[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-weights-and-biases-wandb-eval-tables":3,"mdc-l2m4gt-key":36,"related-repo-weights-and-biases-wandb-eval-tables":667,"related-org-weights-and-biases-wandb-eval-tables":711},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":25,"repoUrl":26,"updatedAt":27,"license":28,"forks":29,"topics":30,"repo":31,"sourceUrl":34,"mdContent":35},"wandb-eval-tables","convert W&B artifacts into EvalTable previews","Convert W&B Table artifacts into non-destructive EvalTable previews with scan-first planning, typed input\u002Foutput\u002Fscore columns, bounded batches, verification, and safe removal. Use when a coding agent needs to create, inspect, compare, verify, or remove W&B EvalTable previews.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"weights-and-biases","Weights & Biases","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fweights-and-biases.png","wandb",[13,16,19,22],{"name":9,"slug":14,"type":15},"weights-biases","tag",{"name":17,"slug":18,"type":15},"Evals","evals",{"name":20,"slug":21,"type":15},"Data Analysis","data-analysis",{"name":23,"slug":24,"type":15},"Visualization","visualization",60,"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fskills","2026-08-07T05:03:33.740012",null,2,[],{"repoUrl":26,"stars":25,"forks":29,"topics":32,"description":33},[],"Official Agent Skills for Weights & Biases Models and Weave","https:\u002F\u002Fgithub.com\u002Fwandb\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fwandb-eval-tables","---\nname: wandb-eval-tables\ndescription: \"Convert W&B Table artifacts into non-destructive EvalTable previews with scan-first planning, typed input\u002Foutput\u002Fscore columns, bounded batches, verification, and safe removal. Use when a coding agent needs to create, inspect, compare, verify, or remove W&B EvalTable previews.\"\n---\n\u003C!--\nSPDX-FileCopyrightText: 2026 CoreWeave, Inc.\nSPDX-License-Identifier: Apache-2.0\nSPDX-PackageName: skills\n-->\n\n# W&B EvalTable previews\n\nUse the bundled helper to preview existing `wandb.Table` data as\n`wandb.EvalTable` data. A preview creates new runs and keys; it never overwrites\nthe source runs or tables.\n\nRead `references\u002FEVAL_TABLES.md` before converting. It is the canonical source\nfor EvalTable semantics, source selection, limits, column roles, verification,\nand removal.\n\n## Environment\n\nRun the helper from an environment that provides a W&B SDK with\n`wandb.EvalTable` and Weave. Use `uv` to supply missing dependencies:\n\n```bash\nuv run --with 'wandb[workspaces]>=0.28.1' --with weave \\\n  python skills\u002Fwandb-eval-tables\u002Fscripts\u002Ftable_artifact_to_eval_table.py --help\n```\n\nCredentials and default scope may come from `WANDB_API_KEY`, `WANDB_ENTITY`,\nand `WANDB_PROJECT`; otherwise pass explicit entity\u002Fproject arguments.\nDownloads use the operating system's temporary directory, not a fixed current\nworking directory.\n\n## Required workflow\n\n1. Choose the narrowest source that matches the request: exact artifact, one\n   run, one sweep, or a project\u002Fworkspace. Do not broaden an explicitly named\n   source.\n2. Run `scan`. This is read-only preflight and is not proof of conversion.\n3. Review `eligible_summary_by_table_key`, table shapes, truncations, warnings,\n   and existing-preview metadata. Select one table key unless the user asks for\n   a broader batch.\n4. Classify columns only when confident. Input tuples must uniquely identify\n   rows; score columns must be numeric or boolean; free-text labels and\n   rationales are outputs. Leave ambiguous tables untyped.\n5. Run `preview` for exactly one `--table-key` per invocation. Keep the target\n   in the source project unless the user requests another writable project.\n6. If runs were created, run `verify-preview` on the final created run and the\n   exact logged key. Report success only when it returns `verified: true`.\n7. Report created and skipped sources plus every truncation or failed check.\n\n```bash\nT=skills\u002Fwandb-eval-tables\u002Fscripts\u002Ftable_artifact_to_eval_table.py\n\nuv run python \"$T\" scan \\\n  --source-workspace ENTITY\u002FPROJECT --max-runs 4\n\nuv run python \"$T\" preview \\\n  --source-workspace ENTITY\u002FPROJECT \\\n  --target-project ENTITY\u002FPROJECT \\\n  --max-runs 4 \\\n  --table-key predictions\n\nuv run python \"$T\" verify-preview \\\n  --run ENTITY\u002FPROJECT\u002FPREVIEW_RUN_ID \\\n  --table-key predictions_preview\n```\n\n## Safety\n\n- `scan` and `preview --dry-run` are read-only. `preview` creates W&B runs,\n  EvalTables, and Weave evaluations; run it only when the user requested a\n  conversion.\n- The helper caps tables at 10,000 rows and 100 columns, warns above 1,000\n  rows, and refuses more than 50 eligible table artifacts for one key. Surface\n  every cap; never imply a truncated preview is complete.\n- Do not bypass helper failures with ad-hoc logging. Narrow or correct helper\n  arguments, then retry only when the change is safe.\n- Removal deletes both Weave evaluations and preview runs. Run\n  `delete-preview --dry-run` first, verify every target is helper-created, and\n  obtain confirmation before the irreversible invocation. Never delete source\n  runs.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,50,73,86,93,113,195,224,230,317,603,609,661],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"wb-evaltable-previews",[47],{"type":48,"value":49},"text","W&B EvalTable previews",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54,56,63,65,71],{"type":48,"value":55},"Use the bundled helper to preview existing ",{"type":42,"tag":57,"props":58,"children":60},"code",{"className":59},[],[61],{"type":48,"value":62},"wandb.Table",{"type":48,"value":64}," data as\n",{"type":42,"tag":57,"props":66,"children":68},{"className":67},[],[69],{"type":48,"value":70},"wandb.EvalTable",{"type":48,"value":72}," data. A preview creates new runs and keys; it never overwrites\nthe source runs or tables.",{"type":42,"tag":51,"props":74,"children":75},{},[76,78,84],{"type":48,"value":77},"Read ",{"type":42,"tag":57,"props":79,"children":81},{"className":80},[],[82],{"type":48,"value":83},"references\u002FEVAL_TABLES.md",{"type":48,"value":85}," before converting. It is the canonical source\nfor EvalTable semantics, source selection, limits, column roles, verification,\nand removal.",{"type":42,"tag":87,"props":88,"children":90},"h2",{"id":89},"environment",[91],{"type":48,"value":92},"Environment",{"type":42,"tag":51,"props":94,"children":95},{},[96,98,103,105,111],{"type":48,"value":97},"Run the helper from an environment that provides a W&B SDK with\n",{"type":42,"tag":57,"props":99,"children":101},{"className":100},[],[102],{"type":48,"value":70},{"type":48,"value":104}," and Weave. Use ",{"type":42,"tag":57,"props":106,"children":108},{"className":107},[],[109],{"type":48,"value":110},"uv",{"type":48,"value":112}," to supply missing dependencies:",{"type":42,"tag":114,"props":115,"children":120},"pre",{"className":116,"code":117,"language":118,"meta":119,"style":119},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","uv run --with 'wandb[workspaces]>=0.28.1' --with weave \\\n  python skills\u002Fwandb-eval-tables\u002Fscripts\u002Ftable_artifact_to_eval_table.py --help\n","bash","",[121],{"type":42,"tag":57,"props":122,"children":123},{"__ignoreMap":119},[124,177],{"type":42,"tag":125,"props":126,"children":129},"span",{"class":127,"line":128},"line",1,[130,135,141,146,152,157,162,166,171],{"type":42,"tag":125,"props":131,"children":133},{"style":132},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[134],{"type":48,"value":110},{"type":42,"tag":125,"props":136,"children":138},{"style":137},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[139],{"type":48,"value":140}," run",{"type":42,"tag":125,"props":142,"children":143},{"style":137},[144],{"type":48,"value":145}," --with",{"type":42,"tag":125,"props":147,"children":149},{"style":148},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[150],{"type":48,"value":151}," '",{"type":42,"tag":125,"props":153,"children":154},{"style":137},[155],{"type":48,"value":156},"wandb[workspaces]>=0.28.1",{"type":42,"tag":125,"props":158,"children":159},{"style":148},[160],{"type":48,"value":161},"'",{"type":42,"tag":125,"props":163,"children":164},{"style":137},[165],{"type":48,"value":145},{"type":42,"tag":125,"props":167,"children":168},{"style":137},[169],{"type":48,"value":170}," weave",{"type":42,"tag":125,"props":172,"children":174},{"style":173},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[175],{"type":48,"value":176}," \\\n",{"type":42,"tag":125,"props":178,"children":179},{"class":127,"line":29},[180,185,190],{"type":42,"tag":125,"props":181,"children":182},{"style":137},[183],{"type":48,"value":184},"  python",{"type":42,"tag":125,"props":186,"children":187},{"style":137},[188],{"type":48,"value":189}," skills\u002Fwandb-eval-tables\u002Fscripts\u002Ftable_artifact_to_eval_table.py",{"type":42,"tag":125,"props":191,"children":192},{"style":137},[193],{"type":48,"value":194}," --help\n",{"type":42,"tag":51,"props":196,"children":197},{},[198,200,206,208,214,216,222],{"type":48,"value":199},"Credentials and default scope may come from ",{"type":42,"tag":57,"props":201,"children":203},{"className":202},[],[204],{"type":48,"value":205},"WANDB_API_KEY",{"type":48,"value":207},", ",{"type":42,"tag":57,"props":209,"children":211},{"className":210},[],[212],{"type":48,"value":213},"WANDB_ENTITY",{"type":48,"value":215},",\nand ",{"type":42,"tag":57,"props":217,"children":219},{"className":218},[],[220],{"type":48,"value":221},"WANDB_PROJECT",{"type":48,"value":223},"; otherwise pass explicit entity\u002Fproject arguments.\nDownloads use the operating system's temporary directory, not a fixed current\nworking directory.",{"type":42,"tag":87,"props":225,"children":227},{"id":226},"required-workflow",[228],{"type":48,"value":229},"Required workflow",{"type":42,"tag":231,"props":232,"children":233},"ol",{},[234,240,253,266,271,291,312],{"type":42,"tag":235,"props":236,"children":237},"li",{},[238],{"type":48,"value":239},"Choose the narrowest source that matches the request: exact artifact, one\nrun, one sweep, or a project\u002Fworkspace. Do not broaden an explicitly named\nsource.",{"type":42,"tag":235,"props":241,"children":242},{},[243,245,251],{"type":48,"value":244},"Run ",{"type":42,"tag":57,"props":246,"children":248},{"className":247},[],[249],{"type":48,"value":250},"scan",{"type":48,"value":252},". This is read-only preflight and is not proof of conversion.",{"type":42,"tag":235,"props":254,"children":255},{},[256,258,264],{"type":48,"value":257},"Review ",{"type":42,"tag":57,"props":259,"children":261},{"className":260},[],[262],{"type":48,"value":263},"eligible_summary_by_table_key",{"type":48,"value":265},", table shapes, truncations, warnings,\nand existing-preview metadata. Select one table key unless the user asks for\na broader batch.",{"type":42,"tag":235,"props":267,"children":268},{},[269],{"type":48,"value":270},"Classify columns only when confident. Input tuples must uniquely identify\nrows; score columns must be numeric or boolean; free-text labels and\nrationales are outputs. Leave ambiguous tables untyped.",{"type":42,"tag":235,"props":272,"children":273},{},[274,275,281,283,289],{"type":48,"value":244},{"type":42,"tag":57,"props":276,"children":278},{"className":277},[],[279],{"type":48,"value":280},"preview",{"type":48,"value":282}," for exactly one ",{"type":42,"tag":57,"props":284,"children":286},{"className":285},[],[287],{"type":48,"value":288},"--table-key",{"type":48,"value":290}," per invocation. Keep the target\nin the source project unless the user requests another writable project.",{"type":42,"tag":235,"props":292,"children":293},{},[294,296,302,304,310],{"type":48,"value":295},"If runs were created, run ",{"type":42,"tag":57,"props":297,"children":299},{"className":298},[],[300],{"type":48,"value":301},"verify-preview",{"type":48,"value":303}," on the final created run and the\nexact logged key. Report success only when it returns ",{"type":42,"tag":57,"props":305,"children":307},{"className":306},[],[308],{"type":48,"value":309},"verified: true",{"type":48,"value":311},".",{"type":42,"tag":235,"props":313,"children":314},{},[315],{"type":48,"value":316},"Report created and skipped sources plus every truncation or failed check.",{"type":42,"tag":114,"props":318,"children":320},{"className":116,"code":319,"language":118,"meta":119,"style":119},"T=skills\u002Fwandb-eval-tables\u002Fscripts\u002Ftable_artifact_to_eval_table.py\n\nuv run python \"$T\" scan \\\n  --source-workspace ENTITY\u002FPROJECT --max-runs 4\n\nuv run python \"$T\" preview \\\n  --source-workspace ENTITY\u002FPROJECT \\\n  --target-project ENTITY\u002FPROJECT \\\n  --max-runs 4 \\\n  --table-key predictions\n\nuv run python \"$T\" verify-preview \\\n  --run ENTITY\u002FPROJECT\u002FPREVIEW_RUN_ID \\\n  --table-key predictions_preview\n",[321],{"type":42,"tag":57,"props":322,"children":323},{"__ignoreMap":119},[324,342,351,392,417,425,462,478,495,513,527,535,572,590],{"type":42,"tag":125,"props":325,"children":326},{"class":127,"line":128},[327,332,337],{"type":42,"tag":125,"props":328,"children":329},{"style":173},[330],{"type":48,"value":331},"T",{"type":42,"tag":125,"props":333,"children":334},{"style":148},[335],{"type":48,"value":336},"=",{"type":42,"tag":125,"props":338,"children":339},{"style":137},[340],{"type":48,"value":341},"skills\u002Fwandb-eval-tables\u002Fscripts\u002Ftable_artifact_to_eval_table.py\n",{"type":42,"tag":125,"props":343,"children":344},{"class":127,"line":29},[345],{"type":42,"tag":125,"props":346,"children":348},{"emptyLinePlaceholder":347},true,[349],{"type":48,"value":350},"\n",{"type":42,"tag":125,"props":352,"children":354},{"class":127,"line":353},3,[355,359,363,368,373,378,383,388],{"type":42,"tag":125,"props":356,"children":357},{"style":132},[358],{"type":48,"value":110},{"type":42,"tag":125,"props":360,"children":361},{"style":137},[362],{"type":48,"value":140},{"type":42,"tag":125,"props":364,"children":365},{"style":137},[366],{"type":48,"value":367}," python",{"type":42,"tag":125,"props":369,"children":370},{"style":148},[371],{"type":48,"value":372}," \"",{"type":42,"tag":125,"props":374,"children":375},{"style":173},[376],{"type":48,"value":377},"$T",{"type":42,"tag":125,"props":379,"children":380},{"style":148},[381],{"type":48,"value":382},"\"",{"type":42,"tag":125,"props":384,"children":385},{"style":137},[386],{"type":48,"value":387}," scan",{"type":42,"tag":125,"props":389,"children":390},{"style":173},[391],{"type":48,"value":176},{"type":42,"tag":125,"props":393,"children":395},{"class":127,"line":394},4,[396,401,406,411],{"type":42,"tag":125,"props":397,"children":398},{"style":137},[399],{"type":48,"value":400},"  --source-workspace",{"type":42,"tag":125,"props":402,"children":403},{"style":137},[404],{"type":48,"value":405}," ENTITY\u002FPROJECT",{"type":42,"tag":125,"props":407,"children":408},{"style":137},[409],{"type":48,"value":410}," --max-runs",{"type":42,"tag":125,"props":412,"children":414},{"style":413},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[415],{"type":48,"value":416}," 4\n",{"type":42,"tag":125,"props":418,"children":420},{"class":127,"line":419},5,[421],{"type":42,"tag":125,"props":422,"children":423},{"emptyLinePlaceholder":347},[424],{"type":48,"value":350},{"type":42,"tag":125,"props":426,"children":428},{"class":127,"line":427},6,[429,433,437,441,445,449,453,458],{"type":42,"tag":125,"props":430,"children":431},{"style":132},[432],{"type":48,"value":110},{"type":42,"tag":125,"props":434,"children":435},{"style":137},[436],{"type":48,"value":140},{"type":42,"tag":125,"props":438,"children":439},{"style":137},[440],{"type":48,"value":367},{"type":42,"tag":125,"props":442,"children":443},{"style":148},[444],{"type":48,"value":372},{"type":42,"tag":125,"props":446,"children":447},{"style":173},[448],{"type":48,"value":377},{"type":42,"tag":125,"props":450,"children":451},{"style":148},[452],{"type":48,"value":382},{"type":42,"tag":125,"props":454,"children":455},{"style":137},[456],{"type":48,"value":457}," preview",{"type":42,"tag":125,"props":459,"children":460},{"style":173},[461],{"type":48,"value":176},{"type":42,"tag":125,"props":463,"children":465},{"class":127,"line":464},7,[466,470,474],{"type":42,"tag":125,"props":467,"children":468},{"style":137},[469],{"type":48,"value":400},{"type":42,"tag":125,"props":471,"children":472},{"style":137},[473],{"type":48,"value":405},{"type":42,"tag":125,"props":475,"children":476},{"style":173},[477],{"type":48,"value":176},{"type":42,"tag":125,"props":479,"children":481},{"class":127,"line":480},8,[482,487,491],{"type":42,"tag":125,"props":483,"children":484},{"style":137},[485],{"type":48,"value":486},"  --target-project",{"type":42,"tag":125,"props":488,"children":489},{"style":137},[490],{"type":48,"value":405},{"type":42,"tag":125,"props":492,"children":493},{"style":173},[494],{"type":48,"value":176},{"type":42,"tag":125,"props":496,"children":498},{"class":127,"line":497},9,[499,504,509],{"type":42,"tag":125,"props":500,"children":501},{"style":137},[502],{"type":48,"value":503},"  --max-runs",{"type":42,"tag":125,"props":505,"children":506},{"style":413},[507],{"type":48,"value":508}," 4",{"type":42,"tag":125,"props":510,"children":511},{"style":173},[512],{"type":48,"value":176},{"type":42,"tag":125,"props":514,"children":516},{"class":127,"line":515},10,[517,522],{"type":42,"tag":125,"props":518,"children":519},{"style":137},[520],{"type":48,"value":521},"  --table-key",{"type":42,"tag":125,"props":523,"children":524},{"style":137},[525],{"type":48,"value":526}," predictions\n",{"type":42,"tag":125,"props":528,"children":530},{"class":127,"line":529},11,[531],{"type":42,"tag":125,"props":532,"children":533},{"emptyLinePlaceholder":347},[534],{"type":48,"value":350},{"type":42,"tag":125,"props":536,"children":538},{"class":127,"line":537},12,[539,543,547,551,555,559,563,568],{"type":42,"tag":125,"props":540,"children":541},{"style":132},[542],{"type":48,"value":110},{"type":42,"tag":125,"props":544,"children":545},{"style":137},[546],{"type":48,"value":140},{"type":42,"tag":125,"props":548,"children":549},{"style":137},[550],{"type":48,"value":367},{"type":42,"tag":125,"props":552,"children":553},{"style":148},[554],{"type":48,"value":372},{"type":42,"tag":125,"props":556,"children":557},{"style":173},[558],{"type":48,"value":377},{"type":42,"tag":125,"props":560,"children":561},{"style":148},[562],{"type":48,"value":382},{"type":42,"tag":125,"props":564,"children":565},{"style":137},[566],{"type":48,"value":567}," verify-preview",{"type":42,"tag":125,"props":569,"children":570},{"style":173},[571],{"type":48,"value":176},{"type":42,"tag":125,"props":573,"children":575},{"class":127,"line":574},13,[576,581,586],{"type":42,"tag":125,"props":577,"children":578},{"style":137},[579],{"type":48,"value":580},"  --run",{"type":42,"tag":125,"props":582,"children":583},{"style":137},[584],{"type":48,"value":585}," ENTITY\u002FPROJECT\u002FPREVIEW_RUN_ID",{"type":42,"tag":125,"props":587,"children":588},{"style":173},[589],{"type":48,"value":176},{"type":42,"tag":125,"props":591,"children":593},{"class":127,"line":592},14,[594,598],{"type":42,"tag":125,"props":595,"children":596},{"style":137},[597],{"type":48,"value":521},{"type":42,"tag":125,"props":599,"children":600},{"style":137},[601],{"type":48,"value":602}," predictions_preview\n",{"type":42,"tag":87,"props":604,"children":606},{"id":605},"safety",[607],{"type":48,"value":608},"Safety",{"type":42,"tag":610,"props":611,"children":612},"ul",{},[613,638,643,648],{"type":42,"tag":235,"props":614,"children":615},{},[616,621,623,629,631,636],{"type":42,"tag":57,"props":617,"children":619},{"className":618},[],[620],{"type":48,"value":250},{"type":48,"value":622}," and ",{"type":42,"tag":57,"props":624,"children":626},{"className":625},[],[627],{"type":48,"value":628},"preview --dry-run",{"type":48,"value":630}," are read-only. ",{"type":42,"tag":57,"props":632,"children":634},{"className":633},[],[635],{"type":48,"value":280},{"type":48,"value":637}," creates W&B runs,\nEvalTables, and Weave evaluations; run it only when the user requested a\nconversion.",{"type":42,"tag":235,"props":639,"children":640},{},[641],{"type":48,"value":642},"The helper caps tables at 10,000 rows and 100 columns, warns above 1,000\nrows, and refuses more than 50 eligible table artifacts for one key. Surface\nevery cap; never imply a truncated preview is complete.",{"type":42,"tag":235,"props":644,"children":645},{},[646],{"type":48,"value":647},"Do not bypass helper failures with ad-hoc logging. Narrow or correct helper\narguments, then retry only when the change is safe.",{"type":42,"tag":235,"props":649,"children":650},{},[651,653,659],{"type":48,"value":652},"Removal deletes both Weave evaluations and preview runs. Run\n",{"type":42,"tag":57,"props":654,"children":656},{"className":655},[],[657],{"type":48,"value":658},"delete-preview --dry-run",{"type":48,"value":660}," first, verify every target is helper-created, and\nobtain confirmation before the irreversible invocation. Never delete source\nruns.",{"type":42,"tag":662,"props":663,"children":664},"style",{},[665],{"type":48,"value":666},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":668,"total":353},[669,686,693],{"slug":670,"name":670,"fn":671,"description":672,"org":673,"tags":674,"stars":25,"repoUrl":26,"updatedAt":685},"wandb-autoresearch","execute evidence-driven training research with W&B","Run bounded, evidence-driven training research through W&B Launch: assess project readiness, establish launchable code and queue capacity, smoke-test real jobs, execute serial trials, compare metrics, and persist resumable research state. Use when a coding agent is asked to autonomously test training hypotheses or tune a real W&B-tracked workload.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[675,678,681,684],{"name":676,"slug":677,"type":15},"Benchmarking","benchmarking",{"name":679,"slug":680,"type":15},"Machine Learning","machine-learning",{"name":682,"slug":683,"type":15},"Research","research",{"name":9,"slug":14,"type":15},"2026-08-07T05:03:43.253721",{"slug":4,"name":4,"fn":5,"description":6,"org":687,"tags":688,"stars":25,"repoUrl":26,"updatedAt":27},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[689,690,691,692],{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},{"name":9,"slug":14,"type":15},{"slug":694,"name":694,"fn":695,"description":696,"org":697,"tags":698,"stars":25,"repoUrl":26,"updatedAt":710},"wandb-primary","manage Weights & Biases projects and runs","Primary W&B skill for broad or mixed Weights & Biases work: project overviews, W&B runs and artifacts, Weave traces and evaluations, Reports, and Launch workflows. Use when the task spans multiple W&B surfaces or the user asks generally what is happening in a W&B project.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[699,700,701,704,707],{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"name":702,"slug":703,"type":15},"MLOps","mlops",{"name":705,"slug":706,"type":15},"Monitoring","monitoring",{"name":708,"slug":709,"type":15},"Tracing","tracing","2026-08-07T04:39:55.990029",{"items":712,"total":529},[713,732,739,746,754,767,780,790,804,817,828],{"slug":714,"name":714,"fn":715,"description":716,"org":717,"tags":718,"stars":729,"repoUrl":730,"updatedAt":731},"weave-instrument","instrument LLM codebases with Weave","Add Weave (Weights & Biases) observability to an LLM or agent codebase. This covers calling `weave.init()`, setting up authentication, and choosing between OTEL auto-instrumentation and the explicit Session SDK agent-logging APIs (Turn, LLM, Tool, SubAgent), based on the libraries the code already uses. Works for Python and TypeScript\u002FNode. Use this whenever the user wants to instrument, trace, or add observability, logging, or monitoring to an agent, chatbot, RAG pipeline, or LLM app. This includes phrasings like \"log my agent to weave\", \"add agent tracing\", \"get my agent into the Weave Agents tab\", \"instrument this with the weave session sdk\", \"trace my tool calls\", or \"set up weave logging\", even when the user does not name a specific API.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[719,722,725,728],{"name":720,"slug":721,"type":15},"Agents","agents",{"name":723,"slug":724,"type":15},"LLM","llm",{"name":726,"slug":727,"type":15},"Observability","observability",{"name":9,"slug":14,"type":15},1104,"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fweave","2026-07-17T06:07:25.81154",{"slug":670,"name":670,"fn":671,"description":672,"org":733,"tags":734,"stars":25,"repoUrl":26,"updatedAt":685},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[735,736,737,738],{"name":676,"slug":677,"type":15},{"name":679,"slug":680,"type":15},{"name":682,"slug":683,"type":15},{"name":9,"slug":14,"type":15},{"slug":4,"name":4,"fn":5,"description":6,"org":740,"tags":741,"stars":25,"repoUrl":26,"updatedAt":27},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[742,743,744,745],{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},{"name":9,"slug":14,"type":15},{"slug":694,"name":694,"fn":695,"description":696,"org":747,"tags":748,"stars":25,"repoUrl":26,"updatedAt":710},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[749,750,751,752,753],{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"name":702,"slug":703,"type":15},{"name":705,"slug":706,"type":15},{"name":708,"slug":709,"type":15},{"slug":755,"name":755,"fn":756,"description":757,"org":758,"tags":759,"stars":497,"repoUrl":765,"updatedAt":766},"weave-config","configure Weave project and settings","This skill should be used when the user wants to \"configure weave\", \"set weave project\", \"change weave project\", \"set wandb api key\", \"update weave settings\", \"show weave config\", \"change weave configuration\", \"restart the weave daemon\", \"apply weave config changes\", \"restart weave to pick up changes\", or needs to read or update any Weave Claude Code plugin settings.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[760,763,764],{"name":761,"slug":762,"type":15},"Configuration","configuration",{"name":726,"slug":727,"type":15},{"name":9,"slug":14,"type":15},"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fweave-claude-code","2026-07-17T06:07:38.107392",{"slug":768,"name":768,"fn":769,"description":770,"org":771,"tags":772,"stars":497,"repoUrl":765,"updatedAt":779},"weave-install","install and configure Weave observability","This skill should be used when the user wants to \"install the weave plugin\", \"set up weave\", \"install weave-claude-code\", \"configure weave for the first time\", \"get started with weave tracing\", or needs to complete the initial setup of the Weave Claude Code plugin including dependency installation and project configuration.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[773,776,777,778],{"name":774,"slug":775,"type":15},"Claude Code","claude-code",{"name":761,"slug":762,"type":15},{"name":726,"slug":727,"type":15},{"name":9,"slug":14,"type":15},"2026-07-17T06:06:35.660384",{"slug":781,"name":781,"fn":782,"description":783,"org":784,"tags":785,"stars":497,"repoUrl":765,"updatedAt":789},"weave-status","verify Weave plugin status and health","This skill should be used when the user wants to \"check weave status\", \"verify the weave plugin is running\", \"see if weave is set up correctly\", \"check weave configuration\", \"is weave working\", \"weave is running an older config\", \"the daemon is on an old config\", or needs to diagnose why Claude Code sessions are not appearing in Weave.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[786,787,788],{"name":705,"slug":706,"type":15},{"name":726,"slug":727,"type":15},{"name":9,"slug":14,"type":15},"2026-07-17T06:07:58.961737",{"slug":791,"name":791,"fn":792,"description":793,"org":794,"tags":795,"stars":29,"repoUrl":802,"updatedAt":803},"annotation-improvement","improve prompts using Weave research traces","Guides coding agents through Discovery Forge prompt improvement after selecting the `wandb-primary` skill. Use `wandb-primary` to fetch W&B Weave research_run traces, human annotations, runnable feedback, and evaluations, then use this workflow when improving researcher.md from annotation queues, reviewed research traces, or human feedback.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[796,797,798,801],{"name":720,"slug":721,"type":15},{"name":17,"slug":18,"type":15},{"name":799,"slug":800,"type":15},"Prompt Engineering","prompt-engineering",{"name":9,"slug":14,"type":15},"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fdiscovery-forge","2026-07-17T06:06:36.008062",{"slug":805,"name":805,"fn":806,"description":807,"org":808,"tags":809,"stars":29,"repoUrl":802,"updatedAt":816},"build-verdict-dataset","build verdict datasets from Weave annotations","Guides coding agents through building the verdict_quality_dataset from W&B Weave research_annotation evidence — querying annotated research_run calls, mapping human QualitySelector verdicts to gold labels, refining row inputs per the rubric, and publishing a new versioned Weave Dataset. Use when the user asks to (re)generate the verdict dataset from annotations, seed a new eval dataset version, or rebuild verdict_quality_dataset.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[810,811,814,815],{"name":20,"slug":21,"type":15},{"name":812,"slug":813,"type":15},"Datasets","datasets",{"name":17,"slug":18,"type":15},{"name":9,"slug":14,"type":15},"2026-07-17T06:07:59.30763",{"slug":818,"name":818,"fn":819,"description":820,"org":821,"tags":822,"stars":29,"repoUrl":802,"updatedAt":827},"offline-eval-improvement","improve prompts using offline evaluation baselines","Guides coding agents through Discovery Forge prompt improvement from a specified Weave offline evaluation baseline. Use `wandb-primary` to fetch evaluation results, failed eval rows, dataset refs, prompt refs, and scorer evidence, then use this workflow when improving researcher.md from failed evaluation rows, comparing eval runs, or iterating on a fixed dataset.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[823,824,825,826],{"name":720,"slug":721,"type":15},{"name":812,"slug":813,"type":15},{"name":17,"slug":18,"type":15},{"name":9,"slug":14,"type":15},"2026-07-17T06:07:26.501045",{"slug":829,"name":829,"fn":830,"description":831,"org":832,"tags":833,"stars":29,"repoUrl":840,"updatedAt":841},"weave-integration","integrate Weave into applications","Comprehensive skill for adding W&B Weave to existing applications. Covers trace-first instrumentation, evaluation only after trace verification, documentation-first implementation, CLI-based Weave data access, and validation workflows. Activate this skill only when the user explicitly mentions the skill by name, such as `weave-integration`, `@skills weave-integration`, or another direct skill reference. Do not auto-trigger from generic Weave or W&B questions.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[834,837,838,839],{"name":835,"slug":836,"type":15},"Instrumentation","instrumentation",{"name":726,"slug":727,"type":15},{"name":708,"slug":709,"type":15},{"name":9,"slug":14,"type":15},"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fweave-integration-skills","2026-07-17T06:07:59.666449"]