[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C9098F25PBYYH1BTKCVZ6E":3,"skill-same:01M7C9098F25PBYYH1BTKCVZ6E":66},{"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},"01M7C9098F25PBYYH1BTKCVZ6E","opensource-release-edho-ferdian",null,"Prepare a project for public open-source release: move secrets to .env.example, run an independent audit that gates on FAIL, then generate README, LICENSE and contributor files. Use for \"mau open-source-kan ini\", \"siapkan repo ini buat publik\", \"audit sebelum rilis publik\", \"cek apakah aman di-publish\".","edhoferdian\u002FEEF","edhoferdian","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F64404158?v=4","01M7C8538ZVVZWZEN1AW2MQXCV","Edho F","01M7C8539NS56BMJ4GXN8A47TQ",22,"MIT","https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.kiro\u002Fskills\u002Fopensource-release-edho-ferdian\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: opensource-release-edho-ferdian\ndescription: >-\n  Prepare a project for public open-source release: move secrets to\n  .env.example, run an independent audit that gates on FAIL, then generate\n  README, LICENSE and contributor files. Use for \"mau open-source-kan ini\",\n  \"siapkan repo ini buat publik\", \"audit sebelum rilis publik\", \"cek apakah\n  aman di-publish\".\nmetadata:\n  last_reviewed: \"2026-10-29\"\n---\n\n# Open-Source Release — Edho Ferdian Mode\n\nYou are running a **three-phase release pipeline**: fork\u002Fprep, then an\nindependent adversarial sanitization audit, then packaging. The three phases\nare separated on purpose — a project is not safe to publish because the\nperson who sanitized it says so; it's safe because someone who didn't do\nthe sanitizing re-checked it from scratch and found nothing.\n\n**Boundary with `security-review-edho-ferdian`.** This skill asks \"can this\nrepository be made public without leaking secrets, private context or\ninternal names?\" It does not hunt exploitable vulnerabilities in the code.\n\"Audit sebelum production\" or \"is this safe to deploy\" is that skill's\nMode C full audit. A project going public *and* to production needs both:\nrun Mode C on the source, then this pipeline on the fork.\n\n## Language routing (fixed — see skill-authoring-edho-ferdian's canonical contract)\n\n- Communication to the user → **Bahasa Indonesia**.\n- Report files (`FORK_REPORT.md`, `SANITIZATION_REPORT.md`, generated\n  `CLAUDE.md`\u002F`README.md`\u002Fetc.) → **English**, matching the base rule's\n  artifact clause.\n- The Phase 2 PASS-WITH-WARNINGS confirmation prompt to the user is always\n  in Bahasa Indonesia (see below) — this is a deliberate exception spelled\n  out in `references\u002Fsanitize-audit.md`, not an inconsistency. Full\n  contract: `skill-authoring-edho-ferdian` §7.\n\n## Phase flow\n\n```\nPhase 1  Fork \u002F Prep         → references\u002Ffork-prep.md\n                                 Copy to staging, detect + extract secrets\n                                 into .env.example, replace internal refs,\n                                 fresh git history, write FORK_REPORT.md.\n\nPhase 2  Sanitize \u002F Audit    → references\u002Fsanitize-audit.md\n                                 Independent adversarial re-scan. Does not\n                                 trust FORK_REPORT.md. Verdict: PASS \u002F FAIL \u002F\n                                 PASS-WITH-WARNINGS. Writes\n                                 SANITIZATION_REPORT.md.\n\nPhase 3  Package             → references\u002Fpackaging-templates.md\n                                 CLAUDE.md (this ecosystem's Execution\n                                 Context Pack format, \u003C100 lines),\n                                 setup.sh, README.md, LICENSE, CONTRIBUTING.md,\n                                 GitHub issue templates.\n```\n\nShared reference used by both Phase 1 and Phase 2:\n**`references\u002Fsecret-patterns.md`** — the single source of truth for every\nsecret\u002FPII regex and the internal-reference replacement map. Neither phase\nkeeps its own inline copy; both read this file. If you ever find yourself\nabout to write a regex pattern inline in Phase 1 or Phase 2's instructions,\nstop — it belongs in `secret-patterns.md` instead, edited once.\n\n## The hard gate — read this before starting Phase 3\n\n**Phase 3 cannot start while Phase 2's verdict is FAIL.** This is not a\nrecommendation, it's a hard stop: no `CLAUDE.md`, no `README.md`, nothing\ngets generated for a project Phase 2 rejected. Send the project back to\nPhase 1 with the specific findings, let Phase 1 fix them, then re-run Phase\n2 **in full, from Step 1** — a partial re-audit against only the previously\nfailing items is not sufficient, because a fix to one file can introduce or\nreveal something a full re-scan would catch and a targeted one wouldn't.\n\n**PASS-WITH-WARNINGS requires an explicit user decision before Phase 3\nproceeds.** Do not silently treat a WARNING verdict as good enough to move\non. Present the warning list in Bahasa Indonesia (template and full\nreasoning in `references\u002Fsanitize-audit.md`) and get an explicit yes\u002Fno —\neither \"lanjut dengan status ini\" or \"perbaiki dulu.\" Record whichever\nanswer you get:\n\n- If this release is happening inside a `dev-kickoff-edho-ferdian`-managed\n  project (a `\u002Fproject-memory\u002F` directory exists), write the decision to\n  that project's `project-memory\u002F01-decision-register.md` — source: this\n  conversation, date, and the specific warnings accepted or the fix\n  requested.\n- Otherwise (a standalone, one-off release with no dev-kickoff project\n  context), record the decision inline in `SANITIZATION_REPORT.md`'s own\n  verdict section instead. Never proceed on a WARNING without *some*\n  durable record of who accepted the risk and why — a chat message alone\n  disappears; a file doesn't.\n\n**PASS** needs no confirmation — proceed straight to Phase 3.\n\n## This skill's Critique-Correction Loop instance\n\nPhase 1 → Phase 2 is this ecosystem's Critique-Correction Loop pattern\n(the same shape `code-review-edho-ferdian` uses between its Reviewer and\nCritic roles — see that skill's `references\u002Freflection-critique.md`),\napplied to a release pipeline instead of a code review:\n\n- Phase 1 is the **Producer** — it claims what it stripped and extracted,\n  and writes `FORK_REPORT.md` as its own account.\n- Phase 2 is the **adversarial Verifier** — it never opens `FORK_REPORT.md`\n  to decide what to scan. It re-derives every finding from the filesystem\n  and git history directly, then optionally compares its independent\n  findings against Phase 1's claims (a mismatch is itself a finding, not a\n  contradiction to paper over).\n\n**On a harness with sub-agent delegation** (Claude Code, OpenCode, Hermes\nvia its delegate_task template, ZCode's own Subagents), Phase 2 runs as\nthe `opensource-sanitizer-edho-ferdian` agent, delegated fresh after Phase\n1 completes — a real separate context, not just an instruction to\ndisregard what's already in view. \"Never trust FORK_REPORT.md\" is much\neasier to actually honor when the verifier genuinely never saw it, versus\nasking the same context that wrote it to pretend otherwise. On a harness\nwith no delegation primitive, run Phase 2 inline per\n`references\u002Fsanitize-audit.md`, and note in `SANITIZATION_REPORT.md` that\nthe independence guarantee is weaker in that mode — still re-derive every\nfinding from scratch, just without hard context isolation backing it.\n- A FAIL sends the actual file\u002Fhistory issue back to Phase 1's method,\n  never a patch applied directly by Phase 2 — Phase 2 stays read-only, full\n  stop, per its own rules in `references\u002Fsanitize-audit.md`.\n\nFull framing and the reasoning behind treating this as the same pattern\nlives at the top of `references\u002Fsanitize-audit.md` — read it there rather\nthan duplicating it here.\n\n## Workflow\n\n1. **Confirm scope with the user**: source project path, target directory\n   for the sanitized copy, intended license (don't default silently — see\n   `references\u002Fpackaging-templates.md` Step 5), and whether a GitHub repo\n   already exists (affects whether `.github\u002FISSUE_TEMPLATE\u002F` gets created).\n2. **Run Phase 1** per `references\u002Ffork-prep.md`. Report file counts,\n   secrets extracted, and internal references replaced. State plainly that\n   this report is not the release gate.\n3. **Run Phase 2** — delegate to `opensource-sanitizer-edho-ferdian` on a\n   harness that supports it, else run `references\u002Fsanitize-audit.md`\n   inline — unconditionally, on the staged copy, regardless of how\n   confident Phase 1's own report sounded. Get a verdict.\n4. **Apply the hard gate** above based on the verdict.\n5. **Run Phase 3** per `references\u002Fpackaging-templates.md` once cleared.\n   Report every file generated or enhanced, with `setup.sh` confirmed\n   executable.\n6. **Final summary to the user** (Bahasa Indonesia): what was done in each\n   phase, the Phase 2 verdict and any recorded warning decision, and where\n   every report\u002Fgenerated file landed.\n\n## Notes\n\n- `references\u002Fsecret-patterns.md` consolidates what used to be two\n  independently-drifting inline pattern lists into one shared source of\n  truth.\n\n## Rules\n\n- Never sanitize in place — always stage to a separate `TARGET_DIR` (Phase\n  1, Step 2).\n- Never let Phase 3 start on a FAIL verdict, no exceptions, no \"package it\n  anyway, fix later\" path.\n- Never silently proceed past PASS-WITH-WARNINGS — get and record an\n  explicit decision first.\n- Never trust `FORK_REPORT.md`'s claims as evidence in Phase 2 — re-derive\n  everything.\n- Keep secret\u002FPII patterns in `secret-patterns.md` only — no inline copies\n  in Phase 1 or Phase 2's own reference files.\n- Generated `CLAUDE.md` reuses this ecosystem's Execution Context Pack\n  format and stays under 100 lines — see `references\u002Fpackaging-templates.md`.\n","# Open-Source Release — Edho Ferdian Mode\n\nYou are running a **three-phase release pipeline**: fork\u002Fprep, then an\nindependent adversarial sanitization audit, then packaging. The three phases\nare separated on purpose — a project is not safe to publish because the\nperson who sanitized it says so; it's safe because someone who didn't do\nthe sanitizing re-checked it from scratch and found nothing.\n\n**Boundary with `security-review-edho-ferdian`.** This skill asks \"can this\nrepository be made public without leaking secrets, private context or\ninternal names?\" It does not hunt exploitable vulnerabilities in the code.\n\"Audit sebelum production\" or \"is this safe to deploy\" is that skill's\nMode C full audit. A project going public *and* to production needs both:\nrun Mode C on the source, then this pipeline on the fork.\n\n## Language routing (fixed — see skill-authoring-edho-ferdian's canonical contract)\n\n- Communication to the user → **Bahasa Indonesia**.\n- Report files (`FORK_REPORT.md`, `SANITIZATION_REPORT.md`, generated\n  `CLAUDE.md`\u002F`README.md`\u002Fetc.) → **English**, matching the base rule's\n  artifact clause.\n- The Phase 2 PASS-WITH-WARNINGS confirmation prompt to the user is always\n  in Bahasa Indonesia (see below) — this is a deliberate exception spelled\n  out in `references\u002Fsanitize-audit.md`, not an inconsistency. Full\n  contract: `skill-authoring-edho-ferdian` §7.\n\n## Phase flow\n\n```\nPhase 1  Fork \u002F Prep         → references\u002Ffork-prep.md\n                                 Copy to staging, detect + extract secrets\n                                 into .env.example, replace internal refs,\n                                 fresh git history, write FORK_REPORT.md.\n\nPhase 2  Sanitize \u002F Audit    → references\u002Fsanitize-audit.md\n                                 Independent adversarial re-scan. Does not\n                                 trust FORK_REPORT.md. Verdict: PASS \u002F FAIL \u002F\n                                 PASS-WITH-WARNINGS. Writes\n                                 SANITIZATION_REPORT.md.\n\nPhase 3  Package             → references\u002Fpackaging-templates.md\n                                 CLAUDE.md (this ecosystem's Execution\n                                 Context Pack format, \u003C100 lines),\n                                 setup.sh, README.md, LICENSE, CONTRIBUTING.md,\n                                 GitHub issue templates.\n```\n\nShared reference used by both Phase 1 and Phase 2:\n**`references\u002Fsecret-patterns.md`** — the single source of truth for every\nsecret\u002FPII regex and the internal-reference replacement map. Neither phase\nkeeps its own inline copy; both read this file. If you ever find yourself\nabout to write a regex pattern inline in Phase 1 or Phase 2's instructions,\nstop — it belongs in `secret-patterns.md` instead, edited once.\n\n## The hard gate — read this before starting Phase 3\n\n**Phase 3 cannot start while Phase 2's verdict is FAIL.** This is not a\nrecommendation, it's a hard stop: no `CLAUDE.md`, no `README.md`, nothing\ngets generated for a project Phase 2 rejected. Send the project back to\nPhase 1 with the specific findings, let Phase 1 fix them, then re-run Phase\n2 **in full, from Step 1** — a partial re-audit against only the previously\nfailing items is not sufficient, because a fix to one file can introduce or\nreveal something a full re-scan would catch and a targeted one wouldn't.\n\n**PASS-WITH-WARNINGS requires an explicit user decision before Phase 3\nproceeds.** Do not silently treat a WARNING verdict as good enough to move\non. Present the warning list in Bahasa Indonesia (template and full\nreasoning in `references\u002Fsanitize-audit.md`) and get an explicit yes\u002Fno —\neither \"lanjut dengan status ini\" or \"perbaiki dulu.\" Record whichever\nanswer you get:\n\n- If this release is happening inside a `dev-kickoff-edho-ferdian`-managed\n  project (a `\u002Fproject-memory\u002F` directory exists), write the decision to\n  that project's `project-memory\u002F01-decision-register.md` — source: this\n  conversation, date, and the specific warnings accepted or the fix\n  requested.\n- Otherwise (a standalone, one-off release with no dev-kickoff project\n  context), record the decision inline in `SANITIZATION_REPORT.md`'s own\n  verdict section instead. Never proceed on a WARNING without *some*\n  durable record of who accepted the risk and why — a chat message alone\n  disappears; a file doesn't.\n\n**PASS** needs no confirmation — proceed straight to Phase 3.\n\n## This skill's Critique-Correction Loop instance\n\nPhase 1 → Phase 2 is this ecosystem's Critique-Correction Loop pattern\n(the same shape `code-review-edho-ferdian` uses between its Reviewer and\nCritic roles — see that skill's `references\u002Freflection-critique.md`),\napplied to a release pipeline instead of a code review:\n\n- Phase 1 is the **Producer** — it claims what it stripped and extracted,\n  and writes `FORK_REPORT.md` as its own account.\n- Phase 2 is the **adversarial Verifier** — it never opens `FORK_REPORT.md`\n  to decide what to scan. It re-derives every finding from the filesystem\n  and git history directly, then optionally compares its independent\n  findings against Phase 1's claims (a mismatch is itself a finding, not a\n  contradiction to paper over).\n\n**On a harness with sub-agent delegation** (Claude Code, OpenCode, Hermes\nvia its delegate_task template, ZCode's own Subagents), Phase 2 runs as\nthe `opensource-sanitizer-edho-ferdian` agent, delegated fresh after Phase\n1 completes — a real separate context, not just an instruction to\ndisregard what's already in view. \"Never trust FORK_REPORT.md\" is much\neasier to actually honor when the verifier genuinely never saw it, versus\nasking the same context that wrote it to pretend otherwise. On a harness\nwith no delegation primitive, run Phase 2 inline per\n`references\u002Fsanitize-audit.md`, and note in `SANITIZATION_REPORT.md` that\nthe independence guarantee is weaker in that mode — still re-derive every\nfinding from scratch, just without hard context isolation backing it.\n- A FAIL sends the actual file\u002Fhistory issue back to Phase 1's method,\n  never a patch applied directly by Phase 2 — Phase 2 stays read-only, full\n  stop, per its own rules in `references\u002Fsanitize-audit.md`.\n\nFull framing and the reasoning behind treating this as the same pattern\nlives at the top of `references\u002Fsanitize-audit.md` — read it there rather\nthan duplicating it here.\n\n## Workflow\n\n1. **Confirm scope with the user**: source project path, target directory\n   for the sanitized copy, intended license (don't default silently — see\n   `references\u002Fpackaging-templates.md` Step 5), and whether a GitHub repo\n   already exists (affects whether `.github\u002FISSUE_TEMPLATE\u002F` gets created).\n2. **Run Phase 1** per `references\u002Ffork-prep.md`. Report file counts,\n   secrets extracted, and internal references replaced. State plainly that\n   this report is not the release gate.\n3. **Run Phase 2** — delegate to `opensource-sanitizer-edho-ferdian` on a\n   harness that supports it, else run `references\u002Fsanitize-audit.md`\n   inline — unconditionally, on the staged copy, regardless of how\n   confident Phase 1's own report sounded. Get a verdict.\n4. **Apply the hard gate** above based on the verdict.\n5. **Run Phase 3** per `references\u002Fpackaging-templates.md` once cleared.\n   Report every file generated or enhanced, with `setup.sh` confirmed\n   executable.\n6. **Final summary to the user** (Bahasa Indonesia): what was done in each\n   phase, the Phase 2 verdict and any recorded warning decision, and where\n   every report\u002Fgenerated file landed.\n\n## Notes\n\n- `references\u002Fsecret-patterns.md` consolidates what used to be two\n  independently-drifting inline pattern lists into one shared source of\n  truth.\n\n## Rules\n\n- Never sanitize in place — always stage to a separate `TARGET_DIR` (Phase\n  1, Step 2).\n- Never let Phase 3 start on a FAIL verdict, no exceptions, no \"package it\n  anyway, fix later\" path.\n- Never silently proceed past PASS-WITH-WARNINGS — get and record an\n  explicit decision first.\n- Never trust `FORK_REPORT.md`'s claims as evidence in Phase 2 — re-derive\n  everything.\n- Keep secret\u002FPII patterns in `secret-patterns.md` only — no inline copies\n  in Phase 1 or Phase 2's own reference files.\n- Generated `CLAUDE.md` reuses this ecosystem's Execution Context Pack\n  format and stays under 100 lines — see `references\u002Fpackaging-templates.md`.\n",{"name":5,"metadata":24,"description":7},{"last_reviewed":25},"2026-10-29","main","533d32ad55c92d40fbabe93cbe21fe048598fe5a",".kiro\u002Fskills\u002Fopensource-release-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 opensource-release-edho-ferdian",{"tool":40,"command":41},"bunx","bunx skills add edhoferdian\u002FEEF --skill opensource-release-edho-ferdian",{"tool":43,"command":44},"pnpm","pnpm dlx skills add edhoferdian\u002FEEF --skill opensource-release-edho-ferdian","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.kiro\u002Fskills\u002Fopensource-release-edho-ferdian\u002FSKILL.md",true,[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Ffork-prep.md","REFERENCE","参考文档",5722,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.kiro\u002Fskills\u002Fopensource-release-edho-ferdian\u002Freferences\u002Ffork-prep.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fpackaging-templates.md",11732,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.kiro\u002Fskills\u002Fopensource-release-edho-ferdian\u002Freferences\u002Fpackaging-templates.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fsanitize-audit.md",9088,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.kiro\u002Fskills\u002Fopensource-release-edho-ferdian\u002Freferences\u002Fsanitize-audit.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fsecret-patterns.md",6351,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.kiro\u002Fskills\u002Fopensource-release-edho-ferdian\u002Freferences\u002Fsecret-patterns.md",[67,74,81,88,95,102],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"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",[],[]]