[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E8M1WNWA27SP05X320HKPV":3,"skill-same:01M7E8M1WNWA27SP05X320HKPV":64},{"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":37,"commitSha":38,"skillDirectory":39,"forksCount":14,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":57},"01M7E8M1WNWA27SP05X320HKPV","architecture",null,"Weave architecture: compare independent adversarial workers, then synthesize the best project architecture","tony\u002Fskills","tony","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F26336?v=4","01M72E5RNJ7SQV8F9KBM5RKRMN","Tony Narlock","01M7E7MBN5C6YZ4JJJ5Y82KBJG",0,"MIT","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Farchitecture\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: architecture\ndescription: \"Weave architecture: compare independent adversarial workers, then synthesize the best project architecture\"\nallowed-tools: [\"Bash\", \"Read\", \"Grep\", \"Glob\", \"Edit\", \"Write\", \"Task\", \"AskUserQuestion\", \"EnterPlanMode\", \"ExitPlanMode\"]\nargument-hint: \"[--passes=N] [--timeout=N|none] [--mode=fast|balanced|deep] [--workers=subagents|model-clis] \u003Carchitecture goal>\"\ndisable-model-invocation: true\n---\n\n# Weave Architecture\n\nRun an architecture or scaffolding task across independent adversarial workers, using host-native sub-agents by default or separate model CLIs when selected. After all workers finish, **cherry-pick the best conventions, skills, agents, and scaffolding from each worker** into one coherent architecture. Unlike `\u002Fweave:execute`, which targets feature implementation, this command targets project-level documentation, conventions, and structural artifacts. Unlike `\u002Fweave:prompt`, which picks one winner, it combines the best parts.\n\nThe architecture goal comes from `$ARGUMENTS`. If there are none, ask the user what they want scaffolded.\n\nA request like `\u002Fweave:architecture apply the latest session` runs no workers: follow `..\u002F..\u002Freferences\u002Fmutating-run.md` (Apply a recorded session) with this skill's `adopt` and `update` commands from its final phase, and skip the other phases.\n\n`\u003Cengine>` is `..\u002F..\u002Fscripts\u002Fengine.py` resolved from this skill's directory to an absolute path, written literally in every command, and run with `python3`.\n\n## Worker selection\n\n\u003C!-- portable: ask-user-choice=headless-default -->\n\nBefore any other unresolved configuration choice or operational step, read\n`..\u002F..\u002Freferences\u002Fworker-backends.md` (Caller contract). Resolve\n`worker_backend` from `--workers=subagents|model-clis` using that reference;\nif the flag is absent, ask its worker question first.\nIf interactive choice is unavailable, honor its documented headless default.\n\n---\n\n## Orchestration Plan\n\nEnter plan mode before the first edit. In Claude Code call `EnterPlanMode`; in Cursor, Codex, or Gemini use `\u002Fplan` or `Shift+Tab`. Where plan mode is unavailable, present the plan as text.\n\nThe plan follows `..\u002F..\u002Freferences\u002Fmutating-run.md` (Shared phases, Orchestration plan), with these items first:\n\n1. **Goal scope**: what the architecture adds or changes, and what it must not touch\n2. **Existing components**: the conventions file, skills, agents, hooks, and MCP or LSP servers already present, and the project layout\n3. **Extra quality gates**: frontmatter and cross-reference validation\n\nPresent the plan and wait for approval, then exit plan mode (`ExitPlanMode`).\n\n---\n\n## Phase 1: Start the session\n\nFollow `..\u002F..\u002Freferences\u002Fensemble-core.md` (Start the session) with `--command architecture --mutating`; it asks each unresolved setting through `AskUserQuestion`. Then proceed per `..\u002F..\u002Freferences\u002Fmutating-run.md` (Shared phases). Explore the project: the existing conventions file, the component inventory (`skills\u002F*\u002FSKILL.md`, `agents\u002F*.md`, `hooks\u002Fhooks.json`, `.mcp.json`, `.lsp.json`), directory layout, module boundaries, test framework, CI, and build system. The context packet holds the conventions summary, the component inventory, and known unknowns about the goal.\n\n---\n\n## Phase 2: Generate in parallel\n\nThe shared worker prompt body is:\n\n> Generate project architecture artifacts for this codebase. Read the project's AGENTS.md\u002FCLAUDE.md and structure first, and follow its conventions strictly.\n>\n> Goal: \u003Cthe architecture goal>\n>\n> Produce any of: conventions-file updates (commit standards, quality gates), skill definitions (`skills\u002F*\u002FSKILL.md`), agent definitions (`agents\u002F*.md`), architecture decision records, example code for core patterns, test harnesses for architectural invariants, and directory scaffolding. Put each artifact in its own file in the appropriate location, and run the quality gates when you finish.\n\n---\n\n## Phase 3: Analyze the architectures\n\nCapture, run the gates, and record the pass per `..\u002F..\u002Freferences\u002Fmutating-run.md` (Shared phases). Also assess convention completeness (commit messages, testing, CI, code style, quality gates), skill quality (scope, description, tool restrictions), agent design (tool access, delegation), architectural coherence across artifacts, and whether test harnesses check real invariants; write the notes with the gate results. **Assess** per `ensemble-core.md` (Blind judging, Synthesis protocol), where the judge participant scores. The convergence mode is **file-by-file**. Its brief asks it, for each file any participant created or modified, to compare the original (`git show HEAD:\u003Cfile>`, if it existed) with each snapshot, verify frontmatter, cross-references, tool names, and convention claims, and score each version per file. Select the artifacts per `..\u002F..\u002Freferences\u002Fmutating-run.md` (Shared phases), and write the analysis per `..\u002F..\u002Freferences\u002Fprose-rules.md`.\n\n---\n\n## Phase 4: Multi-pass refinement\n\nFollow `..\u002F..\u002Freferences\u002Fmutating-run.md` (Refinement passes), repeating Phases 2 and 3.\n\n---\n\n## Phase 5: Apply the best architecture\n\nFollow `..\u002F..\u002Freferences\u002Fmutating-run.md` (Apply gate and presentation): show the synthesis plan and wait before touching the main checkout.\n\n1. Adopt the selected artifacts:\n\n   ```console\n   $ python3 \u003Cengine> adopt \\\n       --session \"\u003Csession_dir>\" \\\n       --pass \u003Cfinal N> \\\n       --pick \u003Cpath>=\u003Cparticipant> \\\n       --delete \u003Cpath>\n   ```\n\n   If `adopt` refuses, follow `..\u002F..\u002Freferences\u002Fmutating-run.md` (Apply gate and presentation).\n\n2. Read the combined result and fix integration problems between files from different participants: naming, formatting, and cross-references (conventions name the right test commands, skills name real tools, agents name real skills).\n\n3. Run the project's quality gates and check that every skill and agent has valid YAML frontmatter with `name` and `description`, that referenced tools exist, and that the conventions file agrees with the existing project structure. Then record the state:\n\n   ```console\n   $ python3 \u003Cengine> update \\\n       --session \"\u003Csession_dir>\" \\\n       --event synthesis_applied\n   ```\n\n4. Clean up per `..\u002F..\u002Freferences\u002Fmutating-run.md` (Shared phases) (Apply).\n\n5. Read `..\u002F..\u002Freferences\u002Fpresent-results.md` and `..\u002F..\u002Freferences\u002Fresults\u002Farchitecture.md`, and apply them with `RESULT_KIND` = `architecture`, `ARTIFACT_PATH` = `\u003Csession_dir>\u002Fpass-NNNN\u002Fsynthesis.md`, `SESSION_DIR`, `PASS_COUNT` = `passes`, `IN_PLAN_MODE` = false, `LABEL_MAP_PATH` = `\u003Csession_dir>\u002Fpass-NNNN\u002Flabel-map.json`.\n\n---\n\n## Finish\n\nFollow `ensemble-core.md` (Finish). Report the artifacts applied and the participant each came from, the quality-gate result, and unavailable participants with their failure class.\n","# Weave Architecture\n\nRun an architecture or scaffolding task across independent adversarial workers, using host-native sub-agents by default or separate model CLIs when selected. After all workers finish, **cherry-pick the best conventions, skills, agents, and scaffolding from each worker** into one coherent architecture. Unlike `\u002Fweave:execute`, which targets feature implementation, this command targets project-level documentation, conventions, and structural artifacts. Unlike `\u002Fweave:prompt`, which picks one winner, it combines the best parts.\n\nThe architecture goal comes from `$ARGUMENTS`. If there are none, ask the user what they want scaffolded.\n\nA request like `\u002Fweave:architecture apply the latest session` runs no workers: follow `..\u002F..\u002Freferences\u002Fmutating-run.md` (Apply a recorded session) with this skill's `adopt` and `update` commands from its final phase, and skip the other phases.\n\n`\u003Cengine>` is `..\u002F..\u002Fscripts\u002Fengine.py` resolved from this skill's directory to an absolute path, written literally in every command, and run with `python3`.\n\n## Worker selection\n\n\u003C!-- portable: ask-user-choice=headless-default -->\n\nBefore any other unresolved configuration choice or operational step, read\n`..\u002F..\u002Freferences\u002Fworker-backends.md` (Caller contract). Resolve\n`worker_backend` from `--workers=subagents|model-clis` using that reference;\nif the flag is absent, ask its worker question first.\nIf interactive choice is unavailable, honor its documented headless default.\n\n---\n\n## Orchestration Plan\n\nEnter plan mode before the first edit. In Claude Code call `EnterPlanMode`; in Cursor, Codex, or Gemini use `\u002Fplan` or `Shift+Tab`. Where plan mode is unavailable, present the plan as text.\n\nThe plan follows `..\u002F..\u002Freferences\u002Fmutating-run.md` (Shared phases, Orchestration plan), with these items first:\n\n1. **Goal scope**: what the architecture adds or changes, and what it must not touch\n2. **Existing components**: the conventions file, skills, agents, hooks, and MCP or LSP servers already present, and the project layout\n3. **Extra quality gates**: frontmatter and cross-reference validation\n\nPresent the plan and wait for approval, then exit plan mode (`ExitPlanMode`).\n\n---\n\n## Phase 1: Start the session\n\nFollow `..\u002F..\u002Freferences\u002Fensemble-core.md` (Start the session) with `--command architecture --mutating`; it asks each unresolved setting through `AskUserQuestion`. Then proceed per `..\u002F..\u002Freferences\u002Fmutating-run.md` (Shared phases). Explore the project: the existing conventions file, the component inventory (`skills\u002F*\u002FSKILL.md`, `agents\u002F*.md`, `hooks\u002Fhooks.json`, `.mcp.json`, `.lsp.json`), directory layout, module boundaries, test framework, CI, and build system. The context packet holds the conventions summary, the component inventory, and known unknowns about the goal.\n\n---\n\n## Phase 2: Generate in parallel\n\nThe shared worker prompt body is:\n\n> Generate project architecture artifacts for this codebase. Read the project's AGENTS.md\u002FCLAUDE.md and structure first, and follow its conventions strictly.\n>\n> Goal: \u003Cthe architecture goal>\n>\n> Produce any of: conventions-file updates (commit standards, quality gates), skill definitions (`skills\u002F*\u002FSKILL.md`), agent definitions (`agents\u002F*.md`), architecture decision records, example code for core patterns, test harnesses for architectural invariants, and directory scaffolding. Put each artifact in its own file in the appropriate location, and run the quality gates when you finish.\n\n---\n\n## Phase 3: Analyze the architectures\n\nCapture, run the gates, and record the pass per `..\u002F..\u002Freferences\u002Fmutating-run.md` (Shared phases). Also assess convention completeness (commit messages, testing, CI, code style, quality gates), skill quality (scope, description, tool restrictions), agent design (tool access, delegation), architectural coherence across artifacts, and whether test harnesses check real invariants; write the notes with the gate results. **Assess** per `ensemble-core.md` (Blind judging, Synthesis protocol), where the judge participant scores. The convergence mode is **file-by-file**. Its brief asks it, for each file any participant created or modified, to compare the original (`git show HEAD:\u003Cfile>`, if it existed) with each snapshot, verify frontmatter, cross-references, tool names, and convention claims, and score each version per file. Select the artifacts per `..\u002F..\u002Freferences\u002Fmutating-run.md` (Shared phases), and write the analysis per `..\u002F..\u002Freferences\u002Fprose-rules.md`.\n\n---\n\n## Phase 4: Multi-pass refinement\n\nFollow `..\u002F..\u002Freferences\u002Fmutating-run.md` (Refinement passes), repeating Phases 2 and 3.\n\n---\n\n## Phase 5: Apply the best architecture\n\nFollow `..\u002F..\u002Freferences\u002Fmutating-run.md` (Apply gate and presentation): show the synthesis plan and wait before touching the main checkout.\n\n1. Adopt the selected artifacts:\n\n   ```console\n   $ python3 \u003Cengine> adopt \\\n       --session \"\u003Csession_dir>\" \\\n       --pass \u003Cfinal N> \\\n       --pick \u003Cpath>=\u003Cparticipant> \\\n       --delete \u003Cpath>\n   ```\n\n   If `adopt` refuses, follow `..\u002F..\u002Freferences\u002Fmutating-run.md` (Apply gate and presentation).\n\n2. Read the combined result and fix integration problems between files from different participants: naming, formatting, and cross-references (conventions name the right test commands, skills name real tools, agents name real skills).\n\n3. Run the project's quality gates and check that every skill and agent has valid YAML frontmatter with `name` and `description`, that referenced tools exist, and that the conventions file agrees with the existing project structure. Then record the state:\n\n   ```console\n   $ python3 \u003Cengine> update \\\n       --session \"\u003Csession_dir>\" \\\n       --event synthesis_applied\n   ```\n\n4. Clean up per `..\u002F..\u002Freferences\u002Fmutating-run.md` (Shared phases) (Apply).\n\n5. Read `..\u002F..\u002Freferences\u002Fpresent-results.md` and `..\u002F..\u002Freferences\u002Fresults\u002Farchitecture.md`, and apply them with `RESULT_KIND` = `architecture`, `ARTIFACT_PATH` = `\u003Csession_dir>\u002Fpass-NNNN\u002Fsynthesis.md`, `SESSION_DIR`, `PASS_COUNT` = `passes`, `IN_PLAN_MODE` = false, `LABEL_MAP_PATH` = `\u003Csession_dir>\u002Fpass-NNNN\u002Flabel-map.json`.\n\n---\n\n## Finish\n\nFollow `ensemble-core.md` (Finish). Report the artifacts applied and the participant each came from, the quality-gate result, and unavailable participants with their failure class.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":35,"disable-model-invocation":36},[25,26,27,28,29,30,31,32,33,34],"Bash","Read","Grep","Glob","Edit","Write","Task","AskUserQuestion","EnterPlanMode","ExitPlanMode","[--passes=N] [--timeout=N|none] [--mode=fast|balanced|deep] [--workers=subagents|model-clis] \u003Carchitecture goal>",true,"main","5fbeb3b47beedea13813be7b7023f736a8d97a65","plugins\u002Fweave\u002Fskills\u002Farchitecture","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills","https:\u002F\u002Fgithub.com\u002Ftony","https:\u002F\u002Ftony.sh","lighthouse keeper","2026-11-08 17:57:34",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":36},[47,50,53],{"tool":48,"command":49},"npx","npx skills add tony\u002Fskills --skill architecture",{"tool":51,"command":52},"bunx","bunx skills add tony\u002Fskills --skill architecture",{"tool":54,"command":55},"pnpm","pnpm dlx skills add tony\u002Fskills --skill architecture","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Farchitecture\u002FSKILL.md",[58],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"agents\u002Fopenai.yaml","REFERENCE","参考文档",301,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Farchitecture\u002Fagents\u002Fopenai.yaml",[65,72,79,86,93,100],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7E8NCSHXV2JPW4J61R0TQS7","serene-bliss","Use when asked to make a CLI --help, docs page, error message, or tooling UX more serene or calmer for developer experience; returns text, no edits.","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fserene-bliss\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7E8N87MAVJD8RRQKQB1ZPS6","review","Weave code review: run independent adversarial reviews in parallel, then synthesize findings","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7E8N402XG4ZBFNACQ413163","refine","Use when asked to refine a draft, iterate on code until cleaner, or polish a README through repeated critique and improvement.","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Frefine\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7E8N01KB86A7136P00GVKJW","prompt","Weave prompt: compare independent adversarial implementations, then adopt the single best one","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fprompt\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7E8MW7YJW2PCMDW3G9RTGNK","plan","Weave planning: compare independent adversarial plans, then synthesize the best one","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fplan\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7E8MSBYXNCV4ZYWDS4PFJXK","fix-review","Fix weave review findings: validate, add test coverage, fix, and commit each as atomic changes","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Ffix-review\u002FSKILL.md",[],[]]