[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796NCRNT5A5TXN8JM537AB1":3,"skill-same:01M796NCRNT5A5TXN8JM537AB1":82},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M796NCRNT5A5TXN8JM537AB1","tree-of-thoughts-llm",null,"Routes Tree of Thoughts workflows for game24, coherent passage generation, and mini-crossword solving, with shared installation and execution guidance.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftree-of-thoughts-llm\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tree-of-thoughts-llm\ndescription: \"Routes Tree of Thoughts workflows for game24, coherent passage\n  generation, and mini-crossword solving, with shared installation and execution\n  guidance.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Tree of Thoughts LLM\n\nUse this skill for the Princeton NLP Tree of Thoughts repository and package.\nIt focuses on the bundled `tot` package, the shared runner, and the three\npublic task modes: arithmetic puzzles, coherent text generation, and mini\ncrossword solving.\n\n## Fast start\n\n- Install from PyPI: `pip install tree-of-thoughts-llm`\n- Install from a checkout: `pip install -e .`\n- Required runtime setting: `OPENAI_API_KEY`\n- Optional proxy\u002Fbase URL: `OPENAI_API_BASE`\n- Smoke check: `python scripts\u002Fcheck_install.py`\n\n## Choose a route\n\n- `sub-skills\u002Fgame24\u002F` for 24-game arithmetic trajectories, ToT BFS, and\n  naive sampling baselines.\n- `sub-skills\u002Ftext\u002F` for coherent passage generation, sample\u002Fvote runs, and\n  GPT-based coherency scoring.\n- `sub-skills\u002Fcrosswords\u002F` for 5x5 mini crosswords, naive sampling, and the\n  notebook-derived DFS search workflow.\n\n## Shared runtime helper\n\n- `scripts\u002Frun_tot.py` is the bundled runner that mirrors the repository\n  runner interface and writes JSON logs under `.\u002Flogs\u002F` relative to the launch\n  directory.\n- `scripts\u002Fcheck_install.py` confirms the runtime package install, public\n  metadata, and the three task constructors from the active environment.\n\n## What this skill does not do\n\n- It does not depend on the original checkout being present at runtime.\n- It does not bundle private API keys, proxies, or machine-specific paths.\n- It does not run the paper experiments automatically; use the route-specific\n  sub-skill scripts or the shared runner with explicit task arguments.\n\n## Shared prerequisites\n\nThe package is pure Python, but the workflows call the OpenAI Chat Completions\nAPI. Expect the following before running any task mode:\n\n- A valid OpenAI key in `OPENAI_API_KEY`.\n- A reachable API endpoint, optionally overridden with `OPENAI_API_BASE`.\n- Network access to the chosen backend.\n- The runtime package installed with its pinned dependencies.\n\n## Read next\n\n- `references\u002Fworkflows.md` for the shared ToT execution model and extension\n  notes.\n- `references\u002Fcli-reference.md` for the bundled runner flags and example\n  commands.\n- `references\u002Fapi-reference.md` for verified package functions and task\n  classes.\n- `references\u002Ftroubleshooting.md` for install, import, API, and parsing\n  failures.\n- `references\u002Frepo-provenance.md` before refreshing this skill from a newer\n  checkout.\n","# Tree of Thoughts LLM\n\nUse this skill for the Princeton NLP Tree of Thoughts repository and package.\nIt focuses on the bundled `tot` package, the shared runner, and the three\npublic task modes: arithmetic puzzles, coherent text generation, and mini\ncrossword solving.\n\n## Fast start\n\n- Install from PyPI: `pip install tree-of-thoughts-llm`\n- Install from a checkout: `pip install -e .`\n- Required runtime setting: `OPENAI_API_KEY`\n- Optional proxy\u002Fbase URL: `OPENAI_API_BASE`\n- Smoke check: `python scripts\u002Fcheck_install.py`\n\n## Choose a route\n\n- `sub-skills\u002Fgame24\u002F` for 24-game arithmetic trajectories, ToT BFS, and\n  naive sampling baselines.\n- `sub-skills\u002Ftext\u002F` for coherent passage generation, sample\u002Fvote runs, and\n  GPT-based coherency scoring.\n- `sub-skills\u002Fcrosswords\u002F` for 5x5 mini crosswords, naive sampling, and the\n  notebook-derived DFS search workflow.\n\n## Shared runtime helper\n\n- `scripts\u002Frun_tot.py` is the bundled runner that mirrors the repository\n  runner interface and writes JSON logs under `.\u002Flogs\u002F` relative to the launch\n  directory.\n- `scripts\u002Fcheck_install.py` confirms the runtime package install, public\n  metadata, and the three task constructors from the active environment.\n\n## What this skill does not do\n\n- It does not depend on the original checkout being present at runtime.\n- It does not bundle private API keys, proxies, or machine-specific paths.\n- It does not run the paper experiments automatically; use the route-specific\n  sub-skill scripts or the shared runner with explicit task arguments.\n\n## Shared prerequisites\n\nThe package is pure Python, but the workflows call the OpenAI Chat Completions\nAPI. Expect the following before running any task mode:\n\n- A valid OpenAI key in `OPENAI_API_KEY`.\n- A reachable API endpoint, optionally overridden with `OPENAI_API_BASE`.\n- Network access to the chosen backend.\n- The runtime package installed with its pinned dependencies.\n\n## Read next\n\n- `references\u002Fworkflows.md` for the shared ToT execution model and extension\n  notes.\n- `references\u002Fcli-reference.md` for the bundled runner flags and example\n  commands.\n- `references\u002Fapi-reference.md` for verified package functions and task\n  classes.\n- `references\u002Ftroubleshooting.md` for install, import, API, and parsing\n  failures.\n- `references\u002Frepo-provenance.md` before refreshing this skill from a newer\n  checkout.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Ftree-of-thoughts-llm",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill tree-of-thoughts-llm",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill tree-of-thoughts-llm",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill tree-of-thoughts-llm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftree-of-thoughts-llm\u002FSKILL.md",[46,52,56,60,64,68,72,78],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",4563,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftree-of-thoughts-llm\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fcli-reference.md",2408,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftree-of-thoughts-llm\u002Freferences\u002Fcli-reference.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-provenance.md",981,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftree-of-thoughts-llm\u002Freferences\u002Frepo-provenance.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Frepo-routing-metadata.json",361,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftree-of-thoughts-llm\u002Freferences\u002Frepo-routing-metadata.json",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftroubleshooting.md",2812,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftree-of-thoughts-llm\u002Freferences\u002Ftroubleshooting.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fworkflows.md",2022,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftree-of-thoughts-llm\u002Freferences\u002Fworkflows.md",{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"scripts\u002Fcheck_install.py","SCRIPT","脚本",632,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftree-of-thoughts-llm\u002Fscripts\u002Fcheck_install.py",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Frun_tot.py",2976,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftree-of-thoughts-llm\u002Fscripts\u002Frun_tot.py",[83,91,98,105,112,119],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]