[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797KTPCT39WHP6EMJSSEX9J":3,"skill-same:01M797KTPCT39WHP6EMJSSEX9J":71},{"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},"01M797KTPCT39WHP6EMJSSEX9J","run",null,"Run YiVal experiments through the CLI or Python APIs, interpret result artifacts, and use interactive\u002FDash\u002Fbot workflows.","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\u002Fyi-val\u002Fsub-skills\u002Frun\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: run\ndescription: \"Run YiVal experiments through the CLI or Python APIs, interpret\n  result artifacts, and use interactive\u002FDash\u002Fbot workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# YiVal run workflows\n\nUse this sub-skill when the config is ready and the user wants to run YiVal, inspect outputs, resume from saved experiment data, use the Dash\u002Finteractive UI, or call `ExperimentRunner` \u002F `LiteExperimentRunner` programmatically.\n\n## Read first\n\n- [Runtime workflows](references\u002Fruntime-workflows.md): CLI and API execution patterns.\n- [Runner API](references\u002Frunner-api.md): `ExperimentRunner`, `LiteExperimentRunner`, state, output pickle behavior.\n- [Output and UI](references\u002Foutput-and-ui.md): result structures, Dash, Streamlit\u002Fbot, interactive mode.\n- [Runtime troubleshooting](references\u002Ftroubleshooting.md): run-time failures and fixes.\n\n## Safe pre-run checks\n\n1. Run installation smoke from the skill root: `python scripts\u002Fcheck_install.py`.\n2. Validate YAML using the setup sub-skill.\n3. Run a tiny no-network fixture from the skill root: `python scripts\u002Fwrite_minimal_experiment.py --run`.\n4. For provider-backed configs, verify environment variables and set small `number_of_examples` \u002F `number_of_variations` first.\n\n## CLI run patterns\n\n```bash\nyival validate config.yml\nyival run config.yml --output_path results.pkl\n```\n\nFor non-blocking\u002Fheadless automation, prefer Python API:\n\n```python\nfrom yival.experiment.experiment_runner import ExperimentRunner\n\nrunner = ExperimentRunner(\"config.yml\")\nrunner.run(display=False, interactive=False, output_path=\"results.pkl\", experiment_input_path=\"\")\n```\n\nWhy: CLI `--display` defaults to `True`, so it may start Dash and block until the UI server exits.\n\n## Programmatic runner selection\n\n| Need | Use |\n| --- | --- |\n| YAML-driven full experiment | `ExperimentRunner(config_path).run(...)` |\n| Existing in-memory data\u002Fevaluator\u002Fconfig | `LiteExperimentRunner(...).run_experiment(enable_selector=True\u002FFalse)` |\n| Async custom function | `ExperimentRunner.run(async_eval=True)` and ensure the custom function is coroutine-compatible |\n| Reuse saved experiment pickle | `ExperimentRunner.run(experiment_input_path=\"previous.pkl\", ...)` |\n| Interactive user input | `dataset.source_type: user_input` or `yival demo --basic_interactive` |\n| Chat\u002Fbot over experiment output | `yival bot config.yml` after checking UI constraints |\n\n## Runtime sequence inside `ExperimentRunner`\n\n1. Load one or more configs with `load_and_validate_configs()`.\n2. Register custom components from the YAML.\n3. Build `Evaluator` and `ExperimentState`.\n4. Build all variation combinations from the state.\n5. Process data with `DataProcessor` unless reusing an experiment pickle.\n6. Call the custom function for each data row \u002F combination.\n7. Evaluate individual results and aggregate metrics into an `Experiment`.\n8. Apply selection strategy, enhancer, and optional trainer when configured.\n9. Write pickle output and optionally launch Dash\u002Finteractive\u002Fbot UI.\n\n## Output interpretation\n\n- `output_path=\"results.pkl\"` writes `results_0.pkl` for the first config.\n- Each `ExperimentResult` contains `input_data`, `combination`, `raw_output`, `latency`, `token_usage`, and `evaluator_outputs`.\n- `Experiment.combination_aggregated_metrics` is where AHP selection reads metrics such as `average_token_usage`, `average_latency`, and aggregated evaluator names.\n- `Experiment.selection_output.best_combination` is a stringified combination key when a selection strategy runs.\n\n## When to route elsewhere\n\n- If the config will generate examples or prompt variations, read [prompt-automation](..\u002Fprompt-automation\u002FSKILL.md).\n- If selecting metrics, evaluators, human ratings, or enhancers is the main issue, read [evaluation-optimization](..\u002Fevaluation-optimization\u002FSKILL.md).\n- If custom components fail to register or import, read [custom-components](..\u002Fcustom-components\u002FSKILL.md).\n- If the user asks for fine-tuning\u002Ftraining, state that it is optional and heavy, then require explicit approval for trainer extras, credentials, downloads, GPU, and cost before proceeding.\n","# YiVal run workflows\n\nUse this sub-skill when the config is ready and the user wants to run YiVal, inspect outputs, resume from saved experiment data, use the Dash\u002Finteractive UI, or call `ExperimentRunner` \u002F `LiteExperimentRunner` programmatically.\n\n## Read first\n\n- [Runtime workflows](references\u002Fruntime-workflows.md): CLI and API execution patterns.\n- [Runner API](references\u002Frunner-api.md): `ExperimentRunner`, `LiteExperimentRunner`, state, output pickle behavior.\n- [Output and UI](references\u002Foutput-and-ui.md): result structures, Dash, Streamlit\u002Fbot, interactive mode.\n- [Runtime troubleshooting](references\u002Ftroubleshooting.md): run-time failures and fixes.\n\n## Safe pre-run checks\n\n1. Run installation smoke from the skill root: `python scripts\u002Fcheck_install.py`.\n2. Validate YAML using the setup sub-skill.\n3. Run a tiny no-network fixture from the skill root: `python scripts\u002Fwrite_minimal_experiment.py --run`.\n4. For provider-backed configs, verify environment variables and set small `number_of_examples` \u002F `number_of_variations` first.\n\n## CLI run patterns\n\n```bash\nyival validate config.yml\nyival run config.yml --output_path results.pkl\n```\n\nFor non-blocking\u002Fheadless automation, prefer Python API:\n\n```python\nfrom yival.experiment.experiment_runner import ExperimentRunner\n\nrunner = ExperimentRunner(\"config.yml\")\nrunner.run(display=False, interactive=False, output_path=\"results.pkl\", experiment_input_path=\"\")\n```\n\nWhy: CLI `--display` defaults to `True`, so it may start Dash and block until the UI server exits.\n\n## Programmatic runner selection\n\n| Need | Use |\n| --- | --- |\n| YAML-driven full experiment | `ExperimentRunner(config_path).run(...)` |\n| Existing in-memory data\u002Fevaluator\u002Fconfig | `LiteExperimentRunner(...).run_experiment(enable_selector=True\u002FFalse)` |\n| Async custom function | `ExperimentRunner.run(async_eval=True)` and ensure the custom function is coroutine-compatible |\n| Reuse saved experiment pickle | `ExperimentRunner.run(experiment_input_path=\"previous.pkl\", ...)` |\n| Interactive user input | `dataset.source_type: user_input` or `yival demo --basic_interactive` |\n| Chat\u002Fbot over experiment output | `yival bot config.yml` after checking UI constraints |\n\n## Runtime sequence inside `ExperimentRunner`\n\n1. Load one or more configs with `load_and_validate_configs()`.\n2. Register custom components from the YAML.\n3. Build `Evaluator` and `ExperimentState`.\n4. Build all variation combinations from the state.\n5. Process data with `DataProcessor` unless reusing an experiment pickle.\n6. Call the custom function for each data row \u002F combination.\n7. Evaluate individual results and aggregate metrics into an `Experiment`.\n8. Apply selection strategy, enhancer, and optional trainer when configured.\n9. Write pickle output and optionally launch Dash\u002Finteractive\u002Fbot UI.\n\n## Output interpretation\n\n- `output_path=\"results.pkl\"` writes `results_0.pkl` for the first config.\n- Each `ExperimentResult` contains `input_data`, `combination`, `raw_output`, `latency`, `token_usage`, and `evaluator_outputs`.\n- `Experiment.combination_aggregated_metrics` is where AHP selection reads metrics such as `average_token_usage`, `average_latency`, and aggregated evaluator names.\n- `Experiment.selection_output.best_combination` is a stringified combination key when a selection strategy runs.\n\n## When to route elsewhere\n\n- If the config will generate examples or prompt variations, read [prompt-automation](..\u002Fprompt-automation\u002FSKILL.md).\n- If selecting metrics, evaluators, human ratings, or enhancers is the main issue, read [evaluation-optimization](..\u002Fevaluation-optimization\u002FSKILL.md).\n- If custom components fail to register or import, read [custom-components](..\u002Fcustom-components\u002FSKILL.md).\n- If the user asks for fine-tuning\u002Ftraining, state that it is optional and heavy, then require explicit approval for trainer extras, credentials, downloads, GPU, and cost before proceeding.\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\u002Fyi-val\u002Fsub-skills\u002Frun",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 run",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill run",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill run","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyi-val\u002Fsub-skills\u002Frun\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Foutput-and-ui.md","REFERENCE","参考文档",1637,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyi-val\u002Fsub-skills\u002Frun\u002Freferences\u002Foutput-and-ui.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frunner-api.md",2207,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyi-val\u002Fsub-skills\u002Frun\u002Freferences\u002Frunner-api.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fruntime-workflows.md",2157,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyi-val\u002Fsub-skills\u002Frun\u002Freferences\u002Fruntime-workflows.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",2250,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyi-val\u002Fsub-skills\u002Frun\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Finspect_pickle.py","SCRIPT","脚本",1647,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyi-val\u002Fsub-skills\u002Frun\u002Fscripts\u002Finspect_pickle.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]