[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-weights-and-biases-wandb-autoresearch":3,"mdc--65sey6-key":36,"related-org-weights-and-biases-wandb-autoresearch":499,"related-repo-weights-and-biases-wandb-autoresearch":652},{"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-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},"weights-and-biases","Weights & Biases","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fweights-and-biases.png","wandb",[13,17,20,22],{"name":14,"slug":15,"type":16},"Research","research","tag",{"name":18,"slug":19,"type":16},"Benchmarking","benchmarking",{"name":9,"slug":21,"type":16},"weights-biases",{"name":23,"slug":24,"type":16},"Machine Learning","machine-learning",60,"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fskills","2026-08-07T05:03:43.253721",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-autoresearch","---\nname: wandb-autoresearch\ndescription: \"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.\"\n---\n\u003C!--\nSPDX-FileCopyrightText: 2026 CoreWeave, Inc.\nSPDX-License-Identifier: Apache-2.0\nSPDX-PackageName: skills\n-->\n\n# W&B autoresearch\n\nUse W&B Launch to execute real training experiments, read their results, and\nchoose the next bounded trial. Do not create a local `wandb.init()` run as a\nsubstitute for compute that was supposed to run through Launch.\n\nThe Launch implementation lives in `skills\u002Fwandb-primary`:\n\n- `skills\u002Fwandb-primary\u002Fscripts\u002Flaunch_helpers.py`\n- the `Launch` section in `skills\u002Fwandb-primary\u002FSKILL.md`\n\nInstall missing packages explicitly with `uv`; do not assume a fixed working\ndirectory or preinstalled environment.\n\n## Flow\n\nRead only the reference for the current stage:\n\n| Stage | Entry condition | Read |\n|---|---|---|\n| Understand | Always first; inspect launchable code, queue capacity, data location, and prior state | `references\u002Funderstand.md` |\n| Set up | Launchable code or usable queue capacity is missing | `references\u002Fsetup.md` |\n| Search | Launchable code and queue capacity both exist | `references\u002Fsearch.md` |\n\nThe readiness gate is `launchable code + queue with usable capacity`. A dataset\nmay be a versioned Artifact or may be supplied by the code\u002Fimage; its storage\nform alone does not determine readiness.\n\n## Experiment records\n\nUse each W&B object for one job:\n\n- Runs hold trial config, metrics, system metrics, status, and code\u002Fjob lineage.\n- Job or code Artifacts make code relaunchable.\n- Dataset Artifacts provide versioned inputs when the workload needs them.\n- Launch queues and agents provide compute.\n- A small local markdown file holds the hypothesis, trial tally, decisions,\n  queue, and next step.\n\nKeep local state at a user-visible path in the current project or a path the\nuser supplied. Sync it to a W&B Artifact only when cross-session resume is\nuseful and the user authorizes the write:\n\n```bash\nS=skills\u002Fwandb-autoresearch\u002Fscripts\u002Fautoresearch_state.py\nuv run --with wandb python \"$S\" load ENTITY PROJECT --dest .\nuv run --with wandb python \"$S\" save ENTITY PROJECT --path AUTORESEARCH_STATE.md\n```\n\n## Compute safety\n\n- Confirm the queue, metric direction, search axis, and trial\u002Fcompute budget\n  before the first non-smoke launch. Do not exceed the agreed budget.\n- Smoke-test the real job at a deliberately small setting before full trials.\n- Change only config fields the program actually reads. Use a code edit and a\n  new job Artifact for architecture or pipeline changes.\n- Run trials serially unless the user explicitly authorizes parallel compute.\n  Inspect each completed result before selecting the next trial.\n- Report failures, hardware utilization, and uncertainty. Re-run a likely\n  winner with another seed when the apparent gap could be noise.\n- Never fabricate a run, metric, queue result, or completion state.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,50,65,78,111,124,131,136,235,248,254,259,287,292,454,460,493],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"wb-autoresearch",[47],{"type":48,"value":49},"text","W&B autoresearch",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54,56,63],{"type":48,"value":55},"Use W&B Launch to execute real training experiments, read their results, and\nchoose the next bounded trial. Do not create a local ",{"type":42,"tag":57,"props":58,"children":60},"code",{"className":59},[],[61],{"type":48,"value":62},"wandb.init()",{"type":48,"value":64}," run as a\nsubstitute for compute that was supposed to run through Launch.",{"type":42,"tag":51,"props":66,"children":67},{},[68,70,76],{"type":48,"value":69},"The Launch implementation lives in ",{"type":42,"tag":57,"props":71,"children":73},{"className":72},[],[74],{"type":48,"value":75},"skills\u002Fwandb-primary",{"type":48,"value":77},":",{"type":42,"tag":79,"props":80,"children":81},"ul",{},[82,92],{"type":42,"tag":83,"props":84,"children":85},"li",{},[86],{"type":42,"tag":57,"props":87,"children":89},{"className":88},[],[90],{"type":48,"value":91},"skills\u002Fwandb-primary\u002Fscripts\u002Flaunch_helpers.py",{"type":42,"tag":83,"props":93,"children":94},{},[95,97,103,105],{"type":48,"value":96},"the ",{"type":42,"tag":57,"props":98,"children":100},{"className":99},[],[101],{"type":48,"value":102},"Launch",{"type":48,"value":104}," section in ",{"type":42,"tag":57,"props":106,"children":108},{"className":107},[],[109],{"type":48,"value":110},"skills\u002Fwandb-primary\u002FSKILL.md",{"type":42,"tag":51,"props":112,"children":113},{},[114,116,122],{"type":48,"value":115},"Install missing packages explicitly with ",{"type":42,"tag":57,"props":117,"children":119},{"className":118},[],[120],{"type":48,"value":121},"uv",{"type":48,"value":123},"; do not assume a fixed working\ndirectory or preinstalled environment.",{"type":42,"tag":125,"props":126,"children":128},"h2",{"id":127},"flow",[129],{"type":48,"value":130},"Flow",{"type":42,"tag":51,"props":132,"children":133},{},[134],{"type":48,"value":135},"Read only the reference for the current stage:",{"type":42,"tag":137,"props":138,"children":139},"table",{},[140,164],{"type":42,"tag":141,"props":142,"children":143},"thead",{},[144],{"type":42,"tag":145,"props":146,"children":147},"tr",{},[148,154,159],{"type":42,"tag":149,"props":150,"children":151},"th",{},[152],{"type":48,"value":153},"Stage",{"type":42,"tag":149,"props":155,"children":156},{},[157],{"type":48,"value":158},"Entry condition",{"type":42,"tag":149,"props":160,"children":161},{},[162],{"type":48,"value":163},"Read",{"type":42,"tag":165,"props":166,"children":167},"tbody",{},[168,191,213],{"type":42,"tag":145,"props":169,"children":170},{},[171,177,182],{"type":42,"tag":172,"props":173,"children":174},"td",{},[175],{"type":48,"value":176},"Understand",{"type":42,"tag":172,"props":178,"children":179},{},[180],{"type":48,"value":181},"Always first; inspect launchable code, queue capacity, data location, and prior state",{"type":42,"tag":172,"props":183,"children":184},{},[185],{"type":42,"tag":57,"props":186,"children":188},{"className":187},[],[189],{"type":48,"value":190},"references\u002Funderstand.md",{"type":42,"tag":145,"props":192,"children":193},{},[194,199,204],{"type":42,"tag":172,"props":195,"children":196},{},[197],{"type":48,"value":198},"Set up",{"type":42,"tag":172,"props":200,"children":201},{},[202],{"type":48,"value":203},"Launchable code or usable queue capacity is missing",{"type":42,"tag":172,"props":205,"children":206},{},[207],{"type":42,"tag":57,"props":208,"children":210},{"className":209},[],[211],{"type":48,"value":212},"references\u002Fsetup.md",{"type":42,"tag":145,"props":214,"children":215},{},[216,221,226],{"type":42,"tag":172,"props":217,"children":218},{},[219],{"type":48,"value":220},"Search",{"type":42,"tag":172,"props":222,"children":223},{},[224],{"type":48,"value":225},"Launchable code and queue capacity both exist",{"type":42,"tag":172,"props":227,"children":228},{},[229],{"type":42,"tag":57,"props":230,"children":232},{"className":231},[],[233],{"type":48,"value":234},"references\u002Fsearch.md",{"type":42,"tag":51,"props":236,"children":237},{},[238,240,246],{"type":48,"value":239},"The readiness gate is ",{"type":42,"tag":57,"props":241,"children":243},{"className":242},[],[244],{"type":48,"value":245},"launchable code + queue with usable capacity",{"type":48,"value":247},". A dataset\nmay be a versioned Artifact or may be supplied by the code\u002Fimage; its storage\nform alone does not determine readiness.",{"type":42,"tag":125,"props":249,"children":251},{"id":250},"experiment-records",[252],{"type":48,"value":253},"Experiment records",{"type":42,"tag":51,"props":255,"children":256},{},[257],{"type":48,"value":258},"Use each W&B object for one job:",{"type":42,"tag":79,"props":260,"children":261},{},[262,267,272,277,282],{"type":42,"tag":83,"props":263,"children":264},{},[265],{"type":48,"value":266},"Runs hold trial config, metrics, system metrics, status, and code\u002Fjob lineage.",{"type":42,"tag":83,"props":268,"children":269},{},[270],{"type":48,"value":271},"Job or code Artifacts make code relaunchable.",{"type":42,"tag":83,"props":273,"children":274},{},[275],{"type":48,"value":276},"Dataset Artifacts provide versioned inputs when the workload needs them.",{"type":42,"tag":83,"props":278,"children":279},{},[280],{"type":48,"value":281},"Launch queues and agents provide compute.",{"type":42,"tag":83,"props":283,"children":284},{},[285],{"type":48,"value":286},"A small local markdown file holds the hypothesis, trial tally, decisions,\nqueue, and next step.",{"type":42,"tag":51,"props":288,"children":289},{},[290],{"type":48,"value":291},"Keep local state at a user-visible path in the current project or a path the\nuser supplied. Sync it to a W&B Artifact only when cross-session resume is\nuseful and the user authorizes the write:",{"type":42,"tag":293,"props":294,"children":299},"pre",{"className":295,"code":296,"language":297,"meta":298,"style":298},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","S=skills\u002Fwandb-autoresearch\u002Fscripts\u002Fautoresearch_state.py\nuv run --with wandb python \"$S\" load ENTITY PROJECT --dest .\nuv run --with wandb python \"$S\" save ENTITY PROJECT --path AUTORESEARCH_STATE.md\n","bash","",[300],{"type":42,"tag":57,"props":301,"children":302},{"__ignoreMap":298},[303,327,395],{"type":42,"tag":304,"props":305,"children":308},"span",{"class":306,"line":307},"line",1,[309,315,321],{"type":42,"tag":304,"props":310,"children":312},{"style":311},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[313],{"type":48,"value":314},"S",{"type":42,"tag":304,"props":316,"children":318},{"style":317},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[319],{"type":48,"value":320},"=",{"type":42,"tag":304,"props":322,"children":324},{"style":323},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[325],{"type":48,"value":326},"skills\u002Fwandb-autoresearch\u002Fscripts\u002Fautoresearch_state.py\n",{"type":42,"tag":304,"props":328,"children":329},{"class":306,"line":29},[330,335,340,345,350,355,360,365,370,375,380,385,390],{"type":42,"tag":304,"props":331,"children":333},{"style":332},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[334],{"type":48,"value":121},{"type":42,"tag":304,"props":336,"children":337},{"style":323},[338],{"type":48,"value":339}," run",{"type":42,"tag":304,"props":341,"children":342},{"style":323},[343],{"type":48,"value":344}," --with",{"type":42,"tag":304,"props":346,"children":347},{"style":323},[348],{"type":48,"value":349}," wandb",{"type":42,"tag":304,"props":351,"children":352},{"style":323},[353],{"type":48,"value":354}," python",{"type":42,"tag":304,"props":356,"children":357},{"style":317},[358],{"type":48,"value":359}," \"",{"type":42,"tag":304,"props":361,"children":362},{"style":311},[363],{"type":48,"value":364},"$S",{"type":42,"tag":304,"props":366,"children":367},{"style":317},[368],{"type":48,"value":369},"\"",{"type":42,"tag":304,"props":371,"children":372},{"style":323},[373],{"type":48,"value":374}," load",{"type":42,"tag":304,"props":376,"children":377},{"style":323},[378],{"type":48,"value":379}," ENTITY",{"type":42,"tag":304,"props":381,"children":382},{"style":323},[383],{"type":48,"value":384}," PROJECT",{"type":42,"tag":304,"props":386,"children":387},{"style":323},[388],{"type":48,"value":389}," --dest",{"type":42,"tag":304,"props":391,"children":392},{"style":323},[393],{"type":48,"value":394}," .\n",{"type":42,"tag":304,"props":396,"children":398},{"class":306,"line":397},3,[399,403,407,411,415,419,423,427,431,436,440,444,449],{"type":42,"tag":304,"props":400,"children":401},{"style":332},[402],{"type":48,"value":121},{"type":42,"tag":304,"props":404,"children":405},{"style":323},[406],{"type":48,"value":339},{"type":42,"tag":304,"props":408,"children":409},{"style":323},[410],{"type":48,"value":344},{"type":42,"tag":304,"props":412,"children":413},{"style":323},[414],{"type":48,"value":349},{"type":42,"tag":304,"props":416,"children":417},{"style":323},[418],{"type":48,"value":354},{"type":42,"tag":304,"props":420,"children":421},{"style":317},[422],{"type":48,"value":359},{"type":42,"tag":304,"props":424,"children":425},{"style":311},[426],{"type":48,"value":364},{"type":42,"tag":304,"props":428,"children":429},{"style":317},[430],{"type":48,"value":369},{"type":42,"tag":304,"props":432,"children":433},{"style":323},[434],{"type":48,"value":435}," save",{"type":42,"tag":304,"props":437,"children":438},{"style":323},[439],{"type":48,"value":379},{"type":42,"tag":304,"props":441,"children":442},{"style":323},[443],{"type":48,"value":384},{"type":42,"tag":304,"props":445,"children":446},{"style":323},[447],{"type":48,"value":448}," --path",{"type":42,"tag":304,"props":450,"children":451},{"style":323},[452],{"type":48,"value":453}," AUTORESEARCH_STATE.md\n",{"type":42,"tag":125,"props":455,"children":457},{"id":456},"compute-safety",[458],{"type":48,"value":459},"Compute safety",{"type":42,"tag":79,"props":461,"children":462},{},[463,468,473,478,483,488],{"type":42,"tag":83,"props":464,"children":465},{},[466],{"type":48,"value":467},"Confirm the queue, metric direction, search axis, and trial\u002Fcompute budget\nbefore the first non-smoke launch. Do not exceed the agreed budget.",{"type":42,"tag":83,"props":469,"children":470},{},[471],{"type":48,"value":472},"Smoke-test the real job at a deliberately small setting before full trials.",{"type":42,"tag":83,"props":474,"children":475},{},[476],{"type":48,"value":477},"Change only config fields the program actually reads. Use a code edit and a\nnew job Artifact for architecture or pipeline changes.",{"type":42,"tag":83,"props":479,"children":480},{},[481],{"type":48,"value":482},"Run trials serially unless the user explicitly authorizes parallel compute.\nInspect each completed result before selecting the next trial.",{"type":42,"tag":83,"props":484,"children":485},{},[486],{"type":48,"value":487},"Report failures, hardware utilization, and uncertainty. Re-run a likely\nwinner with another seed when the apparent gap could be noise.",{"type":42,"tag":83,"props":489,"children":490},{},[491],{"type":48,"value":492},"Never fabricate a run, metric, queue result, or completion state.",{"type":42,"tag":494,"props":495,"children":496},"style",{},[497],{"type":48,"value":498},"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":500,"total":651},[501,520,527,544,562,576,589,599,613,626,637],{"slug":502,"name":502,"fn":503,"description":504,"org":505,"tags":506,"stars":517,"repoUrl":518,"updatedAt":519},"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},[507,510,513,516],{"name":508,"slug":509,"type":16},"Agents","agents",{"name":511,"slug":512,"type":16},"LLM","llm",{"name":514,"slug":515,"type":16},"Observability","observability",{"name":9,"slug":21,"type":16},1104,"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fweave","2026-07-17T06:07:25.81154",{"slug":4,"name":4,"fn":5,"description":6,"org":521,"tags":522,"stars":25,"repoUrl":26,"updatedAt":27},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[523,524,525,526],{"name":18,"slug":19,"type":16},{"name":23,"slug":24,"type":16},{"name":14,"slug":15,"type":16},{"name":9,"slug":21,"type":16},{"slug":528,"name":528,"fn":529,"description":530,"org":531,"tags":532,"stars":25,"repoUrl":26,"updatedAt":543},"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},[533,536,539,542],{"name":534,"slug":535,"type":16},"Data Analysis","data-analysis",{"name":537,"slug":538,"type":16},"Evals","evals",{"name":540,"slug":541,"type":16},"Visualization","visualization",{"name":9,"slug":21,"type":16},"2026-08-07T05:03:33.740012",{"slug":545,"name":545,"fn":546,"description":547,"org":548,"tags":549,"stars":25,"repoUrl":26,"updatedAt":561},"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},[550,551,552,555,558],{"name":534,"slug":535,"type":16},{"name":537,"slug":538,"type":16},{"name":553,"slug":554,"type":16},"MLOps","mlops",{"name":556,"slug":557,"type":16},"Monitoring","monitoring",{"name":559,"slug":560,"type":16},"Tracing","tracing","2026-08-07T04:39:55.990029",{"slug":563,"name":563,"fn":564,"description":565,"org":566,"tags":567,"stars":573,"repoUrl":574,"updatedAt":575},"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},[568,571,572],{"name":569,"slug":570,"type":16},"Configuration","configuration",{"name":514,"slug":515,"type":16},{"name":9,"slug":21,"type":16},9,"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fweave-claude-code","2026-07-17T06:07:38.107392",{"slug":577,"name":577,"fn":578,"description":579,"org":580,"tags":581,"stars":573,"repoUrl":574,"updatedAt":588},"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},[582,585,586,587],{"name":583,"slug":584,"type":16},"Claude Code","claude-code",{"name":569,"slug":570,"type":16},{"name":514,"slug":515,"type":16},{"name":9,"slug":21,"type":16},"2026-07-17T06:06:35.660384",{"slug":590,"name":590,"fn":591,"description":592,"org":593,"tags":594,"stars":573,"repoUrl":574,"updatedAt":598},"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},[595,596,597],{"name":556,"slug":557,"type":16},{"name":514,"slug":515,"type":16},{"name":9,"slug":21,"type":16},"2026-07-17T06:07:58.961737",{"slug":600,"name":600,"fn":601,"description":602,"org":603,"tags":604,"stars":29,"repoUrl":611,"updatedAt":612},"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},[605,606,607,610],{"name":508,"slug":509,"type":16},{"name":537,"slug":538,"type":16},{"name":608,"slug":609,"type":16},"Prompt Engineering","prompt-engineering",{"name":9,"slug":21,"type":16},"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fdiscovery-forge","2026-07-17T06:06:36.008062",{"slug":614,"name":614,"fn":615,"description":616,"org":617,"tags":618,"stars":29,"repoUrl":611,"updatedAt":625},"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},[619,620,623,624],{"name":534,"slug":535,"type":16},{"name":621,"slug":622,"type":16},"Datasets","datasets",{"name":537,"slug":538,"type":16},{"name":9,"slug":21,"type":16},"2026-07-17T06:07:59.30763",{"slug":627,"name":627,"fn":628,"description":629,"org":630,"tags":631,"stars":29,"repoUrl":611,"updatedAt":636},"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},[632,633,634,635],{"name":508,"slug":509,"type":16},{"name":621,"slug":622,"type":16},{"name":537,"slug":538,"type":16},{"name":9,"slug":21,"type":16},"2026-07-17T06:07:26.501045",{"slug":638,"name":638,"fn":639,"description":640,"org":641,"tags":642,"stars":29,"repoUrl":649,"updatedAt":650},"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},[643,646,647,648],{"name":644,"slug":645,"type":16},"Instrumentation","instrumentation",{"name":514,"slug":515,"type":16},{"name":559,"slug":560,"type":16},{"name":9,"slug":21,"type":16},"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fweave-integration-skills","2026-07-17T06:07:59.666449",11,{"items":653,"total":397},[654,661,668],{"slug":4,"name":4,"fn":5,"description":6,"org":655,"tags":656,"stars":25,"repoUrl":26,"updatedAt":27},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[657,658,659,660],{"name":18,"slug":19,"type":16},{"name":23,"slug":24,"type":16},{"name":14,"slug":15,"type":16},{"name":9,"slug":21,"type":16},{"slug":528,"name":528,"fn":529,"description":530,"org":662,"tags":663,"stars":25,"repoUrl":26,"updatedAt":543},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[664,665,666,667],{"name":534,"slug":535,"type":16},{"name":537,"slug":538,"type":16},{"name":540,"slug":541,"type":16},{"name":9,"slug":21,"type":16},{"slug":545,"name":545,"fn":546,"description":547,"org":669,"tags":670,"stars":25,"repoUrl":26,"updatedAt":561},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[671,672,673,674,675],{"name":534,"slug":535,"type":16},{"name":537,"slug":538,"type":16},{"name":553,"slug":554,"type":16},{"name":556,"slug":557,"type":16},{"name":559,"slug":560,"type":16}]