[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C94868N6MBDX7J6FZREA9Z":3,"skill-same:01M7C94868N6MBDX7J6FZREA9Z":58},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7C94868N6MBDX7J6FZREA9Z","communications-triage-edho-ferdian",null,"Triage incoming messages from any channel into four priority tiers, draft replies behind a human-approval gate, and track promises made in sent replies. Use for \"triase pesan\", \"atur inbox\", \"bantu balas email\u002Fchat\", \"klasifikasikan pesan masuk\", \"draft balasan\".","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.zcode\u002Fskills\u002Fcommunications-triage-edho-ferdian\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: communications-triage-edho-ferdian\ndescription: >-\n  Triage incoming messages from any channel into four priority tiers, draft\n  replies behind a human-approval gate, and track promises made in sent\n  replies. Use for \"triase pesan\", \"atur inbox\", \"bantu balas email\u002Fchat\",\n  \"klasifikasikan pesan masuk\", \"draft balasan\".\nmetadata:\n  last_reviewed: \"2026-09-24\"\n---\n\n# Communications Triage — Edho Ferdian Mode (Skill Edition) · v1.0\n\nYou are applying a message-triage discipline, not operating a mail client.\nThis skill is **channel-agnostic on purpose**: at the time this was written,\nno channel integration (Gmail API, Slack MCP, LINE\u002FMessenger bridge, etc.) is\nwired up anywhere in this ecosystem. Do not invent one. Do not pretend a tool\ncall exists that doesn't. What you apply here is the classification logic,\nthe reply-drafting discipline, and the follow-through tracking — the same\nlogic a human would run by hand today, and the same logic a future channel\nintegration would automate.\n\n**If the user has pasted message content directly into chat** (an email\nbody, a Slack thread, a screenshot's transcript), this skill applies fully\nto that pasted content — classify it, draft a reply, ask before anything\nresembling \"send.\" What it does not do is reach out and fetch messages from\na live inbox itself; nothing in this ecosystem is connected to one yet.\n\n## Why channel-agnostic, not \"wire up Gmail now\"\n\nBuilding a specific integration ahead of an actual connected channel would\nmean maintaining fake tool calls, or code that talks to nothing. Per this\necosystem's ground-truth ethos (see `dev-kickoff-edho-ferdian`,\n`spec-mining-edho-ferdian`): never fabricate integrations that don't exist.\nThis skill instead front-loads the part that survives any channel — the\ntiering rules, the drafting discipline, the follow-through contract — so that\nwhenever a real channel is connected (an MCP server, a CLI, an API client),\nthe only new work is the fetch\u002Fsend plumbing. The triage brain does not need\nto be rewritten.\n\n## The four tiers\n\nEvery message gets classified into **exactly one** tier. Apply the checks in\nthis order — the first match wins, don't keep evaluating after a hit:\n\n### 1. `skip` — auto-archive, no summary needed\n- Sender is a no-reply \u002F notification \u002F alert address, or an automated\n  system account (CI bots, ticketing-system bot comments, channel\n  join\u002Fleave events, delivery receipts).\n- No human is waiting on a reaction to this message.\n- **Action**: note the count if triaging a batch (\"12 pesan otomatis\n  di-skip\"), do not surface individual content.\n\n### 2. `info_only` — summarize, no reply needed\n- The user is CC'd, not the primary recipient, and no question is\n  directed at them.\n- Broadcast\u002Fannouncement content (`@channel`\u002F`@here`-style, newsletters,\n  receipts, read-only file shares).\n- Group chat chatter where the user isn't named and isn't the last\n  meaningful contributor.\n- **Action**: one-line summary per message (or per thread), nothing more.\n\n### 3. `meeting_info` — cross-reference, no free-text reply needed\n- Contains a scheduling artifact: a video-call link, a date + meeting\n  context, a room\u002Flocation share, or a calendar-invite attachment.\n- **Action**: this tier is about **reconciling**, not drafting — check it\n  against whatever calendar source is available (a connected calendar tool,\n  or the user's own statement of their schedule) and flag conflicts or\n  missing details. If no calendar source is connected, say so and surface\n  the raw scheduling info instead of guessing availability.\n\n### 4. `action_required` — draft a reply\n- A direct question awaiting an answer.\n- An explicit ask, scheduling request, or decision the user must make.\n- The user is `@mentioned` and a response is clearly expected.\n- **Action**: generate a draft reply (see below). Never send it — see the\n  approval gate.\n\n**Ambiguous cases:** when a message could plausibly fit two tiers, prefer\nthe *more attention-requiring* tier (e.g., `meeting_info` over `info_only`\nif it's unclear whether a reply is expected) — treat under-triage as the\nworse failure than a message getting slightly more attention than it needed.\n\n## Draft-reply generation guidance\n\nFor every `action_required` message:\n\n1. **Read the actual ask before drafting.** Restate to yourself what\n   specifically is being asked — a scheduling slot, a yes\u002Fno decision, a\n   piece of information, an approval. A draft that doesn't answer the real\n   question is worse than no draft.\n2. **Match tone to the relationship**, when that context is available. If\n   the user maintains their own notes on how they talk to specific people or\n   channels (a personal style file, prior message history, explicit\n   instruction in the current conversation), use it. If no such context\n   exists, default to a neutral, professional tone and say so — don't guess\n   a familiarity level you have no evidence for.\n3. **Keep commitments explicit and minimal.** A draft that promises a\n   specific date, a specific deliverable, or \"I'll get back to you by\n   Friday\" is creating an obligation — see follow-through, below. Don't let\n   a draft casually generate more promises than the user actually intends\n   to keep.\n4. **Flag uncertainty instead of hiding it.** If the draft has to guess at\n   something (e.g., availability, a fact the user hasn't confirmed), mark it\n   inline — `[VERIFY: ...]` — rather than stating it as settled.\n5. **Present the draft, don't act on it.** See the approval gate below —\n   this is non-negotiable regardless of how obviously correct the draft\n   seems.\n\n## Language routing (fixed base rule — see skill-authoring-edho-ferdian §7; this skill extends it below)\n\nTriage summaries and discussion with the user → Bahasa Indonesia (base\nrule). The drafted reply itself is this skill's own extension of the base\nrule: match the language of the thread it replies to (reply in Indonesian\nto an Indonesian message, English to an English one) — never translate the\ncorrespondent's own language into the user's, that changes what they\nactually said.\n\n## The approval gate (mandatory, no exceptions)\n\n**A draft reply is never sent automatically. Full stop.**\n\nThis mirrors the ecosystem-wide \"Explicit permission required\" rule for\nsending any message on someone's behalf (email, chat, DM, reply, calendar\ninvite) — approval must come from the user in chat, per-message, not\ninferred from an earlier approval or from how routine the message looks.\nConcretely:\n\n- Present every draft with its tier, the message it's answering, and any\n  `[VERIFY: ...]` markers, then wait for the user to approve, edit, or\n  reject it.\n- An approved draft for message A does not authorize sending draft B, even\n  if B looks similar or arrived in the same batch.\n- If a future channel integration is connected and exposes a \"send\" action,\n  that action is gated the same way any send-a-message action is gated\n  elsewhere in this ecosystem: ask, wait for a clear yes, then act. Do not\n  build or suggest an auto-send path, a \"send all approved drafts\" bulk\n  action without per-item confirmation, or a background job that sends on a\n  timer.\n- If the user says \"just send whatever you think is right\" — that is not a\n  substitute for per-message approval. Say so, and ask them to confirm each\n  draft (or explicitly batch-approve by reviewing the actual list you show\n  them, not by blanket delegation).\n\nThis is a **Reflection gate**, not a suggestion: before treating any draft\nas ready, run through the three checks above (real ask answered \u002F tone\njustified \u002F commitments minimal and flagged) and only then present it. If a\ncheck fails, fix the draft before showing it, don't show a known-flawed\ndraft and rely on the user to catch it.\n\n## Post-send follow-through\n\nThe strongest version of this enforces itself with a `PostToolUse` hook that\nphysically blocks completion until a checklist runs. No hook system is wired\ninto this ecosystem's channel-agnostic version — there is no tool call to\nintercept yet. What applies here is the **logic** such a hook would enforce,\nto be run manually today and wired into a real hook (or a future channel\nintegration's own after-send step) once one exists.\n\nAfter a reply is actually sent (by the user, having approved the draft),\ncheck whether it created any of these obligations, and if so, track them\nsomewhere durable (a todo list, a project-memory file, a calendar entry —\nwhatever this project or the user already uses):\n\n1. **A promised action** (\"I'll send X by Friday\") → becomes a tracked\n   task with a deadline, not just a sent message that's now forgotten.\n2. **A proposed meeting time** → needs a corresponding calendar entry (even\n   tentative) so it doesn't silently double-book, if a calendar is in use.\n3. **A pending response from the other side** (\"let me know if that works\")\n   → becomes a \"waiting on reply\" item with a stale-after date, so it\n   surfaces again if the other person goes quiet instead of disappearing\n   into the sent-mail void.\n4. **A relationship\u002Fcontext update** — if this ecosystem later maintains\n   per-contact notes (tone, history, open threads), the interaction gets\n   appended there so the next draft to this person has better context than\n   this one did.\n\n**The point of this section is that a sent reply is not the end of the\ntask.** A triage pass that drafts and sends replies but never checks back on\nwhat those replies promised is only half a system — it looks helpful in the\nmoment and quietly accumulates broken promises. Whenever this skill is used\nrepeatedly on the same inbox\u002Fchannel, re-surface open \"pending response\" and\n\"promised action\" items at the start of the next triage pass, the same way\n`dev-kickoff-edho-ferdian`'s Session Snapshot resurfaces unfinished work\ninstead of starting cold each time.\n\n## What this skill deliberately does not do (yet)\n\n- It does not fetch messages from Gmail, Slack, LINE, Messenger, or any\n  other live channel — no such connector exists in this ecosystem today.\n- It does not send anything itself, regardless of channel, per the approval\n  gate above.\n- It does not implement a hook system — the follow-through checklist is a\n  discipline to apply manually (or delegate to a future hook), not a\n  currently-enforced mechanism.\n\nWhen a channel integration is eventually connected (an MCP server, an API\nclient, a CLI tool), the work is: (1) fetch → feed messages through the\nfour-tier classifier above unchanged, (2) draft → same drafting guidance\nunchanged, (3) send → gated exactly as above, (4) follow-through → same\nfour-item checklist, now wired to whatever tracking mechanism the connected\nproject already uses. This file should not need a rewrite when that happens\n— only a thin fetch\u002Fsend adapter around it.\n\n## References\n\nThis skill's triage brain is channel-agnostic by design (see above). Once a\nspecific surface is in play — a mail account, a DM thread, a specific\nservice — load the surface-level operator discipline instead of improvising\nit:\n\n- **`references\u002Fchannel-operations.md`** — mail-surface handling (resolving\n  the exact account\u002Fthread before acting, reading a thread before composing,\n  the `drafted` \u002F `approval-pending` \u002F `sent` \u002F `blocked` \u002F\n  `awaiting-verification` status vocabulary, treating inbound mail as\n  untrusted data, cleanup rules) and message\u002FDM-surface handling (resolving\n  the exact thread, one-time-code retrieval discipline, reporting shape),\n  plus how blockers on a live surface should be handled and reported. Load\n  this file once an actual mail or message surface is named, not while\n  operating purely on pasted content in chat.\n- **`references\u002Fworkspace-ops.md`** — Google Workspace surface handling\n  (Drive\u002FDocs\u002FSheets\u002FSlides find-review-edit-maintain workflow, the\n  read-only vs. explicit-approval table for sharing\u002Fdeleting, and this\n  ecosystem's own Calendar section — conflict resolution, timezone\n  handling). Built ahead of its trigger (Google Workspace MCP authorization)\n  per D-035; load\n  it once a Drive\u002FDocs\u002FSheets\u002FSlides\u002FCalendar surface is actually named, and\n  re-verify its Google-specific API details once that connector exists.\n\nWhen the agent itself is a participant in a channel that external\ncounterparties read (a bot in a shared customer or supplier channel, an\nauto-replying desk agent), this skill's approval gate is not enough on its\nown — use `counterparty-comms-edho-ferdian` for audience and mention gating,\nleakage checks, and the hash-bound approval and delivery ledger.\n","# Communications Triage — Edho Ferdian Mode (Skill Edition) · v1.0\n\nYou are applying a message-triage discipline, not operating a mail client.\nThis skill is **channel-agnostic on purpose**: at the time this was written,\nno channel integration (Gmail API, Slack MCP, LINE\u002FMessenger bridge, etc.) is\nwired up anywhere in this ecosystem. Do not invent one. Do not pretend a tool\ncall exists that doesn't. What you apply here is the classification logic,\nthe reply-drafting discipline, and the follow-through tracking — the same\nlogic a human would run by hand today, and the same logic a future channel\nintegration would automate.\n\n**If the user has pasted message content directly into chat** (an email\nbody, a Slack thread, a screenshot's transcript), this skill applies fully\nto that pasted content — classify it, draft a reply, ask before anything\nresembling \"send.\" What it does not do is reach out and fetch messages from\na live inbox itself; nothing in this ecosystem is connected to one yet.\n\n## Why channel-agnostic, not \"wire up Gmail now\"\n\nBuilding a specific integration ahead of an actual connected channel would\nmean maintaining fake tool calls, or code that talks to nothing. Per this\necosystem's ground-truth ethos (see `dev-kickoff-edho-ferdian`,\n`spec-mining-edho-ferdian`): never fabricate integrations that don't exist.\nThis skill instead front-loads the part that survives any channel — the\ntiering rules, the drafting discipline, the follow-through contract — so that\nwhenever a real channel is connected (an MCP server, a CLI, an API client),\nthe only new work is the fetch\u002Fsend plumbing. The triage brain does not need\nto be rewritten.\n\n## The four tiers\n\nEvery message gets classified into **exactly one** tier. Apply the checks in\nthis order — the first match wins, don't keep evaluating after a hit:\n\n### 1. `skip` — auto-archive, no summary needed\n- Sender is a no-reply \u002F notification \u002F alert address, or an automated\n  system account (CI bots, ticketing-system bot comments, channel\n  join\u002Fleave events, delivery receipts).\n- No human is waiting on a reaction to this message.\n- **Action**: note the count if triaging a batch (\"12 pesan otomatis\n  di-skip\"), do not surface individual content.\n\n### 2. `info_only` — summarize, no reply needed\n- The user is CC'd, not the primary recipient, and no question is\n  directed at them.\n- Broadcast\u002Fannouncement content (`@channel`\u002F`@here`-style, newsletters,\n  receipts, read-only file shares).\n- Group chat chatter where the user isn't named and isn't the last\n  meaningful contributor.\n- **Action**: one-line summary per message (or per thread), nothing more.\n\n### 3. `meeting_info` — cross-reference, no free-text reply needed\n- Contains a scheduling artifact: a video-call link, a date + meeting\n  context, a room\u002Flocation share, or a calendar-invite attachment.\n- **Action**: this tier is about **reconciling**, not drafting — check it\n  against whatever calendar source is available (a connected calendar tool,\n  or the user's own statement of their schedule) and flag conflicts or\n  missing details. If no calendar source is connected, say so and surface\n  the raw scheduling info instead of guessing availability.\n\n### 4. `action_required` — draft a reply\n- A direct question awaiting an answer.\n- An explicit ask, scheduling request, or decision the user must make.\n- The user is `@mentioned` and a response is clearly expected.\n- **Action**: generate a draft reply (see below). Never send it — see the\n  approval gate.\n\n**Ambiguous cases:** when a message could plausibly fit two tiers, prefer\nthe *more attention-requiring* tier (e.g., `meeting_info` over `info_only`\nif it's unclear whether a reply is expected) — treat under-triage as the\nworse failure than a message getting slightly more attention than it needed.\n\n## Draft-reply generation guidance\n\nFor every `action_required` message:\n\n1. **Read the actual ask before drafting.** Restate to yourself what\n   specifically is being asked — a scheduling slot, a yes\u002Fno decision, a\n   piece of information, an approval. A draft that doesn't answer the real\n   question is worse than no draft.\n2. **Match tone to the relationship**, when that context is available. If\n   the user maintains their own notes on how they talk to specific people or\n   channels (a personal style file, prior message history, explicit\n   instruction in the current conversation), use it. If no such context\n   exists, default to a neutral, professional tone and say so — don't guess\n   a familiarity level you have no evidence for.\n3. **Keep commitments explicit and minimal.** A draft that promises a\n   specific date, a specific deliverable, or \"I'll get back to you by\n   Friday\" is creating an obligation — see follow-through, below. Don't let\n   a draft casually generate more promises than the user actually intends\n   to keep.\n4. **Flag uncertainty instead of hiding it.** If the draft has to guess at\n   something (e.g., availability, a fact the user hasn't confirmed), mark it\n   inline — `[VERIFY: ...]` — rather than stating it as settled.\n5. **Present the draft, don't act on it.** See the approval gate below —\n   this is non-negotiable regardless of how obviously correct the draft\n   seems.\n\n## Language routing (fixed base rule — see skill-authoring-edho-ferdian §7; this skill extends it below)\n\nTriage summaries and discussion with the user → Bahasa Indonesia (base\nrule). The drafted reply itself is this skill's own extension of the base\nrule: match the language of the thread it replies to (reply in Indonesian\nto an Indonesian message, English to an English one) — never translate the\ncorrespondent's own language into the user's, that changes what they\nactually said.\n\n## The approval gate (mandatory, no exceptions)\n\n**A draft reply is never sent automatically. Full stop.**\n\nThis mirrors the ecosystem-wide \"Explicit permission required\" rule for\nsending any message on someone's behalf (email, chat, DM, reply, calendar\ninvite) — approval must come from the user in chat, per-message, not\ninferred from an earlier approval or from how routine the message looks.\nConcretely:\n\n- Present every draft with its tier, the message it's answering, and any\n  `[VERIFY: ...]` markers, then wait for the user to approve, edit, or\n  reject it.\n- An approved draft for message A does not authorize sending draft B, even\n  if B looks similar or arrived in the same batch.\n- If a future channel integration is connected and exposes a \"send\" action,\n  that action is gated the same way any send-a-message action is gated\n  elsewhere in this ecosystem: ask, wait for a clear yes, then act. Do not\n  build or suggest an auto-send path, a \"send all approved drafts\" bulk\n  action without per-item confirmation, or a background job that sends on a\n  timer.\n- If the user says \"just send whatever you think is right\" — that is not a\n  substitute for per-message approval. Say so, and ask them to confirm each\n  draft (or explicitly batch-approve by reviewing the actual list you show\n  them, not by blanket delegation).\n\nThis is a **Reflection gate**, not a suggestion: before treating any draft\nas ready, run through the three checks above (real ask answered \u002F tone\njustified \u002F commitments minimal and flagged) and only then present it. If a\ncheck fails, fix the draft before showing it, don't show a known-flawed\ndraft and rely on the user to catch it.\n\n## Post-send follow-through\n\nThe strongest version of this enforces itself with a `PostToolUse` hook that\nphysically blocks completion until a checklist runs. No hook system is wired\ninto this ecosystem's channel-agnostic version — there is no tool call to\nintercept yet. What applies here is the **logic** such a hook would enforce,\nto be run manually today and wired into a real hook (or a future channel\nintegration's own after-send step) once one exists.\n\nAfter a reply is actually sent (by the user, having approved the draft),\ncheck whether it created any of these obligations, and if so, track them\nsomewhere durable (a todo list, a project-memory file, a calendar entry —\nwhatever this project or the user already uses):\n\n1. **A promised action** (\"I'll send X by Friday\") → becomes a tracked\n   task with a deadline, not just a sent message that's now forgotten.\n2. **A proposed meeting time** → needs a corresponding calendar entry (even\n   tentative) so it doesn't silently double-book, if a calendar is in use.\n3. **A pending response from the other side** (\"let me know if that works\")\n   → becomes a \"waiting on reply\" item with a stale-after date, so it\n   surfaces again if the other person goes quiet instead of disappearing\n   into the sent-mail void.\n4. **A relationship\u002Fcontext update** — if this ecosystem later maintains\n   per-contact notes (tone, history, open threads), the interaction gets\n   appended there so the next draft to this person has better context than\n   this one did.\n\n**The point of this section is that a sent reply is not the end of the\ntask.** A triage pass that drafts and sends replies but never checks back on\nwhat those replies promised is only half a system — it looks helpful in the\nmoment and quietly accumulates broken promises. Whenever this skill is used\nrepeatedly on the same inbox\u002Fchannel, re-surface open \"pending response\" and\n\"promised action\" items at the start of the next triage pass, the same way\n`dev-kickoff-edho-ferdian`'s Session Snapshot resurfaces unfinished work\ninstead of starting cold each time.\n\n## What this skill deliberately does not do (yet)\n\n- It does not fetch messages from Gmail, Slack, LINE, Messenger, or any\n  other live channel — no such connector exists in this ecosystem today.\n- It does not send anything itself, regardless of channel, per the approval\n  gate above.\n- It does not implement a hook system — the follow-through checklist is a\n  discipline to apply manually (or delegate to a future hook), not a\n  currently-enforced mechanism.\n\nWhen a channel integration is eventually connected (an MCP server, an API\nclient, a CLI tool), the work is: (1) fetch → feed messages through the\nfour-tier classifier above unchanged, (2) draft → same drafting guidance\nunchanged, (3) send → gated exactly as above, (4) follow-through → same\nfour-item checklist, now wired to whatever tracking mechanism the connected\nproject already uses. This file should not need a rewrite when that happens\n— only a thin fetch\u002Fsend adapter around it.\n\n## References\n\nThis skill's triage brain is channel-agnostic by design (see above). Once a\nspecific surface is in play — a mail account, a DM thread, a specific\nservice — load the surface-level operator discipline instead of improvising\nit:\n\n- **`references\u002Fchannel-operations.md`** — mail-surface handling (resolving\n  the exact account\u002Fthread before acting, reading a thread before composing,\n  the `drafted` \u002F `approval-pending` \u002F `sent` \u002F `blocked` \u002F\n  `awaiting-verification` status vocabulary, treating inbound mail as\n  untrusted data, cleanup rules) and message\u002FDM-surface handling (resolving\n  the exact thread, one-time-code retrieval discipline, reporting shape),\n  plus how blockers on a live surface should be handled and reported. Load\n  this file once an actual mail or message surface is named, not while\n  operating purely on pasted content in chat.\n- **`references\u002Fworkspace-ops.md`** — Google Workspace surface handling\n  (Drive\u002FDocs\u002FSheets\u002FSlides find-review-edit-maintain workflow, the\n  read-only vs. explicit-approval table for sharing\u002Fdeleting, and this\n  ecosystem's own Calendar section — conflict resolution, timezone\n  handling). Built ahead of its trigger (Google Workspace MCP authorization)\n  per D-035; load\n  it once a Drive\u002FDocs\u002FSheets\u002FSlides\u002FCalendar surface is actually named, and\n  re-verify its Google-specific API details once that connector exists.\n\nWhen the agent itself is a participant in a channel that external\ncounterparties read (a bot in a shared customer or supplier channel, an\nauto-replying desk agent), this skill's approval gate is not enough on its\nown — use `counterparty-comms-edho-ferdian` for audience and mention gating,\nleakage checks, and the hash-bound approval and delivery ledger.\n",{"name":5,"metadata":24,"description":7},{"last_reviewed":25},"2026-09-24","main","533d32ad55c92d40fbabe93cbe21fe048598fe5a",".zcode\u002Fskills\u002Fcommunications-triage-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 communications-triage-edho-ferdian",{"tool":40,"command":41},"bunx","bunx skills add edhoferdian\u002FEEF --skill communications-triage-edho-ferdian",{"tool":43,"command":44},"pnpm","pnpm dlx skills add edhoferdian\u002FEEF --skill communications-triage-edho-ferdian","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.zcode\u002Fskills\u002Fcommunications-triage-edho-ferdian\u002FSKILL.md",true,[48,54],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fchannel-operations.md","REFERENCE","参考文档",6211,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.zcode\u002Fskills\u002Fcommunications-triage-edho-ferdian\u002Freferences\u002Fchannel-operations.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fworkspace-ops.md",10247,"https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002F.zcode\u002Fskills\u002Fcommunications-triage-edho-ferdian\u002Freferences\u002Fworkspace-ops.md",[59,66,73,80,87,94],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7C9FY2EWE5NB7M3YW0KJX62","video-style-edho-ferdian","Measure a reference video's look and pacing (colour grade as a 3D LUT, cut rhythm, overlays) and reproduce it: grade, cut and composite new footage, verify numerically, hand off an NLE timeline. Use for \"tiru look video ini\", \"samakan grading\", \"bikin video dengan gaya referensi\", \"LUT dari referensi\", \"cut rhythm\".","https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-style-edho-ferdian\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7C9FT74P7JXGQ73116B9WS1","test-authoring-edho-ferdian","Write unit and component tests well: React Testing Library, pytest, Go and Vue, plus regression-test patterns. Use for \"tulis test untuk component ini\", \"bagaimana test hook ini\", \"test yang bagus untuk fitur X\", \"tulis test pytest\u002FGo\u002FVue\", or dev-kickoff's TEST stage.","https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002Fskills\u002Ftest-authoring-edho-ferdian\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7C9FMPE9W76FS7S8ZZ48ARE","system-design-edho-ferdian","Mid-project architecture decisions: ADRs, trade-off analysis, non-functional requirements, scaling tiers and blast radius. Use for \"desain arsitektur\", \"keputusan teknis besar\", \"bikin ADR\", \"trade-off antara X dan Y\", \"microservices atau monolith\", \"apa yang rusak kalau X diubah\", or a capacity question.","https:\u002F\u002Fgithub.com\u002Fedhoferdian\u002FEEF\u002Fblob\u002Fmain\u002Fskills\u002Fsystem-design-edho-ferdian\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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",[],[]]