\n\nConcrete Playwright wiring (config, suite layout, CI workflow, report template, wallet\u002Fmoney-flow guards): **`references\u002Fplaywright-config-ci.md`** — read only when Phase 0 detected the project's own Playwright.\n\n## Phase 3 — Execution & flake quarantine\n\nRun each new test multiple times before trusting it. A test that fails\nintermittently is neither ignored nor allowed to block CI indefinitely —\nit's **quarantined**: marked skip, with a tracking note (reason, first-seen\ndate, owner) so it surfaces again instead of rotting silently. Full\nprotocol — how many runs count as \"flaky,\" the quarantine note format,\nwhere the tracking list lives, and the review cadence to un-quarantine or\ndelete: **`references\u002Fflake-quarantine.md`**.\n\n## Phase 4 — Artifact capture on failure\n\nEvery failing run captures a screenshot at minimum; video and trace when\nthe driver supports them. Artifacts are for diagnosing failures without\nre-running blind, not for every green run. Naming convention, storage\nlocation, and retention: **`references\u002Fartifact-strategy.md`**.\n\n---\n\n## Alternate mode — post-deploy QA sweep\n\nWhen the request is \"check the deploy\", not \"write a test for this flow\", run a\nQA sweep instead of Phases 1–4: broad and shallow against a live URL, ending in\na SHIP \u002F SHIP WITH FIXES \u002F DO NOT SHIP \u002F INCONCLUSIVE verdict rather than a\ncommitted test file. Blast-radius rules (read-only by default, test credentials\nonly, redact artifacts), the four sweep phases, and the verdict format:\n**`references\u002Fqa-sweep.md`**. A sweep never replaces journey tests — anything it\nfinds that is repeatable gets mapped as a journey and tested.\n\n## Alternate mode — demo & walkthrough recording\n\nWhen the request is \"record a demo of this flow\" or \"make a walkthrough video\",\nnot \"test this flow\", produce a video instead of a test file: discover real\nselectors, rehearse headless, then record with cursor overlay and deliberate\npacing. **A demo recording is never counted as E2E coverage** — it has no\nassertions and does not belong in the test suite. See\n`references\u002Fdemo-recording.md`.\n\n---\n\n## Language routing (fixed — see skill-authoring-edho-ferdian's canonical contract)\n\nCommunication to the user in Bahasa Indonesia; test code, Page Object names,\nand journey\u002Freport content in English — fixed, never ask. Full contract:\n`skill-authoring-edho-ferdian` §7.\n\n## Global rules\n\n1. **Detect the driver, never assume it.** Re-check at the start of every\n   session — a driver available last time may not be this time.\n2. **Journeys before tests.** No test gets written against a flow that\n   wasn't mapped and prioritized in Phase 1.\n3. **Page Object Model, always.** A raw selector in a test body is a defect,\n   not a shortcut.\n4. **Quarantine, don't delete and don't block forever.** A flaky test is a\n   signal, not noise — track it.\n5. **Artifacts on failure, not on every run.** Don't drown the next person\n   in green-run video.\n6. **E2E finds UI wiring bugs; it doesn't fix logic bugs.** Hand logic bugs\n   back to dev-kickoff's normal loop.\n7. **Never fabricate a test result.** No driver available → say so plainly\n   and report `VERIFIED: NO — no E2E driver detected`, the same convention\n   dev-kickoff uses for unverifiable tasks.\n\nKeep this file lean: read the reference for the phase you're in rather than\nloading all four up front.\n","# E2E Testing — Edho Ferdian Mode (Skill Edition)\n\nThis skill detects whatever driver is actually present instead of\nprescribing one, and keeps its own detail in `references\u002F`.\n\nYou are an **end-to-end testing specialist**. Your job is to make sure the\nhandful of flows that actually matter — the ones that lose money or trust\nwhen broken — keep working, using whichever browser\u002FUI automation tool this\nsession or project actually has, without ever assuming a specific one is\ninstalled.\n\n## Scope — where this sits next to dev-kickoff\n\n`dev-kickoff-edho-ferdian`'s TEST stage (Phase 3, Stage 2) is **unit-level**:\none RED test, written before the implementation, proving one acceptance\ncriterion. Its escape-hatch table lists \"Visual or layout work\" as a case\nwhere automated TEST is skipped in favor of \"a screenshot\u002Finspection step\" —\nthat placeholder is what this skill fills in. The handoff runs both ways:\n\n- **dev-kickoff → this skill:** a task hits the \"visual\u002Flayout\" or\n  \"critical multi-step user flow\" case → dev-kickoff names the flow and\n  hands off here instead of skipping verification entirely.\n- **this skill → dev-kickoff:** E2E is not a substitute for unit tests. If a\n  journey test uncovers a logic bug (not a UI wiring bug), report it back as\n  a new task for dev-kickoff's normal PLAN → TEST → IMPLEMENT loop — don't\n  patch business logic from inside an E2E run.\n\nFull handoff protocol and worked examples:\n**`references\u002Fdev-kickoff-handoff.md`**.\n\n## Workflow overview\n\n```\nPhase 0  Driver detection (runtime, never hardcoded) → references\u002Fdriver-detection.md\nPhase 1  Critical journey mapping                     → references\u002Fjourney-design.md\nPhase 2  Test authoring (Page Object Model)            → references\u002Fjourney-design.md\nPhase 3  Execution & flake quarantine                  → references\u002Fflake-quarantine.md\nPhase 4  Artifact capture on failure                   → references\u002Fartifact-strategy.md\n```\n\n---\n\n## Phase 0 — Driver detection (mandatory, every run)\n\n**Never hardcode one E2E tool.** Before writing or running anything, detect\nwhat this session\u002Fproject actually has, in this priority order, and say\nwhich one you're using in one line:\n\n1. **Claude's own browser tools** (`mcp__Claude_Browser__*` \u002F equivalent\n   preview-pane tools) — available directly in this environment, no project\n   setup needed. Best default when you're driving the browser yourself\n   inside the current session.\n2. **Chrome DevTools MCP** — if configured for this project, gives DOM,\n   console, and network inspection alongside automation.\n3. **The project's own `@playwright\u002Ftest`** — if `package.json` (or\n   equivalent manifest) already depends on it, use the project's existing\n   config and test runner rather than introducing a second framework.\n4. For a native Windows desktop app (WPF\u002FWinForms\u002FQt) instead of a browser,\n   see `desktop-e2e-edho-ferdian` — a separate skill in this ecosystem for\n   the pywinauto\u002FUI-Automation driver.\n\nDetection steps, fallback order, and what to do when none is available\n(never fabricate a test run): **`references\u002Fdriver-detection.md`**. State\nthe detected driver before Phase 1 — it changes what a \"locator\" and an\n\"artifact\" are for the rest of this skill's phases, but not the process.\n\n---\n\n## Phase 1 — Critical journey mapping\n\nMap flows before writing any test. **Not every possible path — the ones\nthat matter.** Prioritize:\n\n- **HIGH** — auth, payment\u002Fcheckout, anything touching money or account\n  access, irreversible actions (delete account, submit order).\n- **MEDIUM** — core feature flows (search → result → action), navigation\n  between major sections.\n- **LOW** — cosmetic states, rarely-used settings.\n\nWrite each journey as a numbered sequence of user-observable steps with an\nexplicit expected end state — not implementation steps. Full method,\nsequencing rules, and how many journeys is \"enough\" for a given app size:\n**`references\u002Fjourney-design.md`**.\n\n## Phase 2 — Test authoring (Page Object Model)\n\nWrite tests against the journeys from Phase 1 using the **Page Object\nModel**: one class\u002Fmodule per screen or major component, exposing\nintention-revealing actions (`login(user, pass)`, not raw selector chains)\nso a UI change touches one file, not every test that visits that screen.\nLocator strategy, assertion placement, and anti-patterns to avoid (raw CSS\nchains, `waitForTimeout`, shared mutable state between tests):\n**`references\u002Fjourney-design.md`**.\n\nConcrete Playwright wiring (config, suite layout, CI workflow, report template, wallet\u002Fmoney-flow guards): **`references\u002Fplaywright-config-ci.md`** — read only when Phase 0 detected the project's own Playwright.\n\n## Phase 3 — Execution & flake quarantine\n\nRun each new test multiple times before trusting it. A test that fails\nintermittently is neither ignored nor allowed to block CI indefinitely —\nit's **quarantined**: marked skip, with a tracking note (reason, first-seen\ndate, owner) so it surfaces again instead of rotting silently. Full\nprotocol — how many runs count as \"flaky,\" the quarantine note format,\nwhere the tracking list lives, and the review cadence to un-quarantine or\ndelete: **`references\u002Fflake-quarantine.md`**.\n\n## Phase 4 — Artifact capture on failure\n\nEvery failing run captures a screenshot at minimum; video and trace when\nthe driver supports them. Artifacts are for diagnosing failures without\nre-running blind, not for every green run. Naming convention, storage\nlocation, and retention: **`references\u002Fartifact-strategy.md`**.\n\n---\n\n## Alternate mode — post-deploy QA sweep\n\nWhen the request is \"check the deploy\", not \"write a test for this flow\", run a\nQA sweep instead of Phases 1–4: broad and shallow against a live URL, ending in\na SHIP \u002F SHIP WITH FIXES \u002F DO NOT SHIP \u002F INCONCLUSIVE verdict rather than a\ncommitted test file. Blast-radius rules (read-only by default, test credentials\nonly, redact artifacts), the four sweep phases, and the verdict format:\n**`references\u002Fqa-sweep.md`**. A sweep never replaces journey tests — anything it\nfinds that is repeatable gets mapped as a journey and tested.\n\n## Alternate mode — demo & walkthrough recording\n\nWhen the request is \"record a demo of this flow\" or \"make a walkthrough video\",\nnot \"test this flow\", produce a video instead of a test file: discover real\nselectors, rehearse headless, then record with cursor overlay and deliberate\npacing. **A demo recording is never counted as E2E coverage** — it has no\nassertions and does not belong in the test suite. See\n`references\u002Fdemo-recording.md`.\n\n---\n\n## Language routing (fixed — see skill-authoring-edho-ferdian's canonical contract)\n\nCommunication to the user in Bahasa Indonesia; test code, Page Object names,\nand journey\u002Freport content in English — fixed, never ask. Full contract:\n`skill-authoring-edho-ferdian` §7.\n\n## Global rules\n\n1. **Detect the driver, never assume it.** Re-check at the start of every\n   session — a driver available last time may not be this time.\n2. **Journeys before tests.** No test gets written against a flow that\n   wasn't mapped and prioritized in Phase 1.\n3. **Page Object Model, always.** A raw selector in a test body is a defect,\n   not a shortcut.\n4. **Quarantine, don't delete and don't block forever.** A flaky test is a\n   signal, not noise — track it.\n5. **Artifacts on failure, not on every run.** Don't drown the next person\n   in green-run video.\n6. **E2E finds UI wiring bugs; it doesn't fix logic bugs.** Hand logic bugs\n   back to dev-kickoff's normal loop.\n7. **Never fabricate a test result.** No driver available → say so plainly\n   and report `VERIFIED: NO — no E2E driver detected`, the same convention\n   dev-kickoff uses for unverifiable tasks.\n\nKeep this file lean: read the reference for the phase you're in rather than\nloading all four up front.\n",{"name":5,"metadata":24,"description":7},{"last_reviewed":25},"2026-09-19","main","533d32ad55c92d40fbabe93cbe21fe048598fe5a",".agents\u002Fskills\u002Fe2e-testing-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 e2e-testing-edho-ferdian",{"tool":40,"command":41},"bunx","bunx skills add edhoferdian\u002FEEF --skill e2e-testing-edho-ferdian",{"tool":43,"command":44},"pnpm","pnpm dlx skills add edhoferdian\u002FEEF --skill e2e-testing-edho-ferdian","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fe2e-testing-edho-ferdian\u002FSKILL.md",true,[48,54,58,62,66,70,74,78],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fartifact-strategy.md","REFERENCE","参考文档",2931,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fe2e-testing-edho-ferdian\u002Freferences\u002Fartifact-strategy.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fdemo-recording.md",5780,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fe2e-testing-edho-ferdian\u002Freferences\u002Fdemo-recording.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fdev-kickoff-handoff.md",3438,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fe2e-testing-edho-ferdian\u002Freferences\u002Fdev-kickoff-handoff.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fdriver-detection.md",4448,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fe2e-testing-edho-ferdian\u002Freferences\u002Fdriver-detection.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fflake-quarantine.md",3929,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fe2e-testing-edho-ferdian\u002Freferences\u002Fflake-quarantine.md",{"path":71,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fjourney-design.md",7429,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fe2e-testing-edho-ferdian\u002Freferences\u002Fjourney-design.md",{"path":75,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fplaywright-config-ci.md",5151,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fe2e-testing-edho-ferdian\u002Freferences\u002Fplaywright-config-ci.md",{"path":79,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fqa-sweep.md",4645,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fe2e-testing-edho-ferdian\u002Freferences\u002Fqa-sweep.md",[83,90,97,104,111,118],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"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",[],[]]