[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77N7REFJTTD8D56EEB7PD54":3,"skill-same:01M77N7REFJTTD8D56EEB7PD54":80},{"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":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M77N7REFJTTD8D56EEB7PD54","benchmark",null,"Runs, supervises, changes, and publishes ttsc's performance, graph, and evidence benchmarks under benchmarks\u002F. Use before running, changing, or publishing any benchmark or its fixtures.","systemfsoftware\u002Fsystemfsoftware","systemfsoftware","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F172220390?v=4","01M77N4P2T87WAH2KS0GYARYP3","System F Software","01M77N4P3GJRWQAQZ6JNRF99ZB",21,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Fttsc\u002F.agents\u002Fskills\u002Fbenchmark\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: benchmark\ndescription: Runs, supervises, changes, and publishes ttsc's performance, graph, and evidence benchmarks under benchmarks\u002F. Use before running, changing, or publishing any benchmark or its fixtures.\n---\n\n# Benchmark\n\n| Work | Read |\n| --- | --- |\n| Performance harness and its fixture branches | [performance.md](performance.md) |\n| Graph harness, prompts, comparators, traces, and measuring a graph change | [graph.md](graph.md) |\n| Evidence campaign: launch, supervision, dashboard | [evidence\u002Fcampaign.md](evidence\u002Fcampaign.md) |\n| Evidence: whether a cell's edit is allowed, and warning a cell | [evidence\u002Fintegrity.md](evidence\u002Fintegrity.md) |\n| Evidence: a Plain cell's Review boundary | [evidence\u002Freview.md](evidence\u002Freview.md) |\n| Evidence: fixing a repository defect mid-campaign | [evidence\u002Fboundary.md](evidence\u002Fboundary.md) |\n| Evidence: a stopped, hung, or failed cell, or cancellation | [evidence\u002Frecovery.md](evidence\u002Frecovery.md) |\n| Evidence: publishing results and closing the cohort | [evidence\u002Faggregate.md](evidence\u002Faggregate.md) |\n\nThe rules below cover the performance and graph harnesses; the evidence benchmark has its own documents.\n\n- Measure the real product on the full workload, with every comparator set up as its own documentation prescribes. Never restrict an agent or skip input to improve a number.\n- Inspect the raw report or trace behind any surprising result before accepting or explaining it.\n- A CLI entry in `src\u002Fexecutable` only imports one `TtscBenchmark*` owner and calls `main()`, within 12 lines. Every other module exports one `TtscBenchmark*` class or namespace, or one `ITtscBenchmark*` interface with its companion namespace, from a file of that name, and never a standalone function, constant, enum, or type alias. Document each member's role and each field's unit and default. Run the README's strict type check before committing.\n- Give each run its own temporary root, including `GOCACHE` and `GOTMPDIR`, and delete it afterwards unless `--keep-...` or the user says otherwise. Never clean a shared Go cache or temp directory.\n- Edit fixtures in their own repositories, and push a fixture branch only when its build, format, and lint pass and it holds no generated benchmark input.\n- Update the sticky result comment only with [pull-request](..\u002Fpull-request\u002FSKILL.md) authority; otherwise put the table in the report.\n","# Benchmark\n\n| Work | Read |\n| --- | --- |\n| Performance harness and its fixture branches | [performance.md](performance.md) |\n| Graph harness, prompts, comparators, traces, and measuring a graph change | [graph.md](graph.md) |\n| Evidence campaign: launch, supervision, dashboard | [evidence\u002Fcampaign.md](evidence\u002Fcampaign.md) |\n| Evidence: whether a cell's edit is allowed, and warning a cell | [evidence\u002Fintegrity.md](evidence\u002Fintegrity.md) |\n| Evidence: a Plain cell's Review boundary | [evidence\u002Freview.md](evidence\u002Freview.md) |\n| Evidence: fixing a repository defect mid-campaign | [evidence\u002Fboundary.md](evidence\u002Fboundary.md) |\n| Evidence: a stopped, hung, or failed cell, or cancellation | [evidence\u002Frecovery.md](evidence\u002Frecovery.md) |\n| Evidence: publishing results and closing the cohort | [evidence\u002Faggregate.md](evidence\u002Faggregate.md) |\n\nThe rules below cover the performance and graph harnesses; the evidence benchmark has its own documents.\n\n- Measure the real product on the full workload, with every comparator set up as its own documentation prescribes. Never restrict an agent or skip input to improve a number.\n- Inspect the raw report or trace behind any surprising result before accepting or explaining it.\n- A CLI entry in `src\u002Fexecutable` only imports one `TtscBenchmark*` owner and calls `main()`, within 12 lines. Every other module exports one `TtscBenchmark*` class or namespace, or one `ITtscBenchmark*` interface with its companion namespace, from a file of that name, and never a standalone function, constant, enum, or type alias. Document each member's role and each field's unit and default. Run the README's strict type check before committing.\n- Give each run its own temporary root, including `GOCACHE` and `GOTMPDIR`, and delete it afterwards unless `--keep-...` or the user says otherwise. Never clean a shared Go cache or temp directory.\n- Edit fixtures in their own repositories, and push a fixture branch only when its build, format, and lint pass and it holds no generated benchmark input.\n- Update the sticky result comment only with [pull-request](..\u002Fpull-request\u002FSKILL.md) authority; otherwise put the table in the report.\n",{"name":5,"description":7},"main","8a038d9ca9c3f2e7ba7af9ee0ec024e388a46751","repos\u002Fttsc\u002F.agents\u002Fskills\u002Fbenchmark",2,"https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware","https:\u002F\u002Fgithub.com\u002Fsystemfsoftware","https:\u002F\u002Fsystemfsoftware.com\u002F","2026-11-14 09:13:19",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add systemfsoftware\u002Fsystemfsoftware --skill benchmark",{"tool":38,"command":39},"bunx","bunx skills add systemfsoftware\u002Fsystemfsoftware --skill benchmark",{"tool":41,"command":42},"pnpm","pnpm dlx skills add systemfsoftware\u002Fsystemfsoftware --skill benchmark","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Fttsc\u002F.agents\u002Fskills\u002Fbenchmark\u002FSKILL.md",true,[46,52,56,60,64,68,72,76],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"evidence\u002Faggregate.md","REFERENCE","参考文档",1326,"https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Fttsc\u002F.agents\u002Fskills\u002Fbenchmark\u002Fevidence\u002Faggregate.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"evidence\u002Fboundary.md",1201,"https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Fttsc\u002F.agents\u002Fskills\u002Fbenchmark\u002Fevidence\u002Fboundary.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"evidence\u002Fcampaign.md",2110,"https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Fttsc\u002F.agents\u002Fskills\u002Fbenchmark\u002Fevidence\u002Fcampaign.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"evidence\u002Fintegrity.md",2173,"https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Fttsc\u002F.agents\u002Fskills\u002Fbenchmark\u002Fevidence\u002Fintegrity.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"evidence\u002Frecovery.md",1958,"https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Fttsc\u002F.agents\u002Fskills\u002Fbenchmark\u002Fevidence\u002Frecovery.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"evidence\u002Freview.md",1196,"https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Fttsc\u002F.agents\u002Fskills\u002Fbenchmark\u002Fevidence\u002Freview.md",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"graph.md",1354,"https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Fttsc\u002F.agents\u002Fskills\u002Fbenchmark\u002Fgraph.md",{"path":77,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":78,"sourceHtmlUrl":79},"performance.md",926,"https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Fttsc\u002F.agents\u002Fskills\u002Fbenchmark\u002Fperformance.md",[81,88,95,101,108,114],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7BD2282BZGW5BQQD94CQ6W4","contracts","Defines self-acknowledgments for production declarations and tests. Use when implementing or reviewing maintained source, unit tests or E2E tests, or selecting Evidence checklists.","https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Ftypia\u002F.agents\u002Fskills\u002Fcontracts\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7BD1NWTFK6Q3S2HSK2AWFFA","prompting","Writes and trims ttsc's prompts for agents, namely AGENTS.md, CLAUDE.md, and the skills under .agents\u002Fskills. Use before changing any of them, together with the documentation skill's writing rules.","https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Fttsc\u002F.agents\u002Fskills\u002Fprompting\u002FSKILL.md",[],[],{"skillNo":96,"name":83,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7BD1C16RTYT3R4HD7T32V8R","Defines the @evidence checklists every maintained ttsc declaration and test answers, and their evidence.config.json wiring. Use when writing or reviewing maintained source or tests, or changing Evidence selection.","https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Fttsc\u002F.agents\u002Fskills\u002Fcontracts\u002FSKILL.md",[],[],{"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},"01M7BD13ZMCXA6CSYYM8BKZ7JE","alchemy-domain","Build backends with @alchemy.run\u002Fdomain (domain-driven design on Effect) - turn requirements into aggregates, commands, events, rejections, views, policies, sagas, projections, streams, queries, external systems and Apis; lay them out in a monorepo (domain \u002F server \u002F web packages, kind-suffixed files); test them with stories; host them on Durable Objects (Cloudflare, Rivet or Effect Cluster) with alchemy; and drive them from a foldkit frontend. Use when designing or changing an @alchemy.run\u002Fdomain model, adding a building block, wiring hosting or a frontend, or reviewing such code.","https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Falchemy\u002Fpackages\u002Fdomain\u002Fskills\u002Falchemy-domain\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7BD131HNMPMBKNZWMS3M58Z","alchemy-provider","https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Falchemy\u002F.grok\u002Fskills\u002Falchemy-provider\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M7BD1231ZSETXNJV4V5SN0MK","write-docs","https:\u002F\u002Fgithub.com\u002Fsystemfsoftware\u002Fsystemfsoftware\u002Fblob\u002Fmain\u002Frepos\u002Falchemy\u002F.claude\u002Fskills\u002Fwrite-docs\u002FSKILL.md",[],[]]