[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ME5TT1T79KD3P6520EMZ1Z":3,"skill-same:01M6ME5TT1T79KD3P6520EMZ1Z":103},{"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":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":62,"ownerHtmlUrl":63,"ownerBlogUrl":64,"ownerDescription":65,"updatedAt":66,"install":67,"resources":80},"01M6ME5TT1T79KD3P6520EMZ1Z","init",null,"First-time Archcore setup. Wires the host (MCP config, hooks, CLAUDE.md\u002FAGENTS.md managed block), measures the authored context the repo already holds, then composes a first-day seed — stack rule, run guide, data-model, integrations, config, entry points, public surface, a linked architecture overview, and specs for the top hotspot modules — shown in ONE preview and created on a single confirm. Modes, named as the first word: init import converts the repo's authored context — CLAUDE.md, AGENTS.md, .cursor\u002Frules and other agent instructions, ADR and RFC folders, contributor docs, internal pages of a published docs site, recoverable git history — into native typed documents with no import marks, staged by a plan when the volume is large; init refresh adds facts that appeared since, or drills into one domain with init refresh \u003Cdomain>. Use on a fresh clone, empty `.archcore\u002F`, 'set up archcore', 'migrate our CLAUDE.md to archcore', 'import our docs and ADRs', or to wire host configs. Not for individual docs or planning.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1571,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchcore-ai\u002Fplugin\u002Fskills\u002Finit\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"contributor","MCP","managed","top","native","import","host","fresh","as","volume","time","preview","modules","hooks","up","guide","context","model","stack","plan","migrate","SET","git","run","documents","config","architecture","2026-11-10 10:12:30",false,"---\nname: init\nargument-hint: \"[import|refresh] [path or domain]\"\ndescription: \"First-time Archcore setup. Wires the host (MCP config, hooks, CLAUDE.md\u002FAGENTS.md managed block), measures the authored context the repo already holds, then composes a first-day seed — stack rule, run guide, data-model, integrations, config, entry points, public surface, a linked architecture overview, and specs for the top hotspot modules — shown in ONE preview and created on a single confirm. Modes, named as the first word: init import converts the repo's authored context — CLAUDE.md, AGENTS.md, .cursor\u002Frules and other agent instructions, ADR and RFC folders, contributor docs, internal pages of a published docs site, recoverable git history — into native typed documents with no import marks, staged by a plan when the volume is large; init refresh adds facts that appeared since, or drills into one domain with init refresh \u003Cdomain>. Use on a fresh clone, empty `.archcore\u002F`, 'set up archcore', 'migrate our CLAUDE.md to archcore', 'import our docs and ADRs', or to wire host configs. Not for individual docs or planning.\"\n---\n\n# \u002Farchcore:init\n\nFirst-time onboarding. Wires the host, measures the authored context the repository already holds, and fills `.archcore\u002F` from two sources — what people wrote and what the code shows — so the code-alignment hook and per-command grounding have substance from day one. Per `magic-first-day-init.adr` and `init-import-mode.adr`: extractive facts are composed in full; authored content wins over synthesized content on the same subject; the overview is an index, never a prose blob. **Nothing is written before `confirm`.**\n\nBefore planning or writing relations, load `skills\u002F_shared\u002Frelation-authoring.md`.\nApply its claim check to seed and import wiring after reading the endpoint content.\n\n## Arguments\n\nThe first word selects the run: `import` or `refresh`. These two words are the command's modes in the sense of `command-surface-v2.spec`. The rest of the arguments is the subject. No arguments, or any other first word, start a plain init.\n\n- `import [path]` — convert the repository's authored context into native documents, at all five discovery levels of `lib\u002Fsources.md`; a path limits the run to that path. Resumes an open import plan when one exists.\n- `refresh [path or domain]` — re-run on a seeded repo to add facts that appeared since (a new schema, config, or modules) and to retrofit host wiring. A subject scopes the top-up: an existing path wins; otherwise a detected domain slug runs the single-domain pass. Bypasses the \"already seeded\" early-exit.\n- Depth and scale are not arguments. The preview offers the toggles `depth:light|standard|deep` (default `standard`) and `scale:small|medium|large`, where the user already sees each choice's cost (`lib\u002Fseed-compose.md`). Import has no depth.\n- A retired form as the first word — `domain`, or a flag such as `--refresh`, `--depth=deep`, `--scale=large` — starts a plain init; name the current form once: *\"`\u002Farchcore:init [import|refresh] [path or domain]`; depth and scale are toggles in the preview.\"*\n\n## When to use\n\n- Empty `.archcore\u002F` — the SessionStart nudge points here.\n- First session on a fresh clone \u002F fresh install.\n- User says: \"initialize archcore\", \"set up archcore\", \"seed archcore\", \"first-time setup\", \"what should I do first\".\n- User says: \"migrate our CLAUDE.md \u002F AGENTS.md \u002F cursor rules to archcore\", \"import our ADRs and docs\", \"move our docs into archcore\" → `import`.\n\n**Not init** (route elsewhere):\n\n- Recording a specific decision → `\u002Farchcore:document`.\n- Planning a feature → `\u002Farchcore:plan`.\n- Documenting one module → `\u002Farchcore:document`.\n- Codifying a team standard → `\u002Farchcore:document` (offers rule + guide continuation).\n- Filing one external material or a finished report → `\u002Farchcore:document research`.\n- Reading applicable context before coding → automatic; the code-alignment hook injects it on file edits.\n- Docs health audit → `\u002Farchcore:review`.\n\n## Routing table\n\n**Mode routing** — evaluated top-to-bottom, first match wins.\n\n| Signal | Route | Flow files |\n|---|---|---|\n| First word `import`, and the assessment gate (step 5) finds no authored source | → **no-source**: the no-source report; no gated operation, no confirm, no code seed | `lib\u002Fsources.md` \"No authored source\" |\n| First word `import` | → **import**: the whole import track, levels L1–L5; no code seed | `skills\u002F_shared\u002Ftracks\u002Fimport.md`, `lib\u002Fsources.md` |\n| First word `refresh` | → **refresh**: plain-init flow with the early-exit bypassed; existing artifacts are **skip (exists)** | as the plain rows below |\n| Open import plan found (step 3) on a plain init | → report the plan, name `\u002Farchcore:init import`, then continue the plain init without new conversion targets | — |\n| No manifest, no source, no authored source (step 4) | → **empty**: host wiring only, behind its own mini-confirm | `lib\u002Fhost-wiring.md` \"Empty route\" |\n| No manifest and no source, authored sources found | → **import-only**: host wiring + the import track in one preview; no code seed | `skills\u002F_shared\u002Ftracks\u002Fimport.md` |\n| Anything else | → **plain init**: host wiring + facts + the fill the assessment gate divides | `lib\u002Fseed-detect.md`, `lib\u002Fseed-compose.md` |\n\n**Fill routing** — what the assessment gate (step 5) decides on a plain init or a refresh. The extractive facts are composed in **every** row.\n\n| Assessment result | Authored sources | Hotspot specs |\n|---|---|---|\n| no authored source — nothing found, or every source found is `skip` | none; the announce line names what was checked, and names `\u002Farchcore:init import` when deeper levels hold files | the depth's budget over the unchanged ranked pool |\n| tier `S` (≤ 8 targets) | every target listed in the init preview; converted on the init confirm | budget over the pool **minus** the `coverage_set` |\n| tier `M` (9–40) or `L` (> 40) | the init confirm creates the import plan and runs wave 1; the closing message names `\u002Farchcore:init import` | budget over the pool **minus** the `coverage_set` |\n\nScale routing (small \u002F medium \u002F large, and what each seeds) lives in `_shared\u002Fgrounding\u002Fdetect-scale.md` and `lib\u002Fseed-compose.md`. Tier-1 facts are seeded in any scale **when detected** — breadth scales with the repo, presence does not.\n\n**Follow-up routing** — closing-message hand-offs. Init surfaces these as todos; MUST NOT auto-invoke.\n\n| User wants to... | → Invoke |\n|---|---|\n| Continue an open import, or import beyond agent files and ADR folders | `\u002Farchcore:init import` |\n| Import one folder only | `\u002Farchcore:init import \u003Cpath>` |\n| Add facts that appeared since first init | `\u002Farchcore:init refresh` |\n| Drill into another domain (large) | `\u002Farchcore:init refresh \u003Cdomain>` |\n| Capture another module, record a decision, codify a convention | `\u002Farchcore:document` |\n| Plan a feature | `\u002Farchcore:plan` |\n| Scope queries to a domain (large) | `mcp__archcore__search_documents` with the domain tag |\n| See what's loaded | `\u002Farchcore:review` |\n\n## Execution\n\nContent voice: default to architectural prose — decisions, rationale, intent. See `skills\u002F_shared\u002Fprecision-rules.md` Rule 6. Code blocks only where the document type requires it (`rule`, `guide`, `cpat`, and `spec` examples) or the user asks.\n\n**Gating (write boundary).** `init_project()` and the read-only MCP calls (`list_documents`, `get_document`, `search_documents`) are infrastructure — they run **before** the preview. Three groups of operations are gated:\n\n- document writes: `create_document`, `update_document`, `remove_document`, `add_relation`;\n- host-wiring writes: `install_host_config` \u002F `archcore init --agent` — they touch files outside `.archcore\u002F`, like `.mcp.json` and `.claude\u002Fsettings.json`;\n- the source-file edits of the import track's retire gate.\n\n**No gated operation fires before the user types `confirm`.** Absence of an answer is never `confirm`: IF this invocation cannot receive further user input in this turn (a print-mode run, a sub-agent call), THEN print the preview and stop. `cancel` therefore leaves `.archcore\u002F` content-empty and the repo's files untouched (the directory and `settings.json` may exist from `init_project`, which is harmless and idempotent).\n\n**Lazy reading.** Load a flow file only when its step starts: `lib\u002Fhost-wiring.md` at step 1, `lib\u002Fsources.md` at step 5, `lib\u002Fseed-detect.md` then `lib\u002Fseed-compose.md` at step 6, `skills\u002F_shared\u002Ftracks\u002Fimport.md` when a route reaches it. Never load them all at once.\n\n### 1. Pre-flight — CLI and host-wiring gate\n\nRun the CLI availability check and the `cli-gte 0.7.0` host-wiring version gate per `lib\u002Fhost-wiring.md` \"Pre-flight\". The canonical installer is documented at https:\u002F\u002Fdocs.archcore.ai\u002Fstart\u002Finstall\u002F; never suggest another install channel. A missing CLI that the user declines to install stops the run. A CLI older than v0.7.0 continues with host wiring **disabled**.\n\n### 2. Initialize and probe the host\n\nCall `mcp__archcore__init_project()` exactly once (pre-gate infrastructure — idempotent, safe on an already-initialized project). It creates `.archcore\u002F` and `settings.json` if missing. On `initialized: true` print *\"Archcore initialized at `.archcore\u002F`.\"*; on `already_initialized: true` print nothing.\n\nThen run the host and project-root probe per `lib\u002Fhost-wiring.md` \"Host and project root probe\" — always, even when host wiring is disabled. It prints one token: `claude-code` | `cursor` | `codex-cli` | `__UNKNOWN__`. On `__UNKNOWN__`, or anything else than the three host tokens, ask one `AskUserQuestion` — \"Which AI host is this session running in?\" with options Claude Code \u002F Cursor \u002F Codex (CLI or desktop app) \u002F GitHub Copilot CLI — and map the answer to the agent id (`claude-code` \u002F `cursor` \u002F `codex-cli` \u002F `copilot`); there is no `codex-desktop` id. A GitHub Copilot CLI session always lands on `__UNKNOWN__`. Do not run `archcore init` yourself at this step; if the archcore MCP tools are unavailable in this session, the terminal command `archcore init --agent \u003Chost> --project \"\u003Croot>\"` is the user's recovery path.\n\nHost wiring is planned **first** in every preview: when the probe finds the host configs absent, the Host wiring line leads the preview, and its writes lead the create phase.\n\n### 3. Check state\n\nCall `mcp__archcore__list_documents()` once. **Derive every flag below from local documents only** — skip any result carrying `global: true` \u002F `read_only: true` \u002F `source_kind: \"global\"`. A mounted global source must not satisfy the already-seeded early-exit: init seeds THIS repo's documents. If any global results appear, load `skills\u002F_shared\u002Fglobals.md`; never modify a global document and never target one with `add_relation`. Derive:\n\n- `has_stack_rule` — a `rule` whose title contains \"stack\" in `conventions\u002F`; `has_run_guide` — a `guide` whose title contains \"run\"\u002F\"running\" in `onboarding\u002F`.\n- `has_data_model`, `has_integrations`, `has_config`, `has_entry_points`, `has_surface`, `has_top_level_map`, `has_overview` — any `doc` tagged `data-model`, `integrations`, `config`, `entry-points`, `surface`, `top-level-map`, `architecture-overview`.\n- `open_import_plan` — a local `plan` tagged `import-plan`.\n\n**Open import plan.** On `import`, resume it (`skills\u002F_shared\u002Ftracks\u002Fimport.md`, \"Track state and the import plan\") and skip steps 4–5. On a plain init or a refresh, report it — rows done, rows open — and name `\u002Farchcore:init import`; plan no new conversion targets in this run.\n\n**Already-seeded early-exit.** If `has_stack_rule` AND `has_run_guide` AND `has_overview` are all true AND the first word is neither `refresh` nor `import`, reply:\n\n> Init already seeded this repo. Applicable context auto-injects on file edits via the code-alignment hook; use `\u002Farchcore:review` for the dashboard. To add facts that appeared since (a new schema, config, or modules), re-run `\u002Farchcore:init refresh`; to drill into one domain, `\u002Farchcore:init refresh \u003Cdomain>`; to convert the repo's authored docs and agent instructions, `\u002Farchcore:init import`. (Seeded before host wiring existed, or missing the host configs? `refresh` also adds host wiring — MCP config, SessionStart hook, usage hint.)\n\nThen stop. On a `refresh` run, skip this early-exit — every already-present artifact is marked **skip (exists)** in the preview and only missing ones are composed. Resolve a `refresh` subject here: an existing path → path scope; else a detected domain slug → single-domain pass; else ask one question that lists the detected domains.\n\n### 4. Source-signal gate\n\nSingle filesystem probe — one shell call, no catalog reads:\n\n- **`has_manifest`** — at least one project-defining manifest or build file at the project root (depth ≤ 2 for monorepo workspaces): `package.json`, `pyproject.toml`, `requirements.txt`, `Cargo.toml`, `go.mod`, `Gemfile`, `composer.json`, `*.csproj`, `pom.xml`, `build.gradle*`, `mix.exs`, `Package.swift`. **Seed examples, not exhaustive** — also `CMakeLists.txt`, `Makefile`, `deps.edn`, `pubspec.yaml`, `build.sbt`, `*.cabal`, `*.tf`, `Chart.yaml`, `*.sln`, and agent\u002FLLM-plugin manifests such as `marketplace.json` \u002F `plugin.json` \u002F `.claude-plugin\u002F*`.\n- **`has_top_level_source`** — at least one file with a recognizable source extension under the project root, capped at depth 3, excluding `.archcore\u002F`, `.git\u002F`, `node_modules\u002F`, `vendor\u002F`, `dist\u002F`, `build\u002F`, `out\u002F`, `target\u002F`, `coverage\u002F`, `.venv\u002F`, `__pycache__\u002F`, `.next\u002F`, `.turbo\u002F`. The extension list is **not exhaustive** — count any file whose contents are plainly source (a shebang, or import\u002Finclude\u002Fpackage\u002Fmodule\u002Fdef\u002Ffunc\u002Fclass constructs).\n\nIf BOTH are false, do not decide yet — step 5 tells whether authored sources exist. Both false and no authored source → the **empty** route of `lib\u002Fhost-wiring.md` (no placeholder documents, ever). Both false with authored sources → the **import-only** route.\n\n### 5. Assessment gate\n\nSkip on the `import` mode when step 3 resumed a plan. Otherwise read `lib\u002Fsources.md` and run the assess gate of `skills\u002F_shared\u002Ftracks\u002Fimport.md` in callable mode: list authored sources from paths, byte sizes, heading counts, and path mentions — never a full file body — with sizes computed only **after stripping any archcore managed block** (a file whose only content is the managed block is not a source). A plain init and a refresh assess levels L1–L2 — agent instructions (`CLAUDE.md`, `AGENTS.md`, `.cursor\u002Frules\u002F*.mdc`, `.github\u002Finstructions\u002F*.md`, and the other L1 paths) and decision records; `import` assesses L1–L5. A plain init and a refresh also record `deeper_present` — a presence-only path listing of L3–L4 that feeds no measure.\n\nThe gate returns `targets_est`, `tier`, `coverage_set`, and `levels_found`. Announce them in one line, e.g.:\n\n> Authored context: 9 sources at L1–L2 (CLAUDE.md 6 KB, 6 .cursor\u002Frules files, docs\u002Fadr × 2) → ~14 target documents, tier M. 2 hotspot modules look covered (estimate).\n\nPrint the line in every run, including the run that finds nothing. WHEN the gate returns no authored source (`levels_found` is empty), follow `lib\u002Fsources.md` \"No authored source\": a plain init or a refresh prints the \"none\" announce line and goes on to step 6 with the pool unchanged; the `import` mode prints the no-source report and stops — it MUST NOT fall back to the code seed, because the user asked for a conversion and the seed is a separate, costlier run.\n\n### 6. Run the route\n\n- **Plain init \u002F refresh** — run `lib\u002Fseed-detect.md` (Phase A — DETECT), then `lib\u002Fseed-compose.md` (Phase B compose → Phase C preview → Phase D confirm → Phase E — CREATE + WIRE). The `coverage_set` narrows the hotspot pool in Phase A; the authored block of the preview follows the Fill routing table. One preview, one confirm.\n- **Import \u002F import-only** — run `skills\u002F_shared\u002Ftracks\u002Fimport.md` from its discover gate (or from the resumed row). Its plan preview carries the Host wiring line when wiring is absent. One confirm per wave when the plan grew; a separate confirm before any source file is edited.\n\n### 7. Close\n\nSeed runs close per `lib\u002Fseed-compose.md` \"Closing message\"; host-wiring outcome lines per `lib\u002Fhost-wiring.md`. Import runs close with: documents created by type, the conflicts list, fidelity departures, rows still open with `\u002Farchcore:init import` as the continuation, and — after the last row — the retire offer and the removal of the import plan. Always end with:\n\n> Use `\u002Farchcore:review` for the dashboard, `\u002Farchcore:review deep` for a health audit.\n\n## Result\n\nA `.archcore\u002F` filled from two sources, created only on `confirm`; existing artifacts skipped.\n\n- **Empty**: 0 content docs — `.archcore\u002F` and `settings.json`, plus host wiring behind its own mini-confirm. No catalog files read.\n- **Plain init**: host wiring, the detected Tier-1 facts, the architecture overview, hotspot specs for the depth's budget over the pool that authored sources do not cover (the spec budget has no absolute maximum — `standard` 25% of the ranked pool, `light` 10%, `deep` 60%; `lib\u002Fseed-compose.md`), cross-cutting rules (medium\u002Flarge), and — tier `S` — the converted authored documents, or — tier `M`\u002F`L` — the import plan with wave 1 done. Every synthesized or converted document is `status='draft'`.\n- **No-source** (`import` found nothing to convert): 0 documents, 0 file writes — a per-level report of what was checked, each `skip` with its class, and the next command.\n- **Import**: native typed documents (`rule`, `adr`, `rfc`, `guide`, `spec`, `doc`, `idea`) clustered by topic across sources, linked to each other and to the seed facts where their claims support a relation; a conflicts list instead of silent choices; no `imported` tag, no `source:` tag, no pointer line, no `imported-` prefix. After the last wave: the retire offer for agent-instruction files, then the import plan is removed, so the corpus holds no record of the import.\n\nIdempotency: the flagged Tier-1 facts and the overview are skip-on-exists; Tier-2 specs and rules dedupe by filename before create; conversion targets dedupe by a topic search before create and, for tiers `M`\u002F`L`, by the import plan's row states. Host wiring is idempotent end-to-end. A second `\u002Farchcore:init` on a fully-seeded repo early-exits (step 3) unless `refresh` or `import` is the first word. The empty route never creates placeholder documents, so the SessionStart nudge keeps pointing here.\n","# \u002Farchcore:init\n\nFirst-time onboarding. Wires the host, measures the authored context the repository already holds, and fills `.archcore\u002F` from two sources — what people wrote and what the code shows — so the code-alignment hook and per-command grounding have substance from day one. Per `magic-first-day-init.adr` and `init-import-mode.adr`: extractive facts are composed in full; authored content wins over synthesized content on the same subject; the overview is an index, never a prose blob. **Nothing is written before `confirm`.**\n\nBefore planning or writing relations, load `skills\u002F_shared\u002Frelation-authoring.md`.\nApply its claim check to seed and import wiring after reading the endpoint content.\n\n## Arguments\n\nThe first word selects the run: `import` or `refresh`. These two words are the command's modes in the sense of `command-surface-v2.spec`. The rest of the arguments is the subject. No arguments, or any other first word, start a plain init.\n\n- `import [path]` — convert the repository's authored context into native documents, at all five discovery levels of `lib\u002Fsources.md`; a path limits the run to that path. Resumes an open import plan when one exists.\n- `refresh [path or domain]` — re-run on a seeded repo to add facts that appeared since (a new schema, config, or modules) and to retrofit host wiring. A subject scopes the top-up: an existing path wins; otherwise a detected domain slug runs the single-domain pass. Bypasses the \"already seeded\" early-exit.\n- Depth and scale are not arguments. The preview offers the toggles `depth:light|standard|deep` (default `standard`) and `scale:small|medium|large`, where the user already sees each choice's cost (`lib\u002Fseed-compose.md`). Import has no depth.\n- A retired form as the first word — `domain`, or a flag such as `--refresh`, `--depth=deep`, `--scale=large` — starts a plain init; name the current form once: *\"`\u002Farchcore:init [import|refresh] [path or domain]`; depth and scale are toggles in the preview.\"*\n\n## When to use\n\n- Empty `.archcore\u002F` — the SessionStart nudge points here.\n- First session on a fresh clone \u002F fresh install.\n- User says: \"initialize archcore\", \"set up archcore\", \"seed archcore\", \"first-time setup\", \"what should I do first\".\n- User says: \"migrate our CLAUDE.md \u002F AGENTS.md \u002F cursor rules to archcore\", \"import our ADRs and docs\", \"move our docs into archcore\" → `import`.\n\n**Not init** (route elsewhere):\n\n- Recording a specific decision → `\u002Farchcore:document`.\n- Planning a feature → `\u002Farchcore:plan`.\n- Documenting one module → `\u002Farchcore:document`.\n- Codifying a team standard → `\u002Farchcore:document` (offers rule + guide continuation).\n- Filing one external material or a finished report → `\u002Farchcore:document research`.\n- Reading applicable context before coding → automatic; the code-alignment hook injects it on file edits.\n- Docs health audit → `\u002Farchcore:review`.\n\n## Routing table\n\n**Mode routing** — evaluated top-to-bottom, first match wins.\n\n| Signal | Route | Flow files |\n|---|---|---|\n| First word `import`, and the assessment gate (step 5) finds no authored source | → **no-source**: the no-source report; no gated operation, no confirm, no code seed | `lib\u002Fsources.md` \"No authored source\" |\n| First word `import` | → **import**: the whole import track, levels L1–L5; no code seed | `skills\u002F_shared\u002Ftracks\u002Fimport.md`, `lib\u002Fsources.md` |\n| First word `refresh` | → **refresh**: plain-init flow with the early-exit bypassed; existing artifacts are **skip (exists)** | as the plain rows below |\n| Open import plan found (step 3) on a plain init | → report the plan, name `\u002Farchcore:init import`, then continue the plain init without new conversion targets | — |\n| No manifest, no source, no authored source (step 4) | → **empty**: host wiring only, behind its own mini-confirm | `lib\u002Fhost-wiring.md` \"Empty route\" |\n| No manifest and no source, authored sources found | → **import-only**: host wiring + the import track in one preview; no code seed | `skills\u002F_shared\u002Ftracks\u002Fimport.md` |\n| Anything else | → **plain init**: host wiring + facts + the fill the assessment gate divides | `lib\u002Fseed-detect.md`, `lib\u002Fseed-compose.md` |\n\n**Fill routing** — what the assessment gate (step 5) decides on a plain init or a refresh. The extractive facts are composed in **every** row.\n\n| Assessment result | Authored sources | Hotspot specs |\n|---|---|---|\n| no authored source — nothing found, or every source found is `skip` | none; the announce line names what was checked, and names `\u002Farchcore:init import` when deeper levels hold files | the depth's budget over the unchanged ranked pool |\n| tier `S` (≤ 8 targets) | every target listed in the init preview; converted on the init confirm | budget over the pool **minus** the `coverage_set` |\n| tier `M` (9–40) or `L` (> 40) | the init confirm creates the import plan and runs wave 1; the closing message names `\u002Farchcore:init import` | budget over the pool **minus** the `coverage_set` |\n\nScale routing (small \u002F medium \u002F large, and what each seeds) lives in `_shared\u002Fgrounding\u002Fdetect-scale.md` and `lib\u002Fseed-compose.md`. Tier-1 facts are seeded in any scale **when detected** — breadth scales with the repo, presence does not.\n\n**Follow-up routing** — closing-message hand-offs. Init surfaces these as todos; MUST NOT auto-invoke.\n\n| User wants to... | → Invoke |\n|---|---|\n| Continue an open import, or import beyond agent files and ADR folders | `\u002Farchcore:init import` |\n| Import one folder only | `\u002Farchcore:init import \u003Cpath>` |\n| Add facts that appeared since first init | `\u002Farchcore:init refresh` |\n| Drill into another domain (large) | `\u002Farchcore:init refresh \u003Cdomain>` |\n| Capture another module, record a decision, codify a convention | `\u002Farchcore:document` |\n| Plan a feature | `\u002Farchcore:plan` |\n| Scope queries to a domain (large) | `mcp__archcore__search_documents` with the domain tag |\n| See what's loaded | `\u002Farchcore:review` |\n\n## Execution\n\nContent voice: default to architectural prose — decisions, rationale, intent. See `skills\u002F_shared\u002Fprecision-rules.md` Rule 6. Code blocks only where the document type requires it (`rule`, `guide`, `cpat`, and `spec` examples) or the user asks.\n\n**Gating (write boundary).** `init_project()` and the read-only MCP calls (`list_documents`, `get_document`, `search_documents`) are infrastructure — they run **before** the preview. Three groups of operations are gated:\n\n- document writes: `create_document`, `update_document`, `remove_document`, `add_relation`;\n- host-wiring writes: `install_host_config` \u002F `archcore init --agent` — they touch files outside `.archcore\u002F`, like `.mcp.json` and `.claude\u002Fsettings.json`;\n- the source-file edits of the import track's retire gate.\n\n**No gated operation fires before the user types `confirm`.** Absence of an answer is never `confirm`: IF this invocation cannot receive further user input in this turn (a print-mode run, a sub-agent call), THEN print the preview and stop. `cancel` therefore leaves `.archcore\u002F` content-empty and the repo's files untouched (the directory and `settings.json` may exist from `init_project`, which is harmless and idempotent).\n\n**Lazy reading.** Load a flow file only when its step starts: `lib\u002Fhost-wiring.md` at step 1, `lib\u002Fsources.md` at step 5, `lib\u002Fseed-detect.md` then `lib\u002Fseed-compose.md` at step 6, `skills\u002F_shared\u002Ftracks\u002Fimport.md` when a route reaches it. Never load them all at once.\n\n### 1. Pre-flight — CLI and host-wiring gate\n\nRun the CLI availability check and the `cli-gte 0.7.0` host-wiring version gate per `lib\u002Fhost-wiring.md` \"Pre-flight\". The canonical installer is documented at https:\u002F\u002Fdocs.archcore.ai\u002Fstart\u002Finstall\u002F; never suggest another install channel. A missing CLI that the user declines to install stops the run. A CLI older than v0.7.0 continues with host wiring **disabled**.\n\n### 2. Initialize and probe the host\n\nCall `mcp__archcore__init_project()` exactly once (pre-gate infrastructure — idempotent, safe on an already-initialized project). It creates `.archcore\u002F` and `settings.json` if missing. On `initialized: true` print *\"Archcore initialized at `.archcore\u002F`.\"*; on `already_initialized: true` print nothing.\n\nThen run the host and project-root probe per `lib\u002Fhost-wiring.md` \"Host and project root probe\" — always, even when host wiring is disabled. It prints one token: `claude-code` | `cursor` | `codex-cli` | `__UNKNOWN__`. On `__UNKNOWN__`, or anything else than the three host tokens, ask one `AskUserQuestion` — \"Which AI host is this session running in?\" with options Claude Code \u002F Cursor \u002F Codex (CLI or desktop app) \u002F GitHub Copilot CLI — and map the answer to the agent id (`claude-code` \u002F `cursor` \u002F `codex-cli` \u002F `copilot`); there is no `codex-desktop` id. A GitHub Copilot CLI session always lands on `__UNKNOWN__`. Do not run `archcore init` yourself at this step; if the archcore MCP tools are unavailable in this session, the terminal command `archcore init --agent \u003Chost> --project \"\u003Croot>\"` is the user's recovery path.\n\nHost wiring is planned **first** in every preview: when the probe finds the host configs absent, the Host wiring line leads the preview, and its writes lead the create phase.\n\n### 3. Check state\n\nCall `mcp__archcore__list_documents()` once. **Derive every flag below from local documents only** — skip any result carrying `global: true` \u002F `read_only: true` \u002F `source_kind: \"global\"`. A mounted global source must not satisfy the already-seeded early-exit: init seeds THIS repo's documents. If any global results appear, load `skills\u002F_shared\u002Fglobals.md`; never modify a global document and never target one with `add_relation`. Derive:\n\n- `has_stack_rule` — a `rule` whose title contains \"stack\" in `conventions\u002F`; `has_run_guide` — a `guide` whose title contains \"run\"\u002F\"running\" in `onboarding\u002F`.\n- `has_data_model`, `has_integrations`, `has_config`, `has_entry_points`, `has_surface`, `has_top_level_map`, `has_overview` — any `doc` tagged `data-model`, `integrations`, `config`, `entry-points`, `surface`, `top-level-map`, `architecture-overview`.\n- `open_import_plan` — a local `plan` tagged `import-plan`.\n\n**Open import plan.** On `import`, resume it (`skills\u002F_shared\u002Ftracks\u002Fimport.md`, \"Track state and the import plan\") and skip steps 4–5. On a plain init or a refresh, report it — rows done, rows open — and name `\u002Farchcore:init import`; plan no new conversion targets in this run.\n\n**Already-seeded early-exit.** If `has_stack_rule` AND `has_run_guide` AND `has_overview` are all true AND the first word is neither `refresh` nor `import`, reply:\n\n> Init already seeded this repo. Applicable context auto-injects on file edits via the code-alignment hook; use `\u002Farchcore:review` for the dashboard. To add facts that appeared since (a new schema, config, or modules), re-run `\u002Farchcore:init refresh`; to drill into one domain, `\u002Farchcore:init refresh \u003Cdomain>`; to convert the repo's authored docs and agent instructions, `\u002Farchcore:init import`. (Seeded before host wiring existed, or missing the host configs? `refresh` also adds host wiring — MCP config, SessionStart hook, usage hint.)\n\nThen stop. On a `refresh` run, skip this early-exit — every already-present artifact is marked **skip (exists)** in the preview and only missing ones are composed. Resolve a `refresh` subject here: an existing path → path scope; else a detected domain slug → single-domain pass; else ask one question that lists the detected domains.\n\n### 4. Source-signal gate\n\nSingle filesystem probe — one shell call, no catalog reads:\n\n- **`has_manifest`** — at least one project-defining manifest or build file at the project root (depth ≤ 2 for monorepo workspaces): `package.json`, `pyproject.toml`, `requirements.txt`, `Cargo.toml`, `go.mod`, `Gemfile`, `composer.json`, `*.csproj`, `pom.xml`, `build.gradle*`, `mix.exs`, `Package.swift`. **Seed examples, not exhaustive** — also `CMakeLists.txt`, `Makefile`, `deps.edn`, `pubspec.yaml`, `build.sbt`, `*.cabal`, `*.tf`, `Chart.yaml`, `*.sln`, and agent\u002FLLM-plugin manifests such as `marketplace.json` \u002F `plugin.json` \u002F `.claude-plugin\u002F*`.\n- **`has_top_level_source`** — at least one file with a recognizable source extension under the project root, capped at depth 3, excluding `.archcore\u002F`, `.git\u002F`, `node_modules\u002F`, `vendor\u002F`, `dist\u002F`, `build\u002F`, `out\u002F`, `target\u002F`, `coverage\u002F`, `.venv\u002F`, `__pycache__\u002F`, `.next\u002F`, `.turbo\u002F`. The extension list is **not exhaustive** — count any file whose contents are plainly source (a shebang, or import\u002Finclude\u002Fpackage\u002Fmodule\u002Fdef\u002Ffunc\u002Fclass constructs).\n\nIf BOTH are false, do not decide yet — step 5 tells whether authored sources exist. Both false and no authored source → the **empty** route of `lib\u002Fhost-wiring.md` (no placeholder documents, ever). Both false with authored sources → the **import-only** route.\n\n### 5. Assessment gate\n\nSkip on the `import` mode when step 3 resumed a plan. Otherwise read `lib\u002Fsources.md` and run the assess gate of `skills\u002F_shared\u002Ftracks\u002Fimport.md` in callable mode: list authored sources from paths, byte sizes, heading counts, and path mentions — never a full file body — with sizes computed only **after stripping any archcore managed block** (a file whose only content is the managed block is not a source). A plain init and a refresh assess levels L1–L2 — agent instructions (`CLAUDE.md`, `AGENTS.md`, `.cursor\u002Frules\u002F*.mdc`, `.github\u002Finstructions\u002F*.md`, and the other L1 paths) and decision records; `import` assesses L1–L5. A plain init and a refresh also record `deeper_present` — a presence-only path listing of L3–L4 that feeds no measure.\n\nThe gate returns `targets_est`, `tier`, `coverage_set`, and `levels_found`. Announce them in one line, e.g.:\n\n> Authored context: 9 sources at L1–L2 (CLAUDE.md 6 KB, 6 .cursor\u002Frules files, docs\u002Fadr × 2) → ~14 target documents, tier M. 2 hotspot modules look covered (estimate).\n\nPrint the line in every run, including the run that finds nothing. WHEN the gate returns no authored source (`levels_found` is empty), follow `lib\u002Fsources.md` \"No authored source\": a plain init or a refresh prints the \"none\" announce line and goes on to step 6 with the pool unchanged; the `import` mode prints the no-source report and stops — it MUST NOT fall back to the code seed, because the user asked for a conversion and the seed is a separate, costlier run.\n\n### 6. Run the route\n\n- **Plain init \u002F refresh** — run `lib\u002Fseed-detect.md` (Phase A — DETECT), then `lib\u002Fseed-compose.md` (Phase B compose → Phase C preview → Phase D confirm → Phase E — CREATE + WIRE). The `coverage_set` narrows the hotspot pool in Phase A; the authored block of the preview follows the Fill routing table. One preview, one confirm.\n- **Import \u002F import-only** — run `skills\u002F_shared\u002Ftracks\u002Fimport.md` from its discover gate (or from the resumed row). Its plan preview carries the Host wiring line when wiring is absent. One confirm per wave when the plan grew; a separate confirm before any source file is edited.\n\n### 7. Close\n\nSeed runs close per `lib\u002Fseed-compose.md` \"Closing message\"; host-wiring outcome lines per `lib\u002Fhost-wiring.md`. Import runs close with: documents created by type, the conflicts list, fidelity departures, rows still open with `\u002Farchcore:init import` as the continuation, and — after the last row — the retire offer and the removal of the import plan. Always end with:\n\n> Use `\u002Farchcore:review` for the dashboard, `\u002Farchcore:review deep` for a health audit.\n\n## Result\n\nA `.archcore\u002F` filled from two sources, created only on `confirm`; existing artifacts skipped.\n\n- **Empty**: 0 content docs — `.archcore\u002F` and `settings.json`, plus host wiring behind its own mini-confirm. No catalog files read.\n- **Plain init**: host wiring, the detected Tier-1 facts, the architecture overview, hotspot specs for the depth's budget over the pool that authored sources do not cover (the spec budget has no absolute maximum — `standard` 25% of the ranked pool, `light` 10%, `deep` 60%; `lib\u002Fseed-compose.md`), cross-cutting rules (medium\u002Flarge), and — tier `S` — the converted authored documents, or — tier `M`\u002F`L` — the import plan with wave 1 done. Every synthesized or converted document is `status='draft'`.\n- **No-source** (`import` found nothing to convert): 0 documents, 0 file writes — a per-level report of what was checked, each `skip` with its class, and the next command.\n- **Import**: native typed documents (`rule`, `adr`, `rfc`, `guide`, `spec`, `doc`, `idea`) clustered by topic across sources, linked to each other and to the seed facts where their claims support a relation; a conflicts list instead of silent choices; no `imported` tag, no `source:` tag, no pointer line, no `imported-` prefix. After the last wave: the retire offer for agent-instruction files, then the import plan is removed, so the corpus holds no record of the import.\n\nIdempotency: the flagged Tier-1 facts and the overview are skip-on-exists; Tier-2 specs and rules dedupe by filename before create; conversion targets dedupe by a topic search before create and, for tiers `M`\u002F`L`, by the import plan's row states. Host wiring is idempotent end-to-end. A second `\u002Farchcore:init` on a fully-seeded repo early-exits (step 3) unless `refresh` or `import` is the first word. The empty route never creates placeholder documents, so the SessionStart nudge keeps pointing here.\n",{"name":5,"description":7,"argument-hint":56},"[import|refresh] [path or domain]","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Farchcore-ai\u002Fplugin\u002Fskills\u002Finit",490,"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 02:12:02",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill init",{"tool":73,"command":74},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill init",{"tool":76,"command":77},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill init","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchcore-ai\u002Fplugin\u002Fskills\u002Finit\u002FSKILL.md",true,[81,87,91,95,99],{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"lib\u002Fcompose-overview.md","REFERENCE","参考文档",9427,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchcore-ai\u002Fplugin\u002Fskills\u002Finit\u002Flib\u002Fcompose-overview.md",{"path":88,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":89,"sourceHtmlUrl":90},"lib\u002Fhost-wiring.md",13314,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchcore-ai\u002Fplugin\u002Fskills\u002Finit\u002Flib\u002Fhost-wiring.md",{"path":92,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":93,"sourceHtmlUrl":94},"lib\u002Fseed-compose.md",25753,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchcore-ai\u002Fplugin\u002Fskills\u002Finit\u002Flib\u002Fseed-compose.md",{"path":96,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":97,"sourceHtmlUrl":98},"lib\u002Fseed-detect.md",10864,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchcore-ai\u002Fplugin\u002Fskills\u002Finit\u002Flib\u002Fseed-detect.md",{"path":100,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":101,"sourceHtmlUrl":102},"lib\u002Fsources.md",14367,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchcore-ai\u002Fplugin\u002Fskills\u002Finit\u002Flib\u002Fsources.md",[104,112,119,126,153,178],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":111},"01M746ZWACVKMZ1BJXJZHYJSSX","migrate-to-e2e","Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for \u002Fmigrate-to-e2e, \"migrate our tests to e2e\", \"port these Maestro flows\", \"move our TesterArmy tests\", or when a project has an e2e config and an older suite still running.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fmigrate-to-e2e\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":111},"01M746ZPTAX1Q0FBKAB1CYND7E","e2e","Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fe2e\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":111},"01M746ZJN784HVHMDP9MQGCSGG","create-verification-skill","Generate a project-local verify-\u003Capp> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for \u002Fcreate-verification-skill, \"make a verification skill for this repo\", or when a project has no scripted way to prove UI behavior.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fcreate-verification-skill\u002FSKILL.md",[],[],{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":51},"01M716A6ETNB9B1SQ3GXZC75VR","deja-search","deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-search\u002FSKILL.md",[],[133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152],"search","deja search","never","error","ready","memory","re","decide","fix","design","debugging","when","you","done","reviewer","io","change","cli","merge","past",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":51},"01M716A3J2W5SENSE9VGMXB375","deja-reflect","End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-reflect\u002FSKILL.md",[],[160,161,162,148,163,164,165,166,167,168,169,170,171,172,138,173,174,175,176,177],"deja reflect","reflect","review","with","record","github","next","https","node","Rules","decisions","brew","remember","project rules","project","session","end","reflection",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":191,"publishedAt":51},"01M715T3RR4BAYSR57HPPTJ0PF","revid","Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftmakersas\u002Frevid-skills\u002Fskills\u002Frevid\u002FSKILL.md",[184,187,188],{"categoryNo":185,"categoryName":186,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":189,"categoryName":190,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[180,192,193,194,195,196,197,174,198,139,199,200,25,201,144,202,203,204,205,206],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","song","image","mcp server","schedule","api","publish"]