[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79GY80MAX37Q0YFKJP2C33W":3,"skill-same:01M79GY80MAX37Q0YFKJP2C33W":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M79GY80MAX37Q0YFKJP2C33W","architecture-model-bootstrap",null,"Use to refine a generated Better Harness architecture model into a confirmed one for the Impact pane. Trigger when a project has no .better-harness\u002Farchitecture\u002Fmodel.json, when the Impact pane shows an \"Auto-generated\" model, or when a reader asks to name, merge, split, re-kind, or describe the derived Container\u002FComponent structure and propose external systems before saving it as declared.","QoderAI\u002Fbetter-harness","QoderAI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F219277434?v=4","01M79GY4YSX965EKC1H377AF4Q","01M79GY4ZYWF777EJFW8GED19N",2462,"MIT","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Farchitecture-model-bootstrap\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: architecture-model-bootstrap\ndescription: Use to refine a generated Better Harness architecture model into a confirmed one for the Impact pane. Trigger when a project has no\n  .better-harness\u002Farchitecture\u002Fmodel.json, when the Impact pane shows an \"Auto-generated\" model, or when a reader asks to name, merge, split,\n  re-kind, or describe the derived Container\u002FComponent structure and propose external systems before saving it as declared.\n---\n\n# Architecture Model Bootstrap\n\nTurn the deterministic candidate the Impact pane generates into a model a reader\ncan confirm. The server already derives a bounded, grounded skeleton from the\nworktree (one SoftwareSystem, a Container per workspace, Components for source\ndirectories). This skill does the **semantic** half a static analyzer cannot:\nnaming, grouping, kinding, describing, and proposing the external systems the\ncode only hints at — without inventing structure the evidence does not support.\n\nDefault to the repository's reply language. Keep edits grounded and reversible:\nthe output is a *proposal* a human saves, never a fact you assert.\n\n## When to use\n\n- A project declares no model and the Impact pane falls back to a generated one.\n- A reader wants the generated skeleton refined before saving it as declared.\n- An existing declared model needs elements renamed, merged, split, re-kinded, or\n  described against current code.\n\nDo not use it to invent business capabilities, runtime traffic, or external\nsystems that no evidence supports. L1 system context and external systems stay\n**proposed and human-confirmed**, per the parent spec's non-goal.\n\n## Inputs (the evidence pack)\n\nGather these before proposing anything:\n\n1. **The generated candidate.** Open the Impact pane on any commit, or read the\n   model the server would generate — one SoftwareSystem, Containers per\n   workspace manifest, Components per source directory, every element tagged\n   `generated`, plus bindings mapping path globs to element ids.\n2. **Workspace manifests.** `package.json` (root and nested), plus any\n   `Cargo.toml`, `go.mod`, `pyproject.toml`, or similar boundary markers.\n3. **Directory evidence.** The tracked path list and the top-level source layout,\n   so a proposed boundary points at real paths.\n4. **Prose evidence.** `README.md`, `AGENTS.md`, `docs\u002F`, ADRs — for names,\n   ownership, and declared external dependencies only, never for structure the\n   code contradicts.\n\n## Workflow\n\n1. **Read the candidate and the manifests.** Establish the real boundaries the\n   generator found before changing any of them.\n2. **Name and describe.** Replace generic ids\u002Fnames (`packages-api`, `src`) with\n   the project's own vocabulary. Give each kept element a one-line description\n   grounded in what its files do.\n3. **Re-kind where evidence warrants.** A deployable\u002Findependently owned unit is\n   a `Container`; an internal building block inside one is a `Component`. Do not\n   promote a directory to a Container without a boundary marker (a manifest, an\n   entrypoint, a deploy target).\n4. **Merge and split.** Fold sibling directories that are one component; split a\n   directory that clearly hosts two. Every resulting element keeps at least one\n   real path glob.\n5. **Propose relationships** you can ground in imports, HTTP clients, or declared\n   dependencies. Mark each with its kind (`Contains`, `Imports`, `ResolvedCall`,\n   `DeclaredHttp`, `DeclaredRelationship`). Leave an unresolved edge out rather\n   than guessing a target.\n6. **Propose external systems and people** only as clearly-labelled candidates,\n   with the evidence (a client, an env var, a README claim) named in the\n   description. These are the L1 scale the parent spec keeps human-confirmed.\n7. **Validate the shape** against [Model Schema](references\u002Fmodel-schema.md), then\n   hand the model and bindings back for the reader to save through the Impact\n   pane's **Save as declared model** action. Never write the file yourself unless\n   the reader asks.\n\n## Grounding rules (hard constraints)\n\n- Every element you keep must have at least one binding whose path glob matches a\n  real tracked path. No element without evidence.\n- Never invent a binding to a path that does not exist in the worktree.\n- Keep the arch-core shape exactly: `elements` (snake_case `parent_id`) +\n  `relationships` (`source_id`\u002F`target_id`). This is what the Impact host\n  consumes and what discovery validates.\n- A directory is not a component and a repository is not a container. Boundaries\n  need a marker, not just a folder.\n- Proposed external systems, people, and L1 context are candidates a human\n  confirms, labelled as such in their descriptions.\n\n## Output\n\nReturn two artifacts, ready for **Save as declared model**:\n\n- `model.json` — the refined `{ elements, relationships }` in arch-core's shape.\n- `bindings.json` — `[{ \"path_glob\": \"...\", \"element_id\": \"...\" }]`, every glob\n  resolvable in the worktree.\n\nState briefly what you renamed, merged, split, re-kinded, and proposed, and which\nelements remain low-confidence candidates a reader should check first.\n","# Architecture Model Bootstrap\n\nTurn the deterministic candidate the Impact pane generates into a model a reader\ncan confirm. The server already derives a bounded, grounded skeleton from the\nworktree (one SoftwareSystem, a Container per workspace, Components for source\ndirectories). This skill does the **semantic** half a static analyzer cannot:\nnaming, grouping, kinding, describing, and proposing the external systems the\ncode only hints at — without inventing structure the evidence does not support.\n\nDefault to the repository's reply language. Keep edits grounded and reversible:\nthe output is a *proposal* a human saves, never a fact you assert.\n\n## When to use\n\n- A project declares no model and the Impact pane falls back to a generated one.\n- A reader wants the generated skeleton refined before saving it as declared.\n- An existing declared model needs elements renamed, merged, split, re-kinded, or\n  described against current code.\n\nDo not use it to invent business capabilities, runtime traffic, or external\nsystems that no evidence supports. L1 system context and external systems stay\n**proposed and human-confirmed**, per the parent spec's non-goal.\n\n## Inputs (the evidence pack)\n\nGather these before proposing anything:\n\n1. **The generated candidate.** Open the Impact pane on any commit, or read the\n   model the server would generate — one SoftwareSystem, Containers per\n   workspace manifest, Components per source directory, every element tagged\n   `generated`, plus bindings mapping path globs to element ids.\n2. **Workspace manifests.** `package.json` (root and nested), plus any\n   `Cargo.toml`, `go.mod`, `pyproject.toml`, or similar boundary markers.\n3. **Directory evidence.** The tracked path list and the top-level source layout,\n   so a proposed boundary points at real paths.\n4. **Prose evidence.** `README.md`, `AGENTS.md`, `docs\u002F`, ADRs — for names,\n   ownership, and declared external dependencies only, never for structure the\n   code contradicts.\n\n## Workflow\n\n1. **Read the candidate and the manifests.** Establish the real boundaries the\n   generator found before changing any of them.\n2. **Name and describe.** Replace generic ids\u002Fnames (`packages-api`, `src`) with\n   the project's own vocabulary. Give each kept element a one-line description\n   grounded in what its files do.\n3. **Re-kind where evidence warrants.** A deployable\u002Findependently owned unit is\n   a `Container`; an internal building block inside one is a `Component`. Do not\n   promote a directory to a Container without a boundary marker (a manifest, an\n   entrypoint, a deploy target).\n4. **Merge and split.** Fold sibling directories that are one component; split a\n   directory that clearly hosts two. Every resulting element keeps at least one\n   real path glob.\n5. **Propose relationships** you can ground in imports, HTTP clients, or declared\n   dependencies. Mark each with its kind (`Contains`, `Imports`, `ResolvedCall`,\n   `DeclaredHttp`, `DeclaredRelationship`). Leave an unresolved edge out rather\n   than guessing a target.\n6. **Propose external systems and people** only as clearly-labelled candidates,\n   with the evidence (a client, an env var, a README claim) named in the\n   description. These are the L1 scale the parent spec keeps human-confirmed.\n7. **Validate the shape** against [Model Schema](references\u002Fmodel-schema.md), then\n   hand the model and bindings back for the reader to save through the Impact\n   pane's **Save as declared model** action. Never write the file yourself unless\n   the reader asks.\n\n## Grounding rules (hard constraints)\n\n- Every element you keep must have at least one binding whose path glob matches a\n  real tracked path. No element without evidence.\n- Never invent a binding to a path that does not exist in the worktree.\n- Keep the arch-core shape exactly: `elements` (snake_case `parent_id`) +\n  `relationships` (`source_id`\u002F`target_id`). This is what the Impact host\n  consumes and what discovery validates.\n- A directory is not a component and a repository is not a container. Boundaries\n  need a marker, not just a folder.\n- Proposed external systems, people, and L1 context are candidates a human\n  confirms, labelled as such in their descriptions.\n\n## Output\n\nReturn two artifacts, ready for **Save as declared model**:\n\n- `model.json` — the refined `{ elements, relationships }` in arch-core's shape.\n- `bindings.json` — `[{ \"path_glob\": \"...\", \"element_id\": \"...\" }]`, every glob\n  resolvable in the worktree.\n\nState briefly what you renamed, merged, split, re-kinded, and proposed, and which\nelements remain low-confidence candidates a reader should check first.\n",{"name":5,"description":7},"main","c6240a808923630db9d6397ced789eab509f0f66",".agents\u002Fskills\u002Farchitecture-model-bootstrap",205,"https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness","https:\u002F\u002Fqoderai.github.io\u002Fbetter-harness\u002F","https:\u002F\u002Fgithub.com\u002FQoderAI","2026-11-11 23:06:54",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add QoderAI\u002Fbetter-harness --skill architecture-model-bootstrap",{"tool":37,"command":38},"bunx","bunx skills add QoderAI\u002Fbetter-harness --skill architecture-model-bootstrap",{"tool":40,"command":41},"pnpm","pnpm dlx skills add QoderAI\u002Fbetter-harness --skill architecture-model-bootstrap","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Farchitecture-model-bootstrap\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fmodel-schema.md","REFERENCE","参考文档",3320,"https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Farchitecture-model-bootstrap\u002Freferences\u002Fmodel-schema.md",[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M79H048KTM9WH2SDF3B7JEND","verify","Verify one bounded change.","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fharness-component-snapshot\u002Fproject\u002F.qoder\u002Fskills\u002Fverify\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M79H00NA32FVZMZ4Y4YZD8WQ","handoff","Prepare a bounded handoff.","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fharness-component-snapshot\u002Fproject\u002F.agents\u002Fskills\u002Fhandoff\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M79GZTHYXQ0HD7QRQMDS9N2G","intent-correlation-analysis","Analyze a bounded IntentCorrelationPacketV1 and propose reviewable links among user inputs, execution slices, change units, commits, artifacts, and validation outcomes. Use when reconstructing why an observed coding-agent change exists or when Studio needs evidence-backed Intent correlation. Do not use for raw transcript summaries, deterministic file-operation collection, or autonomous confirmation of inferred Intent.","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Fskills\u002Fintent-correlation-analysis\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M79GZMG7TP1PN05085KG0FGF","better-harness","Use when \u002Fbetter-harness reviews the outer coding-agent Harness for lifecycle controls, repeated work, project feedback, agent assets, session outcomes, repair planning, durable reports, finding-bound fixes, or manual direct fixes. Invoke only via slash command.","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Fskills\u002Fbetter-harness\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M79GZFCH9PDS3BTC4HA6E16X","generate-harness-dsl","Generate, revise, or review complete Harness as Code `.harness` files when a coding-agent workflow, agent role, skill, tool contract, MCP connection, runtime, or deployment must be compiler-valid and resolvable with `@qoder-ai\u002Fharness`.","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Fpackages\u002Fharness\u002Fskills\u002Fgenerate-harness-dsl\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M79GZAV6TVS44HKQS4SPAX2M","memory-recap","Create evidence-linked work profiles, diagnose Coding Agent collaboration friction, and recommend concrete improvements from native memories or frozen exports. Use for memory recaps and agent-usage retrospectives, not memory maintenance or session-performance measurement.","https:\u002F\u002Fgithub.com\u002FQoderAI\u002Fbetter-harness\u002Fblob\u002Fmain\u002Fpackages\u002Fharness-studio\u002Fskills\u002Fmemory-recap\u002FSKILL.md",[],[]]