[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78VMV8J18JA4JHAR0DAFMP8":3,"skill-same:01M78VMV8J18JA4JHAR0DAFMP8":70},{"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},"01M78VMV8J18JA4JHAR0DAFMP8","deep-daze",null,"Use deep-daze for CLIP-guided Siren image generation through the imagine CLI and Python APIs, with runtime inspection and troubleshooting.","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\u002Fdeep-daze\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deep-daze\ndescription: \"Use deep-daze for CLIP-guided Siren image generation through the\n  imagine CLI and Python APIs, with runtime inspection and troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Deep Daze\n\nUse this repo skill when a task involves the `deep-daze` \u002F `deep_daze` package:\nCLIP-guided text-to-image generation, image-conditioned generation, start-image\npriming, story mode, the `imagine` command, or programmatic `Imagine` and\n`DeepDaze` usage.\n\nDeep Daze combines OpenAI CLIP guidance with a Siren generator. Generation is an\noptimization run, not a one-shot inference call: it can download CLIP weights,\nconsume substantial VRAM or CPU time, and write image\u002Fprogress artifacts in the\ncurrent working directory.\n\n## Quick install and identity checks\n\nInstall the public package in the user's environment:\n\n```bash\npython -m pip install deep-daze\n```\n\nMinimal import and package-data check:\n\n```bash\npython - \u003C\u003C'PY'\nfrom deep_daze import DeepDaze, Imagine\nfrom deep_daze.clip import available_models, tokenize\nprint(DeepDaze.__name__, Imagine.__name__)\nprint(available_models())\nprint(tuple(tokenize('a house').shape))\nPY\n```\n\nExpected CLIP model names are `RN50`, `RN101`, `RN50x4`, `ViT-B\u002F32`, and\n`ViT-L\u002F14`; `ViT-B\u002F32` is the default model. `tokenize('a house')` should return\nshape `(1, 77)`.\n\nFor a safe inspection that does not download model checkpoints or generate\nimages, run the bundled helper:\n\n```bash\npython scripts\u002Fdeep_daze_inspect.py\n```\n\nRead [references\u002Fusage-overview.md](references\u002Fusage-overview.md) for the\npackage concept map and [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md)\nfor cross-cutting failures.\n\n## Route by task\n\n| User task | Read next |\n|---|---|\n| Verify install\u002Fimport, dependency presence, CLIP model names, tokenizer package data, cache\u002Fdownload behavior, CPU\u002FGPU backend status, or VRAM expectations. | [sub-skills\u002Fruntime-and-models\u002FSKILL.md](sub-skills\u002Fruntime-and-models\u002FSKILL.md) |\n| Build or debug an `imagine` command for text prompts, image targets, text+image conditioning, start-image priming, story mode, progress frames, GIF\u002Fvideo output, or headless execution. | [sub-skills\u002Fcli-workflows\u002FSKILL.md](sub-skills\u002Fcli-workflows\u002FSKILL.md) |\n| Use `deep_daze.Imagine` or lower-level `DeepDaze` from Python, translate CLI settings into code, inspect signatures\u002Fdefaults, use custom CLIP encodings, or control output paths programmatically. | [sub-skills\u002Fpython-api\u002FSKILL.md](sub-skills\u002Fpython-api\u002FSKILL.md) |\n\n## Safe operating defaults\n\n- Start with small `epochs`, `iterations`, `image_width`, and `batch_size` until\n  the prompt, output path, and runtime are known to work.\n- Use `open_folder=False` in scripts, notebooks, remote shells, and headless\n  agents.\n- Use `save_date_time=True` or a clean output directory to avoid CLI overwrite\n  prompts.\n- Keep ordinary prompts within CLIP's 77-token context. Use story mode for long\n  prose, with `save_progress=True` when the transition frames matter.\n- Treat full generation as a potentially long\u002Fnetworked run. It may download a\n  CLIP checkpoint into the user's cache before training starts.\n\n## Useful entry points\n\n- CLI: `imagine \"a house in the forest\" --open_folder=False`\n- Python: `from deep_daze import Imagine`\n- Runtime CLIP utilities: `from deep_daze.clip import available_models, tokenize`\n- Lower-level generator module: `from deep_daze import DeepDaze`\n\n## Validation guidance\n\nUse the bundled inspection helpers and CLI\u002FAPI probes before expensive runs:\n\n- [scripts\u002Fdeep_daze_inspect.py](scripts\u002Fdeep_daze_inspect.py) checks the shared\n  package\u002Fruntime surface.\n- [sub-skills\u002Fruntime-and-models\u002Fscripts\u002Fcheck_deep_daze_runtime.py](sub-skills\u002Fruntime-and-models\u002Fscripts\u002Fcheck_deep_daze_runtime.py)\n  performs a deeper runtime preflight.\n- [sub-skills\u002Fcli-workflows\u002Fscripts\u002Fbuild_imagine_command.py](sub-skills\u002Fcli-workflows\u002Fscripts\u002Fbuild_imagine_command.py)\n  builds a shell-quoted command without running generation.\n- [sub-skills\u002Fpython-api\u002Fscripts\u002Fprobe_api_surface.py](sub-skills\u002Fpython-api\u002Fscripts\u002Fprobe_api_surface.py)\n  checks API signatures\u002Fdefaults without constructing `Imagine`.\n\n## Provenance and refresh\n\nRead [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before using\nthis skill against a different checkout or package version. If the source\ncommit, dirty state, package version, public entry points, CLI signature, or\ncore source layout changed, refresh the repo skill before relying on details.\n","# Deep Daze\n\nUse this repo skill when a task involves the `deep-daze` \u002F `deep_daze` package:\nCLIP-guided text-to-image generation, image-conditioned generation, start-image\npriming, story mode, the `imagine` command, or programmatic `Imagine` and\n`DeepDaze` usage.\n\nDeep Daze combines OpenAI CLIP guidance with a Siren generator. Generation is an\noptimization run, not a one-shot inference call: it can download CLIP weights,\nconsume substantial VRAM or CPU time, and write image\u002Fprogress artifacts in the\ncurrent working directory.\n\n## Quick install and identity checks\n\nInstall the public package in the user's environment:\n\n```bash\npython -m pip install deep-daze\n```\n\nMinimal import and package-data check:\n\n```bash\npython - \u003C\u003C'PY'\nfrom deep_daze import DeepDaze, Imagine\nfrom deep_daze.clip import available_models, tokenize\nprint(DeepDaze.__name__, Imagine.__name__)\nprint(available_models())\nprint(tuple(tokenize('a house').shape))\nPY\n```\n\nExpected CLIP model names are `RN50`, `RN101`, `RN50x4`, `ViT-B\u002F32`, and\n`ViT-L\u002F14`; `ViT-B\u002F32` is the default model. `tokenize('a house')` should return\nshape `(1, 77)`.\n\nFor a safe inspection that does not download model checkpoints or generate\nimages, run the bundled helper:\n\n```bash\npython scripts\u002Fdeep_daze_inspect.py\n```\n\nRead [references\u002Fusage-overview.md](references\u002Fusage-overview.md) for the\npackage concept map and [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md)\nfor cross-cutting failures.\n\n## Route by task\n\n| User task | Read next |\n|---|---|\n| Verify install\u002Fimport, dependency presence, CLIP model names, tokenizer package data, cache\u002Fdownload behavior, CPU\u002FGPU backend status, or VRAM expectations. | [sub-skills\u002Fruntime-and-models\u002FSKILL.md](sub-skills\u002Fruntime-and-models\u002FSKILL.md) |\n| Build or debug an `imagine` command for text prompts, image targets, text+image conditioning, start-image priming, story mode, progress frames, GIF\u002Fvideo output, or headless execution. | [sub-skills\u002Fcli-workflows\u002FSKILL.md](sub-skills\u002Fcli-workflows\u002FSKILL.md) |\n| Use `deep_daze.Imagine` or lower-level `DeepDaze` from Python, translate CLI settings into code, inspect signatures\u002Fdefaults, use custom CLIP encodings, or control output paths programmatically. | [sub-skills\u002Fpython-api\u002FSKILL.md](sub-skills\u002Fpython-api\u002FSKILL.md) |\n\n## Safe operating defaults\n\n- Start with small `epochs`, `iterations`, `image_width`, and `batch_size` until\n  the prompt, output path, and runtime are known to work.\n- Use `open_folder=False` in scripts, notebooks, remote shells, and headless\n  agents.\n- Use `save_date_time=True` or a clean output directory to avoid CLI overwrite\n  prompts.\n- Keep ordinary prompts within CLIP's 77-token context. Use story mode for long\n  prose, with `save_progress=True` when the transition frames matter.\n- Treat full generation as a potentially long\u002Fnetworked run. It may download a\n  CLIP checkpoint into the user's cache before training starts.\n\n## Useful entry points\n\n- CLI: `imagine \"a house in the forest\" --open_folder=False`\n- Python: `from deep_daze import Imagine`\n- Runtime CLIP utilities: `from deep_daze.clip import available_models, tokenize`\n- Lower-level generator module: `from deep_daze import DeepDaze`\n\n## Validation guidance\n\nUse the bundled inspection helpers and CLI\u002FAPI probes before expensive runs:\n\n- [scripts\u002Fdeep_daze_inspect.py](scripts\u002Fdeep_daze_inspect.py) checks the shared\n  package\u002Fruntime surface.\n- [sub-skills\u002Fruntime-and-models\u002Fscripts\u002Fcheck_deep_daze_runtime.py](sub-skills\u002Fruntime-and-models\u002Fscripts\u002Fcheck_deep_daze_runtime.py)\n  performs a deeper runtime preflight.\n- [sub-skills\u002Fcli-workflows\u002Fscripts\u002Fbuild_imagine_command.py](sub-skills\u002Fcli-workflows\u002Fscripts\u002Fbuild_imagine_command.py)\n  builds a shell-quoted command without running generation.\n- [sub-skills\u002Fpython-api\u002Fscripts\u002Fprobe_api_surface.py](sub-skills\u002Fpython-api\u002Fscripts\u002Fprobe_api_surface.py)\n  checks API signatures\u002Fdefaults without constructing `Imagine`.\n\n## Provenance and refresh\n\nRead [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before using\nthis skill against a different checkout or package version. If the source\ncommit, dirty state, package version, public entry points, CLI signature, or\ncore source layout changed, refresh the repo skill before relying on details.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fdeep-daze",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 deep-daze",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill deep-daze",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill deep-daze","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeep-daze\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Frepo-provenance.md","REFERENCE","参考文档",2158,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeep-daze\u002Freferences\u002Frepo-provenance.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-routing-metadata.json",416,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeep-daze\u002Freferences\u002Frepo-routing-metadata.json",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",4914,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeep-daze\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fusage-overview.md",3540,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeep-daze\u002Freferences\u002Fusage-overview.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fdeep_daze_inspect.py","SCRIPT","脚本",5100,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeep-daze\u002Fscripts\u002Fdeep_daze_inspect.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]