[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AXAZFSRCF8N50ZNG08BZ68":3,"skill-same:01M7AXAZFSRCF8N50ZNG08BZ68":47},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":29,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7AXAZFSRCF8N50ZNG08BZ68","architect",null,"Writing and changing the Mermaid diagrams a project keeps under `workspace.artifacts` — choosing which diagram and which level a change belongs in, naming it so it reads where a reader expects, and proving it still draws with `uze agent artifacts check`, which needs no workspace. Use when adding or editing a `.mmd`\u002F`.mermaid` file, when asked to diagram or document an architecture, when a diagram does not draw, or when setting up where a project keeps its architecture.","uze-sh\u002Fuze","uze-sh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F334211959?v=4","01M7AX5KNT81AC56YMRT586MBW","uze","01M7AX5KPDQA2QP7DWGZFMH4PQ",4,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002Fplugins\u002Fuze\u002Fskills\u002Farchitect\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: architect\ndescription: Writing and changing the Mermaid diagrams a project keeps under `workspace.artifacts` — choosing which diagram and which level a change belongs in, naming it so it reads where a reader expects, and proving it still draws with `uze agent artifacts check`, which needs no workspace. Use when adding or editing a `.mmd`\u002F`.mermaid` file, when asked to diagram or document an architecture, when a diagram does not draw, or when setting up where a project keeps its architecture.\n---\n\n> This skill runs `uze`. If `uze` is not on `PATH`, UZE is not installed here and nothing below applies.\n\n# UZE — a project's architecture, as files somebody wrote\n\nA project tells UZE where its architecture lives:\n\n```yaml\n# agents.yaml\nworkspace:\n  artifacts: docs\u002Farchitecture   # or a list: [docs, design]\n```\n\nEvery `.mmd` or `.mermaid` file under those directories is one **artifact**;\nanything else there is ignored, so diagrams can live beside other docs. The\nsame places are where the workspace's spec surface finds decision records\n(ADRs), by their shape, so a decision a diagram depends on can sit beside it\nin `docs\u002Fadr\u002F` without anything else declared.\n`uze agent artifacts check` draws each one the way the workspace would and\nfails on one that does not draw, with or without the workspace running;\nthe workspace's architect surface, when it is used, draws them in terminal\ncells to read and walk. Nothing\nlists the files and nothing registers them: adding a file is the whole act\nof adding a diagram, and an index beside them would be the one document\nthat is wrong the moment somebody adds the next one.\n\nThat is also the boundary of what belongs here. These diagrams are what\nsomebody **wrote down**. What a project *is* — where its lines are, which\nfiles changed, how large each one is — is measured rather than written and\nis already answered elsewhere; a diagram that restates it is a second\nanswer to go stale.\n\n## Before you add a file\n\nAsk whether the change belongs in a diagram that already exists. Most do.\nA project's architecture is a handful of views that stay accurate, not a\ndirectory that grows one file per conversation — and a view nobody updates\nis worse than a view nobody drew, because it still looks current.\n\nAdd one only when the project has no view at the altitude your change is\nabout, and say in the diagram's title what it is a view *of*.\n\n## Choose the altitude before the syntax\n\nThe single most common mistake is drawing at the wrong level, and nothing\ncatches it: a diagram full of components under `C4Context` draws perfectly\nand tells the reader something false about the system's boundary.\n\n- **`C4Context`** — the system as one box, and the people and software\n  systems directly connected to it. Nothing internal appears here. If you\n  are naming a crate, you are in the wrong view.\n- **`C4Container`** — the applications and data stores *inside* the\n  system, and the people and systems directly connected to them.\n- **`C4Component`** — what one container is made of, with the other\n  containers, people and systems its components touch around it.\n- **`sequenceDiagram`** — an interaction over time. Use it when the claim\n  is about **order**; a structure drawn as a sequence hides that it has no\n  order.\n- **`flowchart` \u002F `graph`** — everything whose claim is about\n  relationships that are neither containment nor time: a dependency\n  direction, a pipeline, a lifecycle.\n\nThe first word of the file decides which area the surface lists it under,\nso the choice above is also the choice of that first word. The C4 views\nare listed from the outside in — context, then container, then component —\nwhich is the order a reader meets them. `C4Dynamic` (one feature or use\ncase at runtime, steps numbered) and `C4Deployment` (where containers run\nin one environment) are supplementary views, not levels: draw one only when\nthe static views cannot show an interaction that keeps recurring, or a\ndeployment that differs from the obvious one.\n\n### What each C4 box is\n\n- **Person** — a human: a user, a role, a persona. A program acting for\n  somebody is not a person; an agent's actions are performed by the\n  process running it, so that process (or the system it belongs to) is\n  the box.\n- **Software system** — what one team builds, owns and releases together.\n  One binary with one release is one system, however many bounded\n  contexts it has inside; a context is a container or a component, never\n  a second system.\n- **Container** — a runtime boundary: a process (a CLI, a server, a\n  daemon, a helper the binary re-executes as) or a data store (a\n  database, a directory of files). Ask *does it run, or hold data, on its\n  own?* A crate, a library, a package or a module never is one — it\n  organises code inside a container. Two commands of one binary that run\n  in one process are one container; the same binary started as a separate\n  long-lived process is another.\n- **Component** — a grouping of code inside one container, sharing its\n  process: a module, a crate, a service behind an interface. Not\n  separately deployable. A container too big for one component view is\n  drawn as several, each filtered to one part (one crate's modules, say)\n  and naming that part in its title.\n\n### The notation, every time\n\n- The title names the scope and nothing else: `shop` for its context and\n  container views, `shop API` for a component view, `shop API: billing`\n  for one part of it. The view's type is its keyword, and the surface\n  shows it as the level the view stands on, so a title that repeats it\n  (`Component diagram for …`) says it twice. A view that leaves part of\n  its scope out says so on the boundary it leaves it out of:\n  `Boundary(billing, \"billing\", \"Crate, main modules\")`.\n- Every element is the macro of its type, with a short description of its\n  responsibility; every container and component carries a real technology\n  (`Rust, clap`, `PostgreSQL`, `Filesystem, JSON`) — never a crate name or a\n  file path.\n- Every relationship is one-way, with a label that says what happens in\n  that direction — never `Uses`, `Calls` or `Runs` alone. Between\n  containers, and from a container to a system, name the protocol in\n  `Rel`'s fourth argument: `Rel(api, db, \"Reads orders from\", \"SQL\u002FTCP\")`.\n  No `BiRel`: draw the two directions as two relationships.\n- A technology is a property of an edge, not a box: Git, HTTPS or a socket\n  is how two things talk, not an external system of its own.\n- Draw no legend of your own: the surface draws each view's key under it,\n  from the notation that view uses.\n\n### One model, many views: aliases are join keys\n\nEvery C4 view is a projection of the same model, so a person or system\nappears with the **same alias, name and description** in every view that\nshows it, and an alias names **one element** across every file — never a\nsystem here and a container or boundary there. The surface joins levels by\nalias:\n\n- a `C4Container` view's scope is its outermost `System_Boundary`; it is\n  the inside of the `System` with that alias in the context view;\n- a `C4Component` view's scope is its outermost `Container_Boundary`; it\n  is the inside of the `Container` (or `ContainerDb`, `ContainerQueue`)\n  with that alias in the container view. Several component views of one\n  container are siblings;\n- nested `Boundary` blocks inside a scope group elements and join nothing.\n\nWhere an alias cannot say it, declare the zoom: `$link` on an element to\nanother catalogued `.mmd` (`$link=\"docs\u002Farchitecture\u002Fapi-components.mmd\"`)\nopens that file as its inside. Prefer the alias; it is what other Mermaid\nreaders understand too.\n\n## Name it for the reader, not for the filesystem\n\nThe surface lists an artifact by its Mermaid front-matter `title`, else a\n`title` statement in the diagram, else the file name made readable. Give\nit a title:\n\n```\n---\ntitle: shop\n---\nC4Container\n  ...\n```\n\nA name is what somebody scanning a list of a dozen diagrams reads. Name\nthe view (`shop API`, `Install pipeline`, `Agent lifecycle`), not the\noccasion for drawing it. A title holding a colon is YAML, so quote it:\n`title: \"shop API: billing\"`.\n\n## Join a box to the code it stands for\n\nThe code is the level below the last diagram, and it is not drawn: it is\nlinked. In C4, `$link` names the file an element stands for:\n\n```\nComponent(delivery, \"delivery\", \"Rust module\", \"Routes capabilities\", $link=\"crates\u002Fcore\u002Fsrc\u002Fdelivery.rs\")\n```\n\nLink every component, and every container that has no component view of\nits own, to its entry or module file; a data store may link to the code\nthat names its paths. A container that *has* a component view is entered,\nnot linked. In a flowchart, a node does the same with `click`:\n\n```\nflowchart LR\n  core[uze-core] --> integrations[uze-integrations]\n  click core href \"crates\u002Fuze-core\u002Fsrc\u002Flib.rs\"\n```\n\nThe surface opens it. This is what turns a diagram from a picture into a\nway into the code — use it wherever a box stands for something a reader\nwould then want to go and read. Paths are relative to the project.\n\n## Prove it draws — this is not optional\n\n```bash\nuze agent artifacts check          # the whole project\nuze agent artifacts check --format json\n```\n\nIt reads every declared file and **draws** it the way the surface would,\nthen reports each one. It exits non-zero when any of them fails, so it is\na gate and not a report to skim.\n\nRun it after every change to a diagram. Five things it catches that\nreading the file does not:\n\n1. **A diagram type that is listed but not drawn.** The surface draws the\n   C4 family, sequences and flowcharts. Valid Mermaid outside those\n   appears in the list and opens onto a sentence saying it cannot be\n   drawn — which is not what you want a reader to find.\n2. **A statement that cannot be read.** The check quotes it back.\n3. **Relations with nowhere to go.** A diagram can draw with edges\n   *missing* — every box present, the board looking finished, a\n   relationship simply absent. This is the only failure here that nobody\n   catches by looking, and it usually means the view is carrying more\n   relationships than it can show. Split it, or raise its altitude.\n4. **A link that opens nothing.** A box's `$link` or `click … href` is\n   opened in the project: a file that moved, a URL or a path that leaves\n   the project looks like a working link on the board and opens nothing.\n   A directory opens, but link a Rust module by its file\n   (`src\u002Fdelivery.rs`), which is where its documentation starts.\n5. **C4 notes.** Beside a C4 view that draws, the check lists where it\n   departs from the notation above: a box with no description, a container or component with no\n   technology, a line with no label or running both ways, a view that\n   zooms into nothing, an alias naming another kind of element elsewhere.\n   A note fails nothing; leave none.\n\n**Never describe the accepted syntax from memory, including from this\npage.** The parser is the only authority on what draws, it moves, and a\nremembered grammar diverges from it silently. Write the diagram, run the\ncheck, read what it says. If a statement is refused, the answer is the\nrefusal — not a guess at what the parser meant.\n\n## When a diagram does not appear at all\n\n- The file is not under a directory `workspace.artifacts` declares, or does not end in\n  `.mmd` \u002F `.mermaid`.\n- `agents.yaml` declares no `workspace.artifacts` at all, or declares a path that\n  leaves the project — both of which the check names.\n- The directory is read only a few levels deep, so a diagram buried far\n  below the declared root is not found.\n","> This skill runs `uze`. If `uze` is not on `PATH`, UZE is not installed here and nothing below applies.\n\n# UZE — a project's architecture, as files somebody wrote\n\nA project tells UZE where its architecture lives:\n\n```yaml\n# agents.yaml\nworkspace:\n  artifacts: docs\u002Farchitecture   # or a list: [docs, design]\n```\n\nEvery `.mmd` or `.mermaid` file under those directories is one **artifact**;\nanything else there is ignored, so diagrams can live beside other docs. The\nsame places are where the workspace's spec surface finds decision records\n(ADRs), by their shape, so a decision a diagram depends on can sit beside it\nin `docs\u002Fadr\u002F` without anything else declared.\n`uze agent artifacts check` draws each one the way the workspace would and\nfails on one that does not draw, with or without the workspace running;\nthe workspace's architect surface, when it is used, draws them in terminal\ncells to read and walk. Nothing\nlists the files and nothing registers them: adding a file is the whole act\nof adding a diagram, and an index beside them would be the one document\nthat is wrong the moment somebody adds the next one.\n\nThat is also the boundary of what belongs here. These diagrams are what\nsomebody **wrote down**. What a project *is* — where its lines are, which\nfiles changed, how large each one is — is measured rather than written and\nis already answered elsewhere; a diagram that restates it is a second\nanswer to go stale.\n\n## Before you add a file\n\nAsk whether the change belongs in a diagram that already exists. Most do.\nA project's architecture is a handful of views that stay accurate, not a\ndirectory that grows one file per conversation — and a view nobody updates\nis worse than a view nobody drew, because it still looks current.\n\nAdd one only when the project has no view at the altitude your change is\nabout, and say in the diagram's title what it is a view *of*.\n\n## Choose the altitude before the syntax\n\nThe single most common mistake is drawing at the wrong level, and nothing\ncatches it: a diagram full of components under `C4Context` draws perfectly\nand tells the reader something false about the system's boundary.\n\n- **`C4Context`** — the system as one box, and the people and software\n  systems directly connected to it. Nothing internal appears here. If you\n  are naming a crate, you are in the wrong view.\n- **`C4Container`** — the applications and data stores *inside* the\n  system, and the people and systems directly connected to them.\n- **`C4Component`** — what one container is made of, with the other\n  containers, people and systems its components touch around it.\n- **`sequenceDiagram`** — an interaction over time. Use it when the claim\n  is about **order**; a structure drawn as a sequence hides that it has no\n  order.\n- **`flowchart` \u002F `graph`** — everything whose claim is about\n  relationships that are neither containment nor time: a dependency\n  direction, a pipeline, a lifecycle.\n\nThe first word of the file decides which area the surface lists it under,\nso the choice above is also the choice of that first word. The C4 views\nare listed from the outside in — context, then container, then component —\nwhich is the order a reader meets them. `C4Dynamic` (one feature or use\ncase at runtime, steps numbered) and `C4Deployment` (where containers run\nin one environment) are supplementary views, not levels: draw one only when\nthe static views cannot show an interaction that keeps recurring, or a\ndeployment that differs from the obvious one.\n\n### What each C4 box is\n\n- **Person** — a human: a user, a role, a persona. A program acting for\n  somebody is not a person; an agent's actions are performed by the\n  process running it, so that process (or the system it belongs to) is\n  the box.\n- **Software system** — what one team builds, owns and releases together.\n  One binary with one release is one system, however many bounded\n  contexts it has inside; a context is a container or a component, never\n  a second system.\n- **Container** — a runtime boundary: a process (a CLI, a server, a\n  daemon, a helper the binary re-executes as) or a data store (a\n  database, a directory of files). Ask *does it run, or hold data, on its\n  own?* A crate, a library, a package or a module never is one — it\n  organises code inside a container. Two commands of one binary that run\n  in one process are one container; the same binary started as a separate\n  long-lived process is another.\n- **Component** — a grouping of code inside one container, sharing its\n  process: a module, a crate, a service behind an interface. Not\n  separately deployable. A container too big for one component view is\n  drawn as several, each filtered to one part (one crate's modules, say)\n  and naming that part in its title.\n\n### The notation, every time\n\n- The title names the scope and nothing else: `shop` for its context and\n  container views, `shop API` for a component view, `shop API: billing`\n  for one part of it. The view's type is its keyword, and the surface\n  shows it as the level the view stands on, so a title that repeats it\n  (`Component diagram for …`) says it twice. A view that leaves part of\n  its scope out says so on the boundary it leaves it out of:\n  `Boundary(billing, \"billing\", \"Crate, main modules\")`.\n- Every element is the macro of its type, with a short description of its\n  responsibility; every container and component carries a real technology\n  (`Rust, clap`, `PostgreSQL`, `Filesystem, JSON`) — never a crate name or a\n  file path.\n- Every relationship is one-way, with a label that says what happens in\n  that direction — never `Uses`, `Calls` or `Runs` alone. Between\n  containers, and from a container to a system, name the protocol in\n  `Rel`'s fourth argument: `Rel(api, db, \"Reads orders from\", \"SQL\u002FTCP\")`.\n  No `BiRel`: draw the two directions as two relationships.\n- A technology is a property of an edge, not a box: Git, HTTPS or a socket\n  is how two things talk, not an external system of its own.\n- Draw no legend of your own: the surface draws each view's key under it,\n  from the notation that view uses.\n\n### One model, many views: aliases are join keys\n\nEvery C4 view is a projection of the same model, so a person or system\nappears with the **same alias, name and description** in every view that\nshows it, and an alias names **one element** across every file — never a\nsystem here and a container or boundary there. The surface joins levels by\nalias:\n\n- a `C4Container` view's scope is its outermost `System_Boundary`; it is\n  the inside of the `System` with that alias in the context view;\n- a `C4Component` view's scope is its outermost `Container_Boundary`; it\n  is the inside of the `Container` (or `ContainerDb`, `ContainerQueue`)\n  with that alias in the container view. Several component views of one\n  container are siblings;\n- nested `Boundary` blocks inside a scope group elements and join nothing.\n\nWhere an alias cannot say it, declare the zoom: `$link` on an element to\nanother catalogued `.mmd` (`$link=\"docs\u002Farchitecture\u002Fapi-components.mmd\"`)\nopens that file as its inside. Prefer the alias; it is what other Mermaid\nreaders understand too.\n\n## Name it for the reader, not for the filesystem\n\nThe surface lists an artifact by its Mermaid front-matter `title`, else a\n`title` statement in the diagram, else the file name made readable. Give\nit a title:\n\n```\n---\ntitle: shop\n---\nC4Container\n  ...\n```\n\nA name is what somebody scanning a list of a dozen diagrams reads. Name\nthe view (`shop API`, `Install pipeline`, `Agent lifecycle`), not the\noccasion for drawing it. A title holding a colon is YAML, so quote it:\n`title: \"shop API: billing\"`.\n\n## Join a box to the code it stands for\n\nThe code is the level below the last diagram, and it is not drawn: it is\nlinked. In C4, `$link` names the file an element stands for:\n\n```\nComponent(delivery, \"delivery\", \"Rust module\", \"Routes capabilities\", $link=\"crates\u002Fcore\u002Fsrc\u002Fdelivery.rs\")\n```\n\nLink every component, and every container that has no component view of\nits own, to its entry or module file; a data store may link to the code\nthat names its paths. A container that *has* a component view is entered,\nnot linked. In a flowchart, a node does the same with `click`:\n\n```\nflowchart LR\n  core[uze-core] --> integrations[uze-integrations]\n  click core href \"crates\u002Fuze-core\u002Fsrc\u002Flib.rs\"\n```\n\nThe surface opens it. This is what turns a diagram from a picture into a\nway into the code — use it wherever a box stands for something a reader\nwould then want to go and read. Paths are relative to the project.\n\n## Prove it draws — this is not optional\n\n```bash\nuze agent artifacts check          # the whole project\nuze agent artifacts check --format json\n```\n\nIt reads every declared file and **draws** it the way the surface would,\nthen reports each one. It exits non-zero when any of them fails, so it is\na gate and not a report to skim.\n\nRun it after every change to a diagram. Five things it catches that\nreading the file does not:\n\n1. **A diagram type that is listed but not drawn.** The surface draws the\n   C4 family, sequences and flowcharts. Valid Mermaid outside those\n   appears in the list and opens onto a sentence saying it cannot be\n   drawn — which is not what you want a reader to find.\n2. **A statement that cannot be read.** The check quotes it back.\n3. **Relations with nowhere to go.** A diagram can draw with edges\n   *missing* — every box present, the board looking finished, a\n   relationship simply absent. This is the only failure here that nobody\n   catches by looking, and it usually means the view is carrying more\n   relationships than it can show. Split it, or raise its altitude.\n4. **A link that opens nothing.** A box's `$link` or `click … href` is\n   opened in the project: a file that moved, a URL or a path that leaves\n   the project looks like a working link on the board and opens nothing.\n   A directory opens, but link a Rust module by its file\n   (`src\u002Fdelivery.rs`), which is where its documentation starts.\n5. **C4 notes.** Beside a C4 view that draws, the check lists where it\n   departs from the notation above: a box with no description, a container or component with no\n   technology, a line with no label or running both ways, a view that\n   zooms into nothing, an alias naming another kind of element elsewhere.\n   A note fails nothing; leave none.\n\n**Never describe the accepted syntax from memory, including from this\npage.** The parser is the only authority on what draws, it moves, and a\nremembered grammar diverges from it silently. Write the diagram, run the\ncheck, read what it says. If a statement is refused, the answer is the\nrefusal — not a guess at what the parser meant.\n\n## When a diagram does not appear at all\n\n- The file is not under a directory `workspace.artifacts` declares, or does not end in\n  `.mmd` \u002F `.mermaid`.\n- `agents.yaml` declares no `workspace.artifacts` at all, or declares a path that\n  leaves the project — both of which the check names.\n- The directory is read only a few levels deep, so a diagram buried far\n  below the declared root is not found.\n",{"name":5,"description":7},"main","e2cfbb55eec2aa007135f9a2256b73f7170a3b9e","plugins\u002Fuze\u002Fskills\u002Farchitect",1,"https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze","https:\u002F\u002Fuze.sh","https:\u002F\u002Fgithub.com\u002Fuze-sh","🧩 Agents come and go. Your work stays.","2026-11-13 05:15:37",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add uze-sh\u002Fuze --skill architect",{"tool":39,"command":40},"bunx","bunx skills add uze-sh\u002Fuze --skill architect",{"tool":42,"command":43},"pnpm","pnpm dlx skills add uze-sh\u002Fuze --skill architect","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002Fplugins\u002Fuze\u002Fskills\u002Farchitect\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7AXDFA81RA77NHGYVZRCH0E","commit","North Star fixture skill — used to prove native\u002Fgenerated delivery across harnesses.","https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002Ftests\u002F_fixtures\u002Fgolden\u002Fmarketplace\u002Fplugins\u002Fflow\u002Fskills\u002Fcommit\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7AXCYQ5WMH46JRJVF57FTHA","oc-skill","opencode native","https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002Ftests\u002F_fixtures\u002Fforeign\u002Fopencode\u002Fnative-plugin\u002Fskills\u002Foc-skill\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7AXCVSFQ76DR4GXGJ1Q9PBA","uze-plugin-first","Emits the deterministic UZE Plugin First conformance proof.","https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002Ftests\u002F_fixtures\u002Fforeign\u002Fcodex\u002Fnative-plugin\u002Fskills\u002Fuze-plugin-first\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7AXCTD57QJ3GEN54W5PREV2","hello","says hello","https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002Ftests\u002F_fixtures\u002Fforeign\u002Fclaude\u002Fnative-plugin\u002Fskills\u002Fhello\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7AXCR1HKRHJ7PP39JQS8SQ5","agy-native","antigravity native","https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002Ftests\u002F_fixtures\u002Fforeign\u002Fantigravity\u002Fnative-plugin\u002Fskills\u002Fagy-native\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7AXCNTR4WXE4VT89MK4XQST","review","Review code for correctness and missing tests","https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002Ftests\u002F_fixtures\u002Fcanonical\u002Fworkflow\u002Fskills\u002Freview\u002FSKILL.md",[],[]]