[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797QKXM1PSWCGXSA90DSWKY":3,"skill-same:01M797QKXM1PSWCGXSA90DSWKY":67},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M797QKXM1PSWCGXSA90DSWKY","inference-and-export",null,"Run zi2zi checkpoint inference, style interpolation, transition GIF planning, and generator-only export from legacy TensorFlow 1.x checkpoints.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzi2zi\u002Fsub-skills\u002Finference-and-export\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: inference-and-export\ndescription: \"Run zi2zi checkpoint inference, style interpolation, transition\n  GIF planning, and generator-only export from legacy TensorFlow 1.x\n  checkpoints.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# zi2zi inference and export\n\nUse this sub-skill when a task is about generating glyphs from a trained zi2zi\ncheckpoint, interpolating between style labels, creating frame sequences or a\nGIF, or exporting generator-only variables for later reuse. It does not launch\nlong inference jobs automatically; it explains the checkpoint contract and\nprints safe command templates.\n\n## Use this sub-skill when\n\n- The user has a checkpoint directory and wants generated glyphs.\n- The task mentions `infer.py`, `export.py`, `model_dir`, `source_obj`,\n  `embedding_ids`, `interpolate`, `steps`, `output_gif`, `uroboros`, or exported\n  generator weights.\n- The user wants to know how inference chooses between single-style generation\n  and random style selection.\n- The user needs to diagnose checkpoint restore failures, output-image naming,\n  or interpolation problems.\n\n## Route elsewhere\n\n- Data rendering and `.obj` packaging go to\n  [data-preparation](..\u002Fdata-preparation\u002FSKILL.md).\n- Training, fine-tuning, or label shuffling go to\n  [training-and-model](..\u002Ftraining-and-model\u002FSKILL.md).\n- Compatibility questions go to the root [compatibility](..\u002F..\u002Freferences\u002Fcompatibility.md)\n  reference.\n\n## Core inference facts\n\n- `infer.py` restores generator variables from a checkpoint and uses a source\n  object file to provide images.\n- If `embedding_ids` contains one integer, the model uses that style for every\n  source image. If it contains multiple IDs, the script picks randomly from the\n  list for each batch.\n- `interpolate=1` asks the model to linearly interpolate between style vectors.\n  With `uroboros=1`, the interpolation path closes the loop by appending the\n  first ID to the end of the chain.\n- `output_gif` triggers GIF compilation from the rendered interpolation frames.\n- `export.py` saves generator-only variables, which include the embedding table\n  and generator weights.\n\n## Output conventions\n\n- Normal inference writes files named `inferred_%04d.png` in the save directory.\n- Interpolation writes `frame_\u003Csrc>_\u003Cdst>_step_\u003Cidx>.png` files.\n- GIF compilation expects those frame PNGs in the save directory and writes the\n  named GIF beside them.\n- Export uses TensorFlow checkpoint naming with a generator model prefix.\n\n## Recommended workflow\n\n1. Verify the checkpoint directory contains a TensorFlow checkpoint state.\n2. Decide whether you want one style ID, a random mix, or interpolation between\n   two or more style IDs.\n3. Confirm the source object file contains paired glyph records and that its\n   batch size is compatible with the inference command.\n4. Use the command planner to validate flags and paths before launching any\n   long job.\n5. Inspect outputs after the first few batches, especially if the chosen style\n   labels or batch size do not match the training run.\n\nRead [inference-workflow.md](references\u002Finference-workflow.md) for command\nshapes and evaluation steps. Read [checkpoints-and-outputs.md](references\u002Fcheckpoints-and-outputs.md)\nfor restore\u002Fexport expectations and filename conventions. Read [troubleshooting.md](references\u002Ftroubleshooting.md)\nfor checkpoint, batch-size, GIF, and source-object failures.\n\n## Bundled helper\n\n- [scripts\u002Fplan_zi2zi_inference.py](scripts\u002Fplan_zi2zi_inference.py) validates\n  inference, interpolation, and export arguments and prints the command that a\n  future agent should run in a legacy zi2zi environment.\n\n## What not to promise automatically\n\n- Do not promise restoration of a checkpoint without checking that the concrete\n  checkpoint files exist and match the chosen hyperparameters.\n- Do not promise a successful interpolation run unless `embedding_ids` contains\n  at least two integers.\n- Do not promise export success if the model directory contains only partial or\n  mismatched checkpoint shards.\n","# zi2zi inference and export\n\nUse this sub-skill when a task is about generating glyphs from a trained zi2zi\ncheckpoint, interpolating between style labels, creating frame sequences or a\nGIF, or exporting generator-only variables for later reuse. It does not launch\nlong inference jobs automatically; it explains the checkpoint contract and\nprints safe command templates.\n\n## Use this sub-skill when\n\n- The user has a checkpoint directory and wants generated glyphs.\n- The task mentions `infer.py`, `export.py`, `model_dir`, `source_obj`,\n  `embedding_ids`, `interpolate`, `steps`, `output_gif`, `uroboros`, or exported\n  generator weights.\n- The user wants to know how inference chooses between single-style generation\n  and random style selection.\n- The user needs to diagnose checkpoint restore failures, output-image naming,\n  or interpolation problems.\n\n## Route elsewhere\n\n- Data rendering and `.obj` packaging go to\n  [data-preparation](..\u002Fdata-preparation\u002FSKILL.md).\n- Training, fine-tuning, or label shuffling go to\n  [training-and-model](..\u002Ftraining-and-model\u002FSKILL.md).\n- Compatibility questions go to the root [compatibility](..\u002F..\u002Freferences\u002Fcompatibility.md)\n  reference.\n\n## Core inference facts\n\n- `infer.py` restores generator variables from a checkpoint and uses a source\n  object file to provide images.\n- If `embedding_ids` contains one integer, the model uses that style for every\n  source image. If it contains multiple IDs, the script picks randomly from the\n  list for each batch.\n- `interpolate=1` asks the model to linearly interpolate between style vectors.\n  With `uroboros=1`, the interpolation path closes the loop by appending the\n  first ID to the end of the chain.\n- `output_gif` triggers GIF compilation from the rendered interpolation frames.\n- `export.py` saves generator-only variables, which include the embedding table\n  and generator weights.\n\n## Output conventions\n\n- Normal inference writes files named `inferred_%04d.png` in the save directory.\n- Interpolation writes `frame_\u003Csrc>_\u003Cdst>_step_\u003Cidx>.png` files.\n- GIF compilation expects those frame PNGs in the save directory and writes the\n  named GIF beside them.\n- Export uses TensorFlow checkpoint naming with a generator model prefix.\n\n## Recommended workflow\n\n1. Verify the checkpoint directory contains a TensorFlow checkpoint state.\n2. Decide whether you want one style ID, a random mix, or interpolation between\n   two or more style IDs.\n3. Confirm the source object file contains paired glyph records and that its\n   batch size is compatible with the inference command.\n4. Use the command planner to validate flags and paths before launching any\n   long job.\n5. Inspect outputs after the first few batches, especially if the chosen style\n   labels or batch size do not match the training run.\n\nRead [inference-workflow.md](references\u002Finference-workflow.md) for command\nshapes and evaluation steps. Read [checkpoints-and-outputs.md](references\u002Fcheckpoints-and-outputs.md)\nfor restore\u002Fexport expectations and filename conventions. Read [troubleshooting.md](references\u002Ftroubleshooting.md)\nfor checkpoint, batch-size, GIF, and source-object failures.\n\n## Bundled helper\n\n- [scripts\u002Fplan_zi2zi_inference.py](scripts\u002Fplan_zi2zi_inference.py) validates\n  inference, interpolation, and export arguments and prints the command that a\n  future agent should run in a legacy zi2zi environment.\n\n## What not to promise automatically\n\n- Do not promise restoration of a checkpoint without checking that the concrete\n  checkpoint files exist and match the chosen hyperparameters.\n- Do not promise a successful interpolation run unless `embedding_ids` contains\n  at least two integers.\n- Do not promise export success if the model directory contains only partial or\n  mismatched checkpoint shards.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fzi2zi\u002Fsub-skills\u002Finference-and-export",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-and-export",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-and-export",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-and-export","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzi2zi\u002Fsub-skills\u002Finference-and-export\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcheckpoints-and-outputs.md","REFERENCE","参考文档",2084,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzi2zi\u002Fsub-skills\u002Finference-and-export\u002Freferences\u002Fcheckpoints-and-outputs.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Finference-workflow.md",2555,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzi2zi\u002Fsub-skills\u002Finference-and-export\u002Freferences\u002Finference-workflow.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",2006,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzi2zi\u002Fsub-skills\u002Finference-and-export\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fplan_zi2zi_inference.py","SCRIPT","脚本",5680,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzi2zi\u002Fsub-skills\u002Finference-and-export\u002Fscripts\u002Fplan_zi2zi_inference.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]