[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ME4TK4CE2VHH65S1518EWY":3,"skill-same:01M6ME4TK4CE2VHH65S1518EWY":73},{"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":23,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6ME4TK4CE2VHH65S1518EWY","document",null,"Record a decision, document existing code, or file a supplied research material, in free text; no first word is a mode. Use for 'we decided', 'record this decision', 'document why we chose X', 'make it our standard', 'draft an RFC', 'should we switch to Y' proposals, 'resolve the RFC', 'we accepted the proposal', 'document the auth module', 'capture how the payment system works', reference material, how-to instructions, a repeated agent procedure, a user flow with examples over an existing spec, or a finished report or one external material already in hand. Name any document type inside the subject — journey, prd, idea, or cpat included — to get exactly that type. Planning a feature, an investigation not yet done, or an intended user journey the request asks to plan ('plan the onboarding journey') → \u002Farchcore:plan. Checking docs against code or docs health → \u002Farchcore:review.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchcore-ai\u002Farchcore\u002Fskills\u002Fdocument\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"idea","request","mode","hand","make","proposal","free","get","done","journey","review","decision","text","plan","why","how","flow","code","auth","2026-11-10 10:12:30",false,"---\nname: document\nargument-hint: \"[subject]\"\ndescription: \"Record a decision, document existing code, or file a supplied research material, in free text; no first word is a mode. Use for 'we decided', 'record this decision', 'document why we chose X', 'make it our standard', 'draft an RFC', 'should we switch to Y' proposals, 'resolve the RFC', 'we accepted the proposal', 'document the auth module', 'capture how the payment system works', reference material, how-to instructions, a repeated agent procedure, a user flow with examples over an existing spec, or a finished report or one external material already in hand. Name any document type inside the subject — journey, prd, idea, or cpat included — to get exactly that type. Planning a feature, an investigation not yet done, or an intended user journey the request asks to plan ('plan the onboarding journey') → \u002Farchcore:plan. Checking docs against code or docs health → \u002Farchcore:review.\"\n---\n\n# \u002Farchcore:document\n\nRecord the present state: a technical decision, existing code, or a supplied\nresearch material. Context resolution (`skills\u002F_shared\u002Fgate-contract.md`,\nsection Context resolution) classifies the request and finds the present owner;\na gate inside the selected track selects the document type. Write affinity: knowledge\ntypes; a filed `research` and the decision cascade's `plan` belong to vision.\nThe standard cascade can add a `cpat` (experience). A type the user names\nexplicitly keeps its own category (Named type below).\n\nCommand tense: `\u002Farchcore:plan` declares a future canon delta, `\u002Farchcore:document`\nrecords the present state — including work that shipped without a plan — and\n`\u002Farchcore:review` reconciles a past declared delta. Claim vocabulary:\n`skills\u002F_shared\u002Fdelta-routing.md`.\n\nLoad `skills\u002F_shared\u002Fgate-contract.md` and `skills\u002F_shared\u002Felicitation-contract.md` before executing any gate.\n\n## Tracks\n\n| Classification | Track and entry | Types the entry gate selects |\n|---|---|---|\n| decision | `skills\u002F_shared\u002Ftracks\u002Fdecision.md`, `decision.classify` | `adr`, `rfc`; `rule` through the standard cascade; an existing `rfc` draft on the topic → `decision.resolve`, which records an `adr` on an accepted verdict |\n| code-doc | `skills\u002F_shared\u002Ftracks\u002Fdescribe.md`, `describe.read` | `spec`, `guide`, `task-type`, `scenario`, `doc` |\n| research material | `skills\u002F_shared\u002Ftracks\u002Fresearch.md`, `research.frame` | `research`, `rnd` by the closing test; one external material → `evidence` |\n\nNo first word is a mode. When the subject text names a type (`skills\u002F_shared\u002Fgate-contract.md`,\nEntry terms) that the selected track produces, the selecting gate treats that type as settled and asks no\ntype question: `record an rfc for gRPC` reaches the RFC branch; a leading type\nslug takes the Named type path. No track produces a `journey`; a `journey` comes\nfrom `\u002Farchcore:plan` or from the named-type path below.\n\n### Named type\n\nWHEN the first word of the subject is a kernel document type slug, or the subject writes a slug in\nbackticks, the named type wins over routing (`explicit-type-request-wins.adr`).\nA slug elsewhere in plain topic text names no type here; inside a track the gate\ncontract's naming rule still applies. When two slugs qualify, the\nfirst one wins.\n\n1. IF a document track produces the named type as its own product, THEN enter that track with the type settled: `adr`, `rfc` → decision; `spec`, `doc`, `guide`, `scenario` → describe; `research`, `rnd`, `evidence` → research.\n2. IF no document track produces it as its own product — `rule`, `journey`, `prd`, `idea`, `plan`, `cpat`, `task-type`, `mrd`, `brd`, `urd`, `brs`, `strs`, `syrs`, `srs` — THEN compose it directly per the steps below. A `rule` comes from the decision track only as a cascade member behind an `adr`; a named `rule` needs neither.\n3. Apply the compatibility file for the type before the first MCP call that names it.\n4. Search `.archcore\u002F` for a local document of that type on the topic; when one exists, offer to update it instead.\n5. Load `skills\u002F_shared\u002F\u003Ctype>-contract.md` when that file exists, and `skills\u002F_shared\u002Fprecision-rules.md`.\n6. WHEN no contract file exists, compose the sections of the `create_document` template for that type.\n7. Create the document with `status: draft` through `create_document`.\n8. Evaluate relations through `skills\u002F_shared\u002Frelation-authoring.md`.\n9. WHEN the type's routing condition fails, report it in one result line naming the better-fitting type; ask no question.\n\nExamples of a failed routing condition: a `journey` where a covering `spec`\nexists (`scenario` fits), a `plan` composed without the conductor (it\ncarries no Declared Delta), or a `rule` with no `adr` recording its reason.\n\n## When to use\n\n- \"We decided to go with microservices\" — settled decision\n- \"Record the decision to use PostgreSQL\"\n- \"Document why we chose JWT over sessions\"\n- \"Make this our team standard for error handling\"\n- \"Draft an RFC for switching from REST to gRPC\"\n- \"Should we switch to Kubernetes?\" — open choice: one question offers an `adr`, an `rfc` (resolved into an `adr` later), or investigating first\n- \"We accepted the proposal — resolve the RFC\" — proposal resolution\n- \"Document the auth module\"\n- \"Capture how the payment system works\"\n- \"Create reference docs for the config system\" — reference material\n- \"Write a guide for the release process\" — how-to instructions\n- \"Write down how the agent cuts a release\" — a repeated agent procedure (`task-type`)\n- \"Scenario for checkout over the checkout spec\" — a user flow with examples over an existing spec\n- \"File this benchmark report\" — a ready investigation\n- \"File this vendor PDF as evidence\" — one external material\n\n**Not document:**\n\n- Planning a feature, an initiative, or an intended user journey the request does not name as a `journey` → `\u002Farchcore:plan`\n- Checking documents against code, reviewing branch changes, or a documentation audit → `\u002Farchcore:review`\n- First-time setup → `\u002Farchcore:init`\n\n## Routing table\n\n| Signal | Route |\n|---|---|\n| No arguments, one draft with a state block this command resumes | → resume it |\n| No arguments, branch changes or supplied material name a present fact | → a start menu of at most four owners, each with its evidence, the smallest owner first |\n| No arguments and no reliable signal | → ask one question: what present fact or subject to record |\n| The subject names a document type that no document track produces | → Named type, direct composition |\n| Decision signals: \"we decided\", \"record this decision\", \"document why we chose X\", \"make it our standard\", \"draft an RFC\", a \"should we switch to Y\" question (the decision track asks which exit). A bare \"compare X vs Y\" with no proposed target belongs to `\u002Farchcore:plan`'s research track; a proposal to add a new capability with no named technical target (\"should we add caching?\") is feature framing → `\u002Farchcore:plan` | → decision track — `skills\u002F_shared\u002Ftracks\u002Fdecision.md`, entry at `decision.classify` |\n| Resolution signals: \"resolve the RFC\", \"we accepted the proposal\", \"reject the RFC\" — an `rfc` draft exists on the topic | → decision track — `skills\u002F_shared\u002Ftracks\u002Fdecision.md`, entry at `decision.resolve` |\n| Code-doc signals: \"document the auth module\", \"capture how the payment system works\", reference material (registry, glossary, lookup), how-to instructions, a repeated agent procedure, a user flow with examples over an existing `spec` | → describe track — `skills\u002F_shared\u002Ftracks\u002Fdescribe.md`, entry at `describe.read` |\n| Research-material signals: a supplied investigation report, benchmark, transcript, or vendor document to file as is | → research track — `skills\u002F_shared\u002Ftracks\u002Fresearch.md`, entry at `research.frame` |\n| Unclear | → git investigation, then one classifying question (Step 3) |\n\n## Execution\n\n### Step 1: Ground\n\nApply `skills\u002F_shared\u002Fresearch-compatibility.md` under its condition 1 — a\nrequest or type naming `research` or `evidence`, the research track, or a\ngrounding result of either type. If this skill has no shell tool and no probe\nresult was supplied, report `needs-vocabulary-probe` with the helper path and\nstop before the first MCP call that names either type.\nBefore delegating research or evidence work, pass the current vocabulary probe\nresult and absolute plugin root to the assistant. If the assistant returns\n`needs-vocabulary-probe`, run the helper and resume the same task.\nBefore delegating any other document write or relation work, pass the absolute\nplugin root to the assistant. The assistant reads\n`skills\u002F_shared\u002Frelation-authoring.md` under that root.\nApply `skills\u002F_shared\u002Factor-subject-compatibility.md` under its own condition 1 —\na request whose subject names `scenario` or `journey`, or a grounding result of\neither type. When that probe returns `yes`, add `scenario` and `journey` to the\ntype filter below. On older engines, keep the legacy filter; a request to\ndescribe code whose subject names `scenario` then reports the required version\nand exits without a write.\nWhen the probe returns `yes`, add `research` and `evidence` to the type filter\nbelow. On older engines, keep the legacy filter.\n\nSearch `.archcore\u002F` on the request topic across all three categories — vision,\nknowledge, experience. Do not exclude a category from reads. Pass a type filter\nmatched to this command's moment (`adr`, `rfc`, `spec`, `doc`, `guide`, `rule`,\nplus `rnd` as decision evidence, and `research` and `evidence` when the probe returned `yes`) instead of relying on the global type ranking. When a found document carries\n`implements`, `depends_on`, or `related` relations, pull the linked documents one hop across\ncategories. Duplicate handling lives in the tracks' check-existing gates — do\nnot resolve duplicates here.\n\nWHEN a found draft on the topic carries an `archcore:track` state block,\nresume it per the resume rules in `skills\u002F_shared\u002Fgate-contract.md` instead of\nopening a new track; a block this command does not resume follows resume\nrules 8 and 9 there.\n\nIf the session root holds no `.archcore\u002F`, follow\n`skills\u002F_shared\u002Ftarget-project.md`, section Projects without `.archcore\u002F`: name\nthe roots the session recap listed, ask which project to use or whether to\ninitialize the session root, and do not call `mcp__archcore__init_project`\nbefore the answer. If `.archcore\u002F` exists\nbut contains no documents, proceed on outer-context grounding and report that\nzero documents were found.\n\n**Global sources.** If a `mcp__archcore__list_documents` \u002F\n`mcp__archcore__search_documents` result has `source_kind: \"global\"`, load `skills\u002F_shared\u002Fglobals.md`. Also load it when a\n`search_documents` response's `coverage` names a source other than `\"local\"` —\neven when `results` is empty: the empty page is exactly where that file's retry\nladder applies. Edit a global document only through its source project, per that\nfile's write convention, and never join a local and a global document with\n`add_relation`. Absent any global match, proceed as usual.\n\n### Step 2: Resolve context\n\nBuild the context record per `skills\u002F_shared\u002Fgate-contract.md`, section Context\nresolution. IF the subject names a type per Named type above, THEN apply Named\ntype first. IF accepted canon conflicts with the code the request describes,\nTHEN report the conflict before any write.\n\n### Step 3: Classify\n\nClassify the target as resolution, decision, code-doc, research material, or unclear:\n\n- **Resolution** — the request names a verdict on an existing open proposal\n  (resolution signals above) and an `rfc` draft on the topic exists → decision\n  track at `decision.resolve`. Check this before Decision: wording that also\n  reads as a settled-decision signal (\"we accepted the proposal\") routes here\n  whenever a matching `rfc` draft exists.\n- **Decision** — the request records a settled choice or an open proposal\n  (decision signals above) → decision track at `decision.classify`, which\n  selects `adr`, `rfc`, or the standard outcome. A type name in the subject\n  (`adr`, `rfc`, `rule`) satisfies that gate's `skip_when`.\n- **Code-doc** — the request describes existing code, reference material, a\n  procedure, or a user flow over an existing `spec` (code-doc signals above) →\n  describe track at `describe.read`. `describe.read` records\n  `features\u002F*.feature` files as evidence when present; a `scenario` with no\n  covering `spec` routes to the earliest gate that produces the `spec` per\n  `skills\u002F_shared\u002Fgate-contract.md`.\n- **Research material** — the request supplies a ready report or one external\n  material to file (research-material signals above) → research track at\n  `research.frame`;\n  the supplied report satisfies frame inputs without an interview (investigation versus one external material:\n  `skills\u002F_shared\u002Fgate-contract.md`, Entry terms), and the closing test selects\n  the type — a report that ends in a recommendation is an `rnd`, a report that\n  covers a scope is a `research`. One external material with no investigation\n  enters `research.gather` as standalone evidence, records the request in the\n  evidence draft's Clarifications, and exits after gather. Follow the\n  compatibility contract's no-write exit when the type is unsupported.\n- **No material** — the request asks an unanswered question, including a bare\n  \"compare X and Y\" with no proposed target, and supplies\n  neither a report nor a material → write nothing and name `\u002Farchcore:plan\n  \u003Ctopic>` for a new investigation.\n- **Unclear** — inspect git state and the working tree first: recent commits and\n  changed files are evidence of what the user has been working on. If the\n  evidence still supports both readings, ask one classifying question — \"Is this\n  a decision to record or existing code to document?\" — with the recommendation\n  drawn from the git evidence.\n\n### Step 4: Execute the track\n\nRun the selected track gate by gate per `skills\u002F_shared\u002Fgate-contract.md`. The\ntrack owns check-existing, per-gate elicitation, composition, and relation\nwiring.\n\nQuestion budget: the ceiling of 5 questions per invocation in\n`skills\u002F_shared\u002Felicitation-contract.md`.\n\n## Result\n\nReport the produced documents grouped by category:\n\n- **knowledge** — `adr`, `rfc`, `spec`, `doc`, `guide`, `rule`, `evidence`, `scenario`\n- **vision** — `research` (scope-covering report), `rnd` (recommendation-closed report, or compatibility fallback), `plan` (architecture cascade)\n- **experience** — `task-type` (repeated agent procedure), `cpat` (standard cascade opt-in)\n- any category — a type composed on the Named type path, with its routing-condition line when one failed\n\nList each document's path and relation edges. Name tracks and steps in plain\nwords; do not print a gate address of the form `\u003Ctrack>.\u003Cstage>`. Close with one\nrecommended next action naming only `\u002Farchcore:plan`, `\u002Farchcore:review`, or a\nrepeat `\u002Farchcore:document` invocation with its subject. WHEN a gate stopped on a\nblocking exit check, the next action is the resume command for that draft.\nWHEN the run created drafts other than an `rfc` and no `plan` covers them, the\nnext action is `\u002Farchcore:review`, which offers their acceptance. An `rfc`\nresolves through `\u002Farchcore:document resolve the \u003Crfc title> RFC`.\n","# \u002Farchcore:document\n\nRecord the present state: a technical decision, existing code, or a supplied\nresearch material. Context resolution (`skills\u002F_shared\u002Fgate-contract.md`,\nsection Context resolution) classifies the request and finds the present owner;\na gate inside the selected track selects the document type. Write affinity: knowledge\ntypes; a filed `research` and the decision cascade's `plan` belong to vision.\nThe standard cascade can add a `cpat` (experience). A type the user names\nexplicitly keeps its own category (Named type below).\n\nCommand tense: `\u002Farchcore:plan` declares a future canon delta, `\u002Farchcore:document`\nrecords the present state — including work that shipped without a plan — and\n`\u002Farchcore:review` reconciles a past declared delta. Claim vocabulary:\n`skills\u002F_shared\u002Fdelta-routing.md`.\n\nLoad `skills\u002F_shared\u002Fgate-contract.md` and `skills\u002F_shared\u002Felicitation-contract.md` before executing any gate.\n\n## Tracks\n\n| Classification | Track and entry | Types the entry gate selects |\n|---|---|---|\n| decision | `skills\u002F_shared\u002Ftracks\u002Fdecision.md`, `decision.classify` | `adr`, `rfc`; `rule` through the standard cascade; an existing `rfc` draft on the topic → `decision.resolve`, which records an `adr` on an accepted verdict |\n| code-doc | `skills\u002F_shared\u002Ftracks\u002Fdescribe.md`, `describe.read` | `spec`, `guide`, `task-type`, `scenario`, `doc` |\n| research material | `skills\u002F_shared\u002Ftracks\u002Fresearch.md`, `research.frame` | `research`, `rnd` by the closing test; one external material → `evidence` |\n\nNo first word is a mode. When the subject text names a type (`skills\u002F_shared\u002Fgate-contract.md`,\nEntry terms) that the selected track produces, the selecting gate treats that type as settled and asks no\ntype question: `record an rfc for gRPC` reaches the RFC branch; a leading type\nslug takes the Named type path. No track produces a `journey`; a `journey` comes\nfrom `\u002Farchcore:plan` or from the named-type path below.\n\n### Named type\n\nWHEN the first word of the subject is a kernel document type slug, or the subject writes a slug in\nbackticks, the named type wins over routing (`explicit-type-request-wins.adr`).\nA slug elsewhere in plain topic text names no type here; inside a track the gate\ncontract's naming rule still applies. When two slugs qualify, the\nfirst one wins.\n\n1. IF a document track produces the named type as its own product, THEN enter that track with the type settled: `adr`, `rfc` → decision; `spec`, `doc`, `guide`, `scenario` → describe; `research`, `rnd`, `evidence` → research.\n2. IF no document track produces it as its own product — `rule`, `journey`, `prd`, `idea`, `plan`, `cpat`, `task-type`, `mrd`, `brd`, `urd`, `brs`, `strs`, `syrs`, `srs` — THEN compose it directly per the steps below. A `rule` comes from the decision track only as a cascade member behind an `adr`; a named `rule` needs neither.\n3. Apply the compatibility file for the type before the first MCP call that names it.\n4. Search `.archcore\u002F` for a local document of that type on the topic; when one exists, offer to update it instead.\n5. Load `skills\u002F_shared\u002F\u003Ctype>-contract.md` when that file exists, and `skills\u002F_shared\u002Fprecision-rules.md`.\n6. WHEN no contract file exists, compose the sections of the `create_document` template for that type.\n7. Create the document with `status: draft` through `create_document`.\n8. Evaluate relations through `skills\u002F_shared\u002Frelation-authoring.md`.\n9. WHEN the type's routing condition fails, report it in one result line naming the better-fitting type; ask no question.\n\nExamples of a failed routing condition: a `journey` where a covering `spec`\nexists (`scenario` fits), a `plan` composed without the conductor (it\ncarries no Declared Delta), or a `rule` with no `adr` recording its reason.\n\n## When to use\n\n- \"We decided to go with microservices\" — settled decision\n- \"Record the decision to use PostgreSQL\"\n- \"Document why we chose JWT over sessions\"\n- \"Make this our team standard for error handling\"\n- \"Draft an RFC for switching from REST to gRPC\"\n- \"Should we switch to Kubernetes?\" — open choice: one question offers an `adr`, an `rfc` (resolved into an `adr` later), or investigating first\n- \"We accepted the proposal — resolve the RFC\" — proposal resolution\n- \"Document the auth module\"\n- \"Capture how the payment system works\"\n- \"Create reference docs for the config system\" — reference material\n- \"Write a guide for the release process\" — how-to instructions\n- \"Write down how the agent cuts a release\" — a repeated agent procedure (`task-type`)\n- \"Scenario for checkout over the checkout spec\" — a user flow with examples over an existing spec\n- \"File this benchmark report\" — a ready investigation\n- \"File this vendor PDF as evidence\" — one external material\n\n**Not document:**\n\n- Planning a feature, an initiative, or an intended user journey the request does not name as a `journey` → `\u002Farchcore:plan`\n- Checking documents against code, reviewing branch changes, or a documentation audit → `\u002Farchcore:review`\n- First-time setup → `\u002Farchcore:init`\n\n## Routing table\n\n| Signal | Route |\n|---|---|\n| No arguments, one draft with a state block this command resumes | → resume it |\n| No arguments, branch changes or supplied material name a present fact | → a start menu of at most four owners, each with its evidence, the smallest owner first |\n| No arguments and no reliable signal | → ask one question: what present fact or subject to record |\n| The subject names a document type that no document track produces | → Named type, direct composition |\n| Decision signals: \"we decided\", \"record this decision\", \"document why we chose X\", \"make it our standard\", \"draft an RFC\", a \"should we switch to Y\" question (the decision track asks which exit). A bare \"compare X vs Y\" with no proposed target belongs to `\u002Farchcore:plan`'s research track; a proposal to add a new capability with no named technical target (\"should we add caching?\") is feature framing → `\u002Farchcore:plan` | → decision track — `skills\u002F_shared\u002Ftracks\u002Fdecision.md`, entry at `decision.classify` |\n| Resolution signals: \"resolve the RFC\", \"we accepted the proposal\", \"reject the RFC\" — an `rfc` draft exists on the topic | → decision track — `skills\u002F_shared\u002Ftracks\u002Fdecision.md`, entry at `decision.resolve` |\n| Code-doc signals: \"document the auth module\", \"capture how the payment system works\", reference material (registry, glossary, lookup), how-to instructions, a repeated agent procedure, a user flow with examples over an existing `spec` | → describe track — `skills\u002F_shared\u002Ftracks\u002Fdescribe.md`, entry at `describe.read` |\n| Research-material signals: a supplied investigation report, benchmark, transcript, or vendor document to file as is | → research track — `skills\u002F_shared\u002Ftracks\u002Fresearch.md`, entry at `research.frame` |\n| Unclear | → git investigation, then one classifying question (Step 3) |\n\n## Execution\n\n### Step 1: Ground\n\nApply `skills\u002F_shared\u002Fresearch-compatibility.md` under its condition 1 — a\nrequest or type naming `research` or `evidence`, the research track, or a\ngrounding result of either type. If this skill has no shell tool and no probe\nresult was supplied, report `needs-vocabulary-probe` with the helper path and\nstop before the first MCP call that names either type.\nBefore delegating research or evidence work, pass the current vocabulary probe\nresult and absolute plugin root to the assistant. If the assistant returns\n`needs-vocabulary-probe`, run the helper and resume the same task.\nBefore delegating any other document write or relation work, pass the absolute\nplugin root to the assistant. The assistant reads\n`skills\u002F_shared\u002Frelation-authoring.md` under that root.\nApply `skills\u002F_shared\u002Factor-subject-compatibility.md` under its own condition 1 —\na request whose subject names `scenario` or `journey`, or a grounding result of\neither type. When that probe returns `yes`, add `scenario` and `journey` to the\ntype filter below. On older engines, keep the legacy filter; a request to\ndescribe code whose subject names `scenario` then reports the required version\nand exits without a write.\nWhen the probe returns `yes`, add `research` and `evidence` to the type filter\nbelow. On older engines, keep the legacy filter.\n\nSearch `.archcore\u002F` on the request topic across all three categories — vision,\nknowledge, experience. Do not exclude a category from reads. Pass a type filter\nmatched to this command's moment (`adr`, `rfc`, `spec`, `doc`, `guide`, `rule`,\nplus `rnd` as decision evidence, and `research` and `evidence` when the probe returned `yes`) instead of relying on the global type ranking. When a found document carries\n`implements`, `depends_on`, or `related` relations, pull the linked documents one hop across\ncategories. Duplicate handling lives in the tracks' check-existing gates — do\nnot resolve duplicates here.\n\nWHEN a found draft on the topic carries an `archcore:track` state block,\nresume it per the resume rules in `skills\u002F_shared\u002Fgate-contract.md` instead of\nopening a new track; a block this command does not resume follows resume\nrules 8 and 9 there.\n\nIf the session root holds no `.archcore\u002F`, follow\n`skills\u002F_shared\u002Ftarget-project.md`, section Projects without `.archcore\u002F`: name\nthe roots the session recap listed, ask which project to use or whether to\ninitialize the session root, and do not call `mcp__archcore__init_project`\nbefore the answer. If `.archcore\u002F` exists\nbut contains no documents, proceed on outer-context grounding and report that\nzero documents were found.\n\n**Global sources.** If a `mcp__archcore__list_documents` \u002F\n`mcp__archcore__search_documents` result has `source_kind: \"global\"`, load `skills\u002F_shared\u002Fglobals.md`. Also load it when a\n`search_documents` response's `coverage` names a source other than `\"local\"` —\neven when `results` is empty: the empty page is exactly where that file's retry\nladder applies. Edit a global document only through its source project, per that\nfile's write convention, and never join a local and a global document with\n`add_relation`. Absent any global match, proceed as usual.\n\n### Step 2: Resolve context\n\nBuild the context record per `skills\u002F_shared\u002Fgate-contract.md`, section Context\nresolution. IF the subject names a type per Named type above, THEN apply Named\ntype first. IF accepted canon conflicts with the code the request describes,\nTHEN report the conflict before any write.\n\n### Step 3: Classify\n\nClassify the target as resolution, decision, code-doc, research material, or unclear:\n\n- **Resolution** — the request names a verdict on an existing open proposal\n  (resolution signals above) and an `rfc` draft on the topic exists → decision\n  track at `decision.resolve`. Check this before Decision: wording that also\n  reads as a settled-decision signal (\"we accepted the proposal\") routes here\n  whenever a matching `rfc` draft exists.\n- **Decision** — the request records a settled choice or an open proposal\n  (decision signals above) → decision track at `decision.classify`, which\n  selects `adr`, `rfc`, or the standard outcome. A type name in the subject\n  (`adr`, `rfc`, `rule`) satisfies that gate's `skip_when`.\n- **Code-doc** — the request describes existing code, reference material, a\n  procedure, or a user flow over an existing `spec` (code-doc signals above) →\n  describe track at `describe.read`. `describe.read` records\n  `features\u002F*.feature` files as evidence when present; a `scenario` with no\n  covering `spec` routes to the earliest gate that produces the `spec` per\n  `skills\u002F_shared\u002Fgate-contract.md`.\n- **Research material** — the request supplies a ready report or one external\n  material to file (research-material signals above) → research track at\n  `research.frame`;\n  the supplied report satisfies frame inputs without an interview (investigation versus one external material:\n  `skills\u002F_shared\u002Fgate-contract.md`, Entry terms), and the closing test selects\n  the type — a report that ends in a recommendation is an `rnd`, a report that\n  covers a scope is a `research`. One external material with no investigation\n  enters `research.gather` as standalone evidence, records the request in the\n  evidence draft's Clarifications, and exits after gather. Follow the\n  compatibility contract's no-write exit when the type is unsupported.\n- **No material** — the request asks an unanswered question, including a bare\n  \"compare X and Y\" with no proposed target, and supplies\n  neither a report nor a material → write nothing and name `\u002Farchcore:plan\n  \u003Ctopic>` for a new investigation.\n- **Unclear** — inspect git state and the working tree first: recent commits and\n  changed files are evidence of what the user has been working on. If the\n  evidence still supports both readings, ask one classifying question — \"Is this\n  a decision to record or existing code to document?\" — with the recommendation\n  drawn from the git evidence.\n\n### Step 4: Execute the track\n\nRun the selected track gate by gate per `skills\u002F_shared\u002Fgate-contract.md`. The\ntrack owns check-existing, per-gate elicitation, composition, and relation\nwiring.\n\nQuestion budget: the ceiling of 5 questions per invocation in\n`skills\u002F_shared\u002Felicitation-contract.md`.\n\n## Result\n\nReport the produced documents grouped by category:\n\n- **knowledge** — `adr`, `rfc`, `spec`, `doc`, `guide`, `rule`, `evidence`, `scenario`\n- **vision** — `research` (scope-covering report), `rnd` (recommendation-closed report, or compatibility fallback), `plan` (architecture cascade)\n- **experience** — `task-type` (repeated agent procedure), `cpat` (standard cascade opt-in)\n- any category — a type composed on the Named type path, with its routing-condition line when one failed\n\nList each document's path and relation edges. Name tracks and steps in plain\nwords; do not print a gate address of the form `\u003Ctrack>.\u003Cstage>`. Close with one\nrecommended next action naming only `\u002Farchcore:plan`, `\u002Farchcore:review`, or a\nrepeat `\u002Farchcore:document` invocation with its subject. WHEN a gate stopped on a\nblocking exit check, the next action is the resume command for that draft.\nWHEN the run created drafts other than an `rfc` and no `plan` covers them, the\nnext action is `\u002Farchcore:review`, which offers their acceptance. An `rfc`\nresolves through `\u002Farchcore:document resolve the \u003Crfc title> RFC`.\n",{"name":5,"description":7,"argument-hint":48},"[subject]","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Farchcore-ai\u002Farchcore\u002Fskills\u002Fdocument",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill document",{"tool":65,"command":66},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill document",{"tool":68,"command":69},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill document","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchcore-ai\u002Farchcore\u002Fskills\u002Fdocument\u002FSKILL.md",true,[],[74,84,92,100,108,116],{"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":78,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":83},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":83},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":83},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":83},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":83},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":83},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]