[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M790FBVSWT5ZGCDDQRPNDRPD":3,"skill-same:01M790FBVSWT5ZGCDDQRPNDRPD":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},"01M790FBVSWT5ZGCDDQRPNDRPD","mljar-supervised",null,"Use MLJAR AutoML for tabular classification, regression, fairness-aware training, reports, persistence, and generated Mercury apps.","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\u002Fmljar-supervised\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mljar-supervised\ndescription: \"Use MLJAR AutoML for tabular classification, regression,\n  fairness-aware training, reports, persistence, and generated Mercury apps.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# MLJAR Supervised\n\nUse this repo skill when a task involves `mljar-supervised`, `supervised.AutoML`, MLJAR AutoML, automated tabular machine learning, MLJAR reports, fairness-aware AutoML, or generated Mercury prediction apps.\n\nMLJAR Supervised trains supervised AutoML pipelines for tabular binary classification, multiclass classification, and regression. It handles common preprocessing, model search, reports, explainability outputs, fairness options, persistence, and app generation through the Python package imported as `supervised`.\n\n## Start here\n\n1. Confirm the package is installed and importable:\n\n   ```python\n   from supervised import AutoML\n   print(AutoML)\n   ```\n\n   For a more detailed local check, run [`scripts\u002Fcheck_mljar_supervised_install.py`](scripts\u002Fcheck_mljar_supervised_install.py).\n2. Identify whether the user wants to train a model, prepare data, inspect an existing run, add fairness constraints, or build an app.\n3. Route to the focused sub-skill below before giving detailed API, data, report, or deployment instructions.\n4. Keep user examples bounded: disable expensive feature engineering and explanations for smoke checks; use larger `Perform`, `Compete`, or `Optuna` runs only when the user accepts the runtime.\n\n## Route map\n\n| User intent | Read |\n| --- | --- |\n| Train\u002Fconfigure `AutoML`, choose `mode`, algorithms, validation, metrics, time limits, ensembling\u002Fstacking, predict\u002Fscore\u002Fretrain | [`training-core`](sub-skills\u002Ftraining-core\u002F) |\n| Prepare `X`, `y`, `sample_weight`, custom CV, missing\u002Fcategorical\u002Ftext\u002Fdatetime columns, target inference, preprocessing and feature-engineering flags | [`data-preprocessing`](sub-skills\u002Fdata-preprocessing\u002F) |\n| Inspect `results_path`, load saved runs, use leaderboards, reports, structured reports, explainability artifacts, SHAP\u002Fimportance\u002Flearning curves, persistence | [`artifacts-reports`](sub-skills\u002Fartifacts-reports\u002F) |\n| Configure fairness-aware training with `sensitive_features`, fairness metrics, thresholds, privileged\u002Funderprivileged groups, fairness reports | [`fairness-workflows`](sub-skills\u002Ffairness-workflows\u002F) |\n| Generate app files, preview locally with Mercury, or prepare guarded publishing with `app()`, `local_app()`, `publish_app()` | [`app-deployment`](sub-skills\u002Fapp-deployment\u002F) |\n\n## Package assumptions\n\n- Distribution name: `mljar-supervised`; import name: `supervised`.\n- Main public class: `supervised.AutoML`.\n- Supported ML tasks: binary classification, multiclass classification, and regression.\n- Built-in modes: `Explain`, `Perform`, `Compete`, and `Optuna`.\n- Common algorithms include `Baseline`, `Linear`, `Decision Tree`, `Random Forest`, `Extra Trees`, `LightGBM`, `Xgboost`, `CatBoost`, `Neural Network`, and `Nearest Neighbors`.\n- Core workflows are CPU-compatible. GPU hardware is not required for this skill's selected scope.\n- Optional surfaces can need extra system\u002Fruntime setup: Graphviz for some tree visualizations and Mercury plus browser\u002Fnetwork\u002Fauth for local or hosted apps.\n\nRead [`references\u002Fpackage-overview.md`](references\u002Fpackage-overview.md) for install prerequisites, high-level capabilities, optional dependencies, and safe smoke-test strategy. Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for cross-cutting install\u002Fimport\u002Fdependency failures.\n\n## Common operating patterns\n\n- For a quick user-data smoke, use `AutoML(mode=\"Explain\", algorithms=[\"Baseline\", \"Decision Tree\"], explain_level=0, train_ensemble=False, stack_models=False, golden_features=False, features_selection=False, total_time_limit=30)` and a disposable `results_path`.\n- For production-style tabular modeling, start from `mode=\"Perform\"`, set a realistic `total_time_limit`, and keep `results_path` stable for later reports and reload.\n- For competition or maximum-performance work, use `mode=\"Compete\"` or `mode=\"Optuna\"` only after discussing runtime, validation, stacking, and per-algorithm tuning budgets.\n- For saved runs, load the full AutoML results directory with `AutoML(results_path=\"...\")`; do not load learner files directly unless a sub-skill explicitly says why.\n- For fairness, pass sensitive features to `fit(..., sensitive_features=...)` and choose task-compatible fairness metrics.\n- For generated apps, call `automl.app()` to create files first; do not start Mercury or publish without explicit user approval.\n\n## Bundled checks\n\n- [`scripts\u002Fcheck_mljar_supervised_install.py`](scripts\u002Fcheck_mljar_supervised_install.py): import\u002Fversion\u002Fsignature and optional dependency probe.\n- [`sub-skills\u002Ftraining-core\u002Fscripts\u002Fmljar_automl_smoke.py`](sub-skills\u002Ftraining-core\u002Fscripts\u002Fmljar_automl_smoke.py): tiny synthetic training\u002Fprediction smoke.\n- [`sub-skills\u002Fdata-preprocessing\u002Fscripts\u002Finspect_preprocessing_behaviour.py`](sub-skills\u002Fdata-preprocessing\u002Fscripts\u002Finspect_preprocessing_behaviour.py): lightweight preprocessing utility checks.\n- [`sub-skills\u002Fartifacts-reports\u002Fscripts\u002Fstructured_report_smoke.py`](sub-skills\u002Fartifacts-reports\u002Fscripts\u002Fstructured_report_smoke.py): tiny structured-report and reload smoke.\n- [`sub-skills\u002Ffairness-workflows\u002Fscripts\u002Ffairness_smoke.py`](sub-skills\u002Ffairness-workflows\u002Fscripts\u002Ffairness_smoke.py): tiny fairness-aware fit and report signal check.\n- [`sub-skills\u002Fapp-deployment\u002Fscripts\u002Fgenerate_app_workspace_smoke.py`](sub-skills\u002Fapp-deployment\u002Fscripts\u002Fgenerate_app_workspace_smoke.py): tiny app-workspace generation check without serving or publishing.\n\n## Refresh and provenance\n\nRead [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) before deciding whether this skill is current for a checkout. If the package version, commit, public `AutoML` signatures, docs, examples, or test-backed behavior changed, run `refresh-repo-skill` instead of relying on this snapshot.\n","# MLJAR Supervised\n\nUse this repo skill when a task involves `mljar-supervised`, `supervised.AutoML`, MLJAR AutoML, automated tabular machine learning, MLJAR reports, fairness-aware AutoML, or generated Mercury prediction apps.\n\nMLJAR Supervised trains supervised AutoML pipelines for tabular binary classification, multiclass classification, and regression. It handles common preprocessing, model search, reports, explainability outputs, fairness options, persistence, and app generation through the Python package imported as `supervised`.\n\n## Start here\n\n1. Confirm the package is installed and importable:\n\n   ```python\n   from supervised import AutoML\n   print(AutoML)\n   ```\n\n   For a more detailed local check, run [`scripts\u002Fcheck_mljar_supervised_install.py`](scripts\u002Fcheck_mljar_supervised_install.py).\n2. Identify whether the user wants to train a model, prepare data, inspect an existing run, add fairness constraints, or build an app.\n3. Route to the focused sub-skill below before giving detailed API, data, report, or deployment instructions.\n4. Keep user examples bounded: disable expensive feature engineering and explanations for smoke checks; use larger `Perform`, `Compete`, or `Optuna` runs only when the user accepts the runtime.\n\n## Route map\n\n| User intent | Read |\n| --- | --- |\n| Train\u002Fconfigure `AutoML`, choose `mode`, algorithms, validation, metrics, time limits, ensembling\u002Fstacking, predict\u002Fscore\u002Fretrain | [`training-core`](sub-skills\u002Ftraining-core\u002F) |\n| Prepare `X`, `y`, `sample_weight`, custom CV, missing\u002Fcategorical\u002Ftext\u002Fdatetime columns, target inference, preprocessing and feature-engineering flags | [`data-preprocessing`](sub-skills\u002Fdata-preprocessing\u002F) |\n| Inspect `results_path`, load saved runs, use leaderboards, reports, structured reports, explainability artifacts, SHAP\u002Fimportance\u002Flearning curves, persistence | [`artifacts-reports`](sub-skills\u002Fartifacts-reports\u002F) |\n| Configure fairness-aware training with `sensitive_features`, fairness metrics, thresholds, privileged\u002Funderprivileged groups, fairness reports | [`fairness-workflows`](sub-skills\u002Ffairness-workflows\u002F) |\n| Generate app files, preview locally with Mercury, or prepare guarded publishing with `app()`, `local_app()`, `publish_app()` | [`app-deployment`](sub-skills\u002Fapp-deployment\u002F) |\n\n## Package assumptions\n\n- Distribution name: `mljar-supervised`; import name: `supervised`.\n- Main public class: `supervised.AutoML`.\n- Supported ML tasks: binary classification, multiclass classification, and regression.\n- Built-in modes: `Explain`, `Perform`, `Compete`, and `Optuna`.\n- Common algorithms include `Baseline`, `Linear`, `Decision Tree`, `Random Forest`, `Extra Trees`, `LightGBM`, `Xgboost`, `CatBoost`, `Neural Network`, and `Nearest Neighbors`.\n- Core workflows are CPU-compatible. GPU hardware is not required for this skill's selected scope.\n- Optional surfaces can need extra system\u002Fruntime setup: Graphviz for some tree visualizations and Mercury plus browser\u002Fnetwork\u002Fauth for local or hosted apps.\n\nRead [`references\u002Fpackage-overview.md`](references\u002Fpackage-overview.md) for install prerequisites, high-level capabilities, optional dependencies, and safe smoke-test strategy. Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for cross-cutting install\u002Fimport\u002Fdependency failures.\n\n## Common operating patterns\n\n- For a quick user-data smoke, use `AutoML(mode=\"Explain\", algorithms=[\"Baseline\", \"Decision Tree\"], explain_level=0, train_ensemble=False, stack_models=False, golden_features=False, features_selection=False, total_time_limit=30)` and a disposable `results_path`.\n- For production-style tabular modeling, start from `mode=\"Perform\"`, set a realistic `total_time_limit`, and keep `results_path` stable for later reports and reload.\n- For competition or maximum-performance work, use `mode=\"Compete\"` or `mode=\"Optuna\"` only after discussing runtime, validation, stacking, and per-algorithm tuning budgets.\n- For saved runs, load the full AutoML results directory with `AutoML(results_path=\"...\")`; do not load learner files directly unless a sub-skill explicitly says why.\n- For fairness, pass sensitive features to `fit(..., sensitive_features=...)` and choose task-compatible fairness metrics.\n- For generated apps, call `automl.app()` to create files first; do not start Mercury or publish without explicit user approval.\n\n## Bundled checks\n\n- [`scripts\u002Fcheck_mljar_supervised_install.py`](scripts\u002Fcheck_mljar_supervised_install.py): import\u002Fversion\u002Fsignature and optional dependency probe.\n- [`sub-skills\u002Ftraining-core\u002Fscripts\u002Fmljar_automl_smoke.py`](sub-skills\u002Ftraining-core\u002Fscripts\u002Fmljar_automl_smoke.py): tiny synthetic training\u002Fprediction smoke.\n- [`sub-skills\u002Fdata-preprocessing\u002Fscripts\u002Finspect_preprocessing_behaviour.py`](sub-skills\u002Fdata-preprocessing\u002Fscripts\u002Finspect_preprocessing_behaviour.py): lightweight preprocessing utility checks.\n- [`sub-skills\u002Fartifacts-reports\u002Fscripts\u002Fstructured_report_smoke.py`](sub-skills\u002Fartifacts-reports\u002Fscripts\u002Fstructured_report_smoke.py): tiny structured-report and reload smoke.\n- [`sub-skills\u002Ffairness-workflows\u002Fscripts\u002Ffairness_smoke.py`](sub-skills\u002Ffairness-workflows\u002Fscripts\u002Ffairness_smoke.py): tiny fairness-aware fit and report signal check.\n- [`sub-skills\u002Fapp-deployment\u002Fscripts\u002Fgenerate_app_workspace_smoke.py`](sub-skills\u002Fapp-deployment\u002Fscripts\u002Fgenerate_app_workspace_smoke.py): tiny app-workspace generation check without serving or publishing.\n\n## Refresh and provenance\n\nRead [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) before deciding whether this skill is current for a checkout. If the package version, commit, public `AutoML` signatures, docs, examples, or test-backed behavior changed, run `refresh-repo-skill` instead of relying on this snapshot.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fmljar-supervised",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 mljar-supervised",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill mljar-supervised",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill mljar-supervised","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmljar-supervised\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fpackage-overview.md","REFERENCE","参考文档",4197,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmljar-supervised\u002Freferences\u002Fpackage-overview.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",2326,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmljar-supervised\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",460,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmljar-supervised\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",4199,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmljar-supervised\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_mljar_supervised_install.py","SCRIPT","脚本",4108,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmljar-supervised\u002Fscripts\u002Fcheck_mljar_supervised_install.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",[],[]]