[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E86J0ASZTM3VZZZHVENGES":3,"skill-same:01M7E86J0ASZTM3VZZZHVENGES":100},{"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":39,"commitSha":40,"skillDirectory":41,"forksCount":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":44,"ownerDescription":45,"updatedAt":46,"install":47,"resources":59},"01M7E86J0ASZTM3VZZZHVENGES","weave-prompt",null,"Weave prompt: compare independent adversarial implementations, then adopt the single best one","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\u002F.agents\u002Fskills\u002Fweave-prompt\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: weave-prompt\ndescription: >-\n  Weave prompt: compare independent adversarial implementations, then adopt\n  the single best one\ndisable-model-invocation: true\nallowed-tools: [\"Bash\", \"Read\", \"Grep\", \"Glob\", \"Edit\", \"Write\", \"Task\", \"AskUserQuestion\", \"EnterPlanMode\", \"ExitPlanMode\"]\nmetadata:\n  argument-hint: \"[--passes=N] [--timeout=N|none] [--mode=fast|balanced|deep] [--workers=subagents|model-clis] \u003Cimplementation prompt>\"\n  source: \"plugins\u002Fweave\u002Fskills\u002Fprompt\u002FSKILL.md\"\n---\n\n# Weave Prompt\n\nRun an implementation prompt across independent adversarial workers, using host-native sub-agents by default or separate model CLIs when selected. After all workers finish, compare the implementations and **adopt the single best one**, whole. Unlike the `weave-execute` skill, which cherry-picks the best parts of each worker's work, this command never merges code across implementations.\n\nThe implementation prompt comes from `$ARGUMENTS`. With no prompt, ask the user what they want implemented.\n\nA request like `this skill apply the latest session` runs no workers: follow `references\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 `references\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\n\nBefore any other unresolved configuration choice or operational step, read\n`references\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\nWrite the plan per `references\u002Fmutating-run.md` (Shared phases, Orchestration plan).\n\nPresent it, wait for approval, and exit plan mode (`ExitPlanMode`).\n\n---\n\n## Phase 1: Start the session\n\nFollow `references\u002Fensemble-core.md` (Start the session) with `--command prompt --mutating`; it asks each unresolved setting through `ask-user-choice`. Dispatch per `references\u002Fmutating-run.md` (Shared phases).\n\n---\n\n## Phase 2: Implement in parallel\n\nUse the worker prompt body of `references\u002Fmutating-run.md` (Shared phases), with the implementation prompt as `\u003Cthe task>`.\n\n---\n\n## Phase 3: Compare the implementations\n\nCapture, run the gates, and record the pass per `references\u002Fmutating-run.md` (Shared phases). **Compare** per `ensemble-core.md` (Blind judging, Synthesis protocol), where the judge participant scores. The convergence mode is **pick-winner**: the highest-scoring implementation wins, and no code merges across implementations. Its brief asks it to verify what each implementation does against what its participant claims. A failing quality gate caps that implementation's Correctness at 3. Write the comparison (scores per implementation, quality-gate results, the winner and why) to `\u003Csession_dir>\u002Fpass-NNNN\u002Fsynthesis.md` per `references\u002Fprose-rules.md`.\n\n---\n\n## Phase 4: Multi-pass refinement\n\nFollow `references\u002Fmutating-run.md` (Refinement passes), repeating Phases 2 and 3.\n\n---\n\n## Phase 5: Adopt the chosen implementation\n\nFollow `references\u002Fmutating-run.md` (Apply gate and presentation): show the comparison and the recommended winner, and let the user choose and wait before touching the main checkout.\n\n1. Copy everything the winner captured into the main checkout, deletions included:\n\n   ```console\n   $ python3 \u003Cengine> adopt \\\n       --session \"\u003Csession_dir>\" \\\n       --pass \u003Cfinal N> \\\n       --all \u003Cwinner>\n   ```\n\n   If `adopt` refuses, follow `references\u002Fmutating-run.md` (Apply gate and presentation).\n\n2. Run the project's quality gates, then record the state:\n\n   ```console\n   $ python3 \u003Cengine> update \\\n       --session \"\u003Csession_dir>\" \\\n       --event adoption_applied\n   ```\n\n3. Clean up per `references\u002Fmutating-run.md` (Shared phases) (Apply), checking `git diff --stat HEAD` against the winner's patch.\n\n4. Read `references\u002Fpresent-results.md` and `references\u002Fprompt.md`, and apply them with `RESULT_KIND` = `prompt`, `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 winning participant, the quality-gate result, and unavailable participants with their failure class.\n\n\n## Portability notes\n\n- `ask-user-choice` — follow the source's choice contract. Hosts with a structured multiple-choice tool (Claude Code's `AskUserQuestion`) should use it. Honor a documented headless default when the source defines one; otherwise print a numbered list and wait for a numbered reply. Never invent a choice.\n- `$ARGUMENTS` — the text the user passed when invoking this skill. If your host does not substitute it, read it as the user's request in the current turn, and ask when there is none.\n- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.\n","# Weave Prompt\n\nRun an implementation prompt across independent adversarial workers, using host-native sub-agents by default or separate model CLIs when selected. After all workers finish, compare the implementations and **adopt the single best one**, whole. Unlike the `weave-execute` skill, which cherry-picks the best parts of each worker's work, this command never merges code across implementations.\n\nThe implementation prompt comes from `$ARGUMENTS`. With no prompt, ask the user what they want implemented.\n\nA request like `this skill apply the latest session` runs no workers: follow `references\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 `references\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\n\nBefore any other unresolved configuration choice or operational step, read\n`references\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\nWrite the plan per `references\u002Fmutating-run.md` (Shared phases, Orchestration plan).\n\nPresent it, wait for approval, and exit plan mode (`ExitPlanMode`).\n\n---\n\n## Phase 1: Start the session\n\nFollow `references\u002Fensemble-core.md` (Start the session) with `--command prompt --mutating`; it asks each unresolved setting through `ask-user-choice`. Dispatch per `references\u002Fmutating-run.md` (Shared phases).\n\n---\n\n## Phase 2: Implement in parallel\n\nUse the worker prompt body of `references\u002Fmutating-run.md` (Shared phases), with the implementation prompt as `\u003Cthe task>`.\n\n---\n\n## Phase 3: Compare the implementations\n\nCapture, run the gates, and record the pass per `references\u002Fmutating-run.md` (Shared phases). **Compare** per `ensemble-core.md` (Blind judging, Synthesis protocol), where the judge participant scores. The convergence mode is **pick-winner**: the highest-scoring implementation wins, and no code merges across implementations. Its brief asks it to verify what each implementation does against what its participant claims. A failing quality gate caps that implementation's Correctness at 3. Write the comparison (scores per implementation, quality-gate results, the winner and why) to `\u003Csession_dir>\u002Fpass-NNNN\u002Fsynthesis.md` per `references\u002Fprose-rules.md`.\n\n---\n\n## Phase 4: Multi-pass refinement\n\nFollow `references\u002Fmutating-run.md` (Refinement passes), repeating Phases 2 and 3.\n\n---\n\n## Phase 5: Adopt the chosen implementation\n\nFollow `references\u002Fmutating-run.md` (Apply gate and presentation): show the comparison and the recommended winner, and let the user choose and wait before touching the main checkout.\n\n1. Copy everything the winner captured into the main checkout, deletions included:\n\n   ```console\n   $ python3 \u003Cengine> adopt \\\n       --session \"\u003Csession_dir>\" \\\n       --pass \u003Cfinal N> \\\n       --all \u003Cwinner>\n   ```\n\n   If `adopt` refuses, follow `references\u002Fmutating-run.md` (Apply gate and presentation).\n\n2. Run the project's quality gates, then record the state:\n\n   ```console\n   $ python3 \u003Cengine> update \\\n       --session \"\u003Csession_dir>\" \\\n       --event adoption_applied\n   ```\n\n3. Clean up per `references\u002Fmutating-run.md` (Shared phases) (Apply), checking `git diff --stat HEAD` against the winner's patch.\n\n4. Read `references\u002Fpresent-results.md` and `references\u002Fprompt.md`, and apply them with `RESULT_KIND` = `prompt`, `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 winning participant, the quality-gate result, and unavailable participants with their failure class.\n\n\n## Portability notes\n\n- `ask-user-choice` — follow the source's choice contract. Hosts with a structured multiple-choice tool (Claude Code's `AskUserQuestion`) should use it. Honor a documented headless default when the source defines one; otherwise print a numbered list and wait for a numbered reply. Never invent a choice.\n- `$ARGUMENTS` — the text the user passed when invoking this skill. If your host does not substitute it, read it as the user's request in the current turn, and ask when there is none.\n- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.\n",{"name":5,"metadata":24,"description":7,"allowed-tools":27,"disable-model-invocation":38},{"source":25,"argument-hint":26},"plugins\u002Fweave\u002Fskills\u002Fprompt\u002FSKILL.md","[--passes=N] [--timeout=N|none] [--mode=fast|balanced|deep] [--workers=subagents|model-clis] \u003Cimplementation prompt>",[28,29,30,31,32,33,34,35,36,37],"Bash","Read","Grep","Glob","Edit","Write","Task","AskUserQuestion","EnterPlanMode","ExitPlanMode",true,"main","5fbeb3b47beedea13813be7b7023f736a8d97a65",".agents\u002Fskills\u002Fweave-prompt","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":48,"prompt":58,"zipAvailable":38},[49,52,55],{"tool":50,"command":51},"npx","npx skills add tony\u002Fskills --skill weave-prompt",{"tool":53,"command":54},"bunx","bunx skills add tony\u002Fskills --skill weave-prompt",{"tool":56,"command":57},"pnpm","pnpm dlx skills add tony\u002Fskills --skill weave-prompt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweave-prompt\u002FSKILL.md",[60,66,72,76,80,84,88,92,96],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"agents\u002Fopenai.yaml","REFERENCE","参考文档",292,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweave-prompt\u002Fagents\u002Fopenai.yaml",{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fclosest_model.py","SCRIPT","脚本",6058,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweave-prompt\u002Freferences\u002Fclosest_model.py",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fengine.py",146101,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweave-prompt\u002Freferences\u002Fengine.py",{"path":77,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fensemble-core.md",21855,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweave-prompt\u002Freferences\u002Fensemble-core.md",{"path":81,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fmutating-run.md",11405,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweave-prompt\u002Freferences\u002Fmutating-run.md",{"path":85,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fpresent-results.md",9387,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweave-prompt\u002Freferences\u002Fpresent-results.md",{"path":89,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fprompt.md",773,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweave-prompt\u002Freferences\u002Fprompt.md",{"path":93,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fprose-rules.md",4644,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweave-prompt\u002Freferences\u002Fprose-rules.md",{"path":97,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fworker-backends.md",11050,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweave-prompt\u002Freferences\u002Fworker-backends.md",[101,108,115,122,128,135],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"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":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"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":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"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":123,"name":124,"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":125,"categories":126,"keywords":127,"publishedAt":19},"01M7E8N01KB86A7136P00GVKJW","prompt","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fprompt\u002FSKILL.md",[],[],{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"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":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"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",[],[]]