[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-weights-and-biases-weave-config":3,"mdc--84r8u3-key":33,"related-org-weights-and-biases-weave-config":576,"related-repo-weights-and-biases-weave-config":700},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":31,"mdContent":32},"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},"weights-and-biases","Weights & Biases","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fweights-and-biases.png","wandb",[13,17,20],{"name":14,"slug":15,"type":16},"Observability","observability","tag",{"name":18,"slug":19,"type":16},"Configuration","configuration",{"name":9,"slug":21,"type":16},"weights-biases",9,"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fweave-claude-code","2026-07-17T06:07:38.107392",null,0,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"Claude Code plugin that traces sessions, tool calls, and subagents to W&B Weave for observability and debugging.","https:\u002F\u002Fgithub.com\u002Fwandb\u002Fweave-claude-code\u002Ftree\u002FHEAD\u002Fskills\u002Fweave-config","---\nname: weave-config\ndescription: 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.\n---\n\n# Weave Claude Code Plugin — Config\n\nRead and update configuration for the Weave Claude Code plugin.\n\n## Determine Intent\n\nIf the user invoked this skill with arguments (e.g., `\u002Fweave:weave-config set weave_project entity\u002Fproject`), execute the corresponding command directly. Otherwise, show the current configuration first and then ask what they want to change.\n\n## Show Current Config\n\nRun:\n```bash\nweave-claude-code config show\n```\n\nThis displays all settings and their sources (settings file vs environment variable).\n\n## Set a Value\n\nTo update a setting:\n```bash\nweave-claude-code config set KEY VALUE\n```\n\nWritable keys:\n\n| Key | Format | Example |\n|-----|--------|---------|\n| `weave_project` | `entity\u002Fproject` | `my-org\u002Fmy-project` |\n| `wandb_api_key` | string | `abc123...` |\n| `agent_name` | string | `my-team-bot` |\n| `debug` | `true` \u002F `false` | `true` |\n| `daemon_socket` | file path | `~\u002F.weave-claude-code\u002Fdaemon.sock` |\n\n**Validation notes:**\n- `weave_project` must contain a `\u002F` (entity\u002Fproject format). Find your entity name at https:\u002F\u002Fwandb.ai.\n- `wandb_api_key` is available at https:\u002F\u002Fwandb.ai\u002Fauthorize.\n- `agent_name` is the name shown for the top-level agent in Weave's Agents view. It must not be empty; surrounding whitespace is trimmed. Defaults to `claude-code` when unset.\n- Environment variables `WEAVE_PROJECT`, `WANDB_API_KEY`, and `WEAVE_AGENT_NAME` take precedence over settings file values when set.\n\n## Get a Single Value\n\nTo read one setting:\n```bash\nweave-claude-code config get KEY\n```\n\n## After Changes\n\nAfter setting `weave_project`, `wandb_api_key`, or `agent_name`, run `weave-claude-code config show` to confirm the new value.\n\nThe daemon reads these once at startup and persists across Claude Code sessions, so a change is **not** picked up by a daemon that is already running. Apply it with:\n\n```bash\nweave-claude-code restart\n```\n\nThis stops the running daemon and starts a fresh one. (If none is running, the next Claude Code session starts one with the updated config.)\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,47,53,60,74,80,85,119,124,130,135,168,173,350,359,456,462,467,495,501,534,546,565,570],{"type":39,"tag":40,"props":41,"children":43},"element","h1",{"id":42},"weave-claude-code-plugin-config",[44],{"type":45,"value":46},"text","Weave Claude Code Plugin — Config",{"type":39,"tag":48,"props":49,"children":50},"p",{},[51],{"type":45,"value":52},"Read and update configuration for the Weave Claude Code plugin.",{"type":39,"tag":54,"props":55,"children":57},"h2",{"id":56},"determine-intent",[58],{"type":45,"value":59},"Determine Intent",{"type":39,"tag":48,"props":61,"children":62},{},[63,65,72],{"type":45,"value":64},"If the user invoked this skill with arguments (e.g., ",{"type":39,"tag":66,"props":67,"children":69},"code",{"className":68},[],[70],{"type":45,"value":71},"\u002Fweave:weave-config set weave_project entity\u002Fproject",{"type":45,"value":73},"), execute the corresponding command directly. Otherwise, show the current configuration first and then ask what they want to change.",{"type":39,"tag":54,"props":75,"children":77},{"id":76},"show-current-config",[78],{"type":45,"value":79},"Show Current Config",{"type":39,"tag":48,"props":81,"children":82},{},[83],{"type":45,"value":84},"Run:",{"type":39,"tag":86,"props":87,"children":92},"pre",{"className":88,"code":89,"language":90,"meta":91,"style":91},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","weave-claude-code config show\n","bash","",[93],{"type":39,"tag":66,"props":94,"children":95},{"__ignoreMap":91},[96],{"type":39,"tag":97,"props":98,"children":101},"span",{"class":99,"line":100},"line",1,[102,108,114],{"type":39,"tag":97,"props":103,"children":105},{"style":104},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[106],{"type":45,"value":107},"weave-claude-code",{"type":39,"tag":97,"props":109,"children":111},{"style":110},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[112],{"type":45,"value":113}," config",{"type":39,"tag":97,"props":115,"children":116},{"style":110},[117],{"type":45,"value":118}," show\n",{"type":39,"tag":48,"props":120,"children":121},{},[122],{"type":45,"value":123},"This displays all settings and their sources (settings file vs environment variable).",{"type":39,"tag":54,"props":125,"children":127},{"id":126},"set-a-value",[128],{"type":45,"value":129},"Set a Value",{"type":39,"tag":48,"props":131,"children":132},{},[133],{"type":45,"value":134},"To update a setting:",{"type":39,"tag":86,"props":136,"children":138},{"className":88,"code":137,"language":90,"meta":91,"style":91},"weave-claude-code config set KEY VALUE\n",[139],{"type":39,"tag":66,"props":140,"children":141},{"__ignoreMap":91},[142],{"type":39,"tag":97,"props":143,"children":144},{"class":99,"line":100},[145,149,153,158,163],{"type":39,"tag":97,"props":146,"children":147},{"style":104},[148],{"type":45,"value":107},{"type":39,"tag":97,"props":150,"children":151},{"style":110},[152],{"type":45,"value":113},{"type":39,"tag":97,"props":154,"children":155},{"style":110},[156],{"type":45,"value":157}," set",{"type":39,"tag":97,"props":159,"children":160},{"style":110},[161],{"type":45,"value":162}," KEY",{"type":39,"tag":97,"props":164,"children":165},{"style":110},[166],{"type":45,"value":167}," VALUE\n",{"type":39,"tag":48,"props":169,"children":170},{},[171],{"type":45,"value":172},"Writable keys:",{"type":39,"tag":174,"props":175,"children":176},"table",{},[177,201],{"type":39,"tag":178,"props":179,"children":180},"thead",{},[181],{"type":39,"tag":182,"props":183,"children":184},"tr",{},[185,191,196],{"type":39,"tag":186,"props":187,"children":188},"th",{},[189],{"type":45,"value":190},"Key",{"type":39,"tag":186,"props":192,"children":193},{},[194],{"type":45,"value":195},"Format",{"type":39,"tag":186,"props":197,"children":198},{},[199],{"type":45,"value":200},"Example",{"type":39,"tag":202,"props":203,"children":204},"tbody",{},[205,236,262,287,324],{"type":39,"tag":182,"props":206,"children":207},{},[208,218,227],{"type":39,"tag":209,"props":210,"children":211},"td",{},[212],{"type":39,"tag":66,"props":213,"children":215},{"className":214},[],[216],{"type":45,"value":217},"weave_project",{"type":39,"tag":209,"props":219,"children":220},{},[221],{"type":39,"tag":66,"props":222,"children":224},{"className":223},[],[225],{"type":45,"value":226},"entity\u002Fproject",{"type":39,"tag":209,"props":228,"children":229},{},[230],{"type":39,"tag":66,"props":231,"children":233},{"className":232},[],[234],{"type":45,"value":235},"my-org\u002Fmy-project",{"type":39,"tag":182,"props":237,"children":238},{},[239,248,253],{"type":39,"tag":209,"props":240,"children":241},{},[242],{"type":39,"tag":66,"props":243,"children":245},{"className":244},[],[246],{"type":45,"value":247},"wandb_api_key",{"type":39,"tag":209,"props":249,"children":250},{},[251],{"type":45,"value":252},"string",{"type":39,"tag":209,"props":254,"children":255},{},[256],{"type":39,"tag":66,"props":257,"children":259},{"className":258},[],[260],{"type":45,"value":261},"abc123...",{"type":39,"tag":182,"props":263,"children":264},{},[265,274,278],{"type":39,"tag":209,"props":266,"children":267},{},[268],{"type":39,"tag":66,"props":269,"children":271},{"className":270},[],[272],{"type":45,"value":273},"agent_name",{"type":39,"tag":209,"props":275,"children":276},{},[277],{"type":45,"value":252},{"type":39,"tag":209,"props":279,"children":280},{},[281],{"type":39,"tag":66,"props":282,"children":284},{"className":283},[],[285],{"type":45,"value":286},"my-team-bot",{"type":39,"tag":182,"props":288,"children":289},{},[290,299,316],{"type":39,"tag":209,"props":291,"children":292},{},[293],{"type":39,"tag":66,"props":294,"children":296},{"className":295},[],[297],{"type":45,"value":298},"debug",{"type":39,"tag":209,"props":300,"children":301},{},[302,308,310],{"type":39,"tag":66,"props":303,"children":305},{"className":304},[],[306],{"type":45,"value":307},"true",{"type":45,"value":309}," \u002F ",{"type":39,"tag":66,"props":311,"children":313},{"className":312},[],[314],{"type":45,"value":315},"false",{"type":39,"tag":209,"props":317,"children":318},{},[319],{"type":39,"tag":66,"props":320,"children":322},{"className":321},[],[323],{"type":45,"value":307},{"type":39,"tag":182,"props":325,"children":326},{},[327,336,341],{"type":39,"tag":209,"props":328,"children":329},{},[330],{"type":39,"tag":66,"props":331,"children":333},{"className":332},[],[334],{"type":45,"value":335},"daemon_socket",{"type":39,"tag":209,"props":337,"children":338},{},[339],{"type":45,"value":340},"file path",{"type":39,"tag":209,"props":342,"children":343},{},[344],{"type":39,"tag":66,"props":345,"children":347},{"className":346},[],[348],{"type":45,"value":349},"~\u002F.weave-claude-code\u002Fdaemon.sock",{"type":39,"tag":48,"props":351,"children":352},{},[353],{"type":39,"tag":354,"props":355,"children":356},"strong",{},[357],{"type":45,"value":358},"Validation notes:",{"type":39,"tag":360,"props":361,"children":362},"ul",{},[363,392,409,427],{"type":39,"tag":364,"props":365,"children":366},"li",{},[367,372,374,380,382,390],{"type":39,"tag":66,"props":368,"children":370},{"className":369},[],[371],{"type":45,"value":217},{"type":45,"value":373}," must contain a ",{"type":39,"tag":66,"props":375,"children":377},{"className":376},[],[378],{"type":45,"value":379},"\u002F",{"type":45,"value":381}," (entity\u002Fproject format). Find your entity name at ",{"type":39,"tag":383,"props":384,"children":388},"a",{"href":385,"rel":386},"https:\u002F\u002Fwandb.ai",[387],"nofollow",[389],{"type":45,"value":385},{"type":45,"value":391},".",{"type":39,"tag":364,"props":393,"children":394},{},[395,400,402,408],{"type":39,"tag":66,"props":396,"children":398},{"className":397},[],[399],{"type":45,"value":247},{"type":45,"value":401}," is available at ",{"type":39,"tag":383,"props":403,"children":406},{"href":404,"rel":405},"https:\u002F\u002Fwandb.ai\u002Fauthorize",[387],[407],{"type":45,"value":404},{"type":45,"value":391},{"type":39,"tag":364,"props":410,"children":411},{},[412,417,419,425],{"type":39,"tag":66,"props":413,"children":415},{"className":414},[],[416],{"type":45,"value":273},{"type":45,"value":418}," is the name shown for the top-level agent in Weave's Agents view. It must not be empty; surrounding whitespace is trimmed. Defaults to ",{"type":39,"tag":66,"props":420,"children":422},{"className":421},[],[423],{"type":45,"value":424},"claude-code",{"type":45,"value":426}," when unset.",{"type":39,"tag":364,"props":428,"children":429},{},[430,432,438,440,446,448,454],{"type":45,"value":431},"Environment variables ",{"type":39,"tag":66,"props":433,"children":435},{"className":434},[],[436],{"type":45,"value":437},"WEAVE_PROJECT",{"type":45,"value":439},", ",{"type":39,"tag":66,"props":441,"children":443},{"className":442},[],[444],{"type":45,"value":445},"WANDB_API_KEY",{"type":45,"value":447},", and ",{"type":39,"tag":66,"props":449,"children":451},{"className":450},[],[452],{"type":45,"value":453},"WEAVE_AGENT_NAME",{"type":45,"value":455}," take precedence over settings file values when set.",{"type":39,"tag":54,"props":457,"children":459},{"id":458},"get-a-single-value",[460],{"type":45,"value":461},"Get a Single Value",{"type":39,"tag":48,"props":463,"children":464},{},[465],{"type":45,"value":466},"To read one setting:",{"type":39,"tag":86,"props":468,"children":470},{"className":88,"code":469,"language":90,"meta":91,"style":91},"weave-claude-code config get KEY\n",[471],{"type":39,"tag":66,"props":472,"children":473},{"__ignoreMap":91},[474],{"type":39,"tag":97,"props":475,"children":476},{"class":99,"line":100},[477,481,485,490],{"type":39,"tag":97,"props":478,"children":479},{"style":104},[480],{"type":45,"value":107},{"type":39,"tag":97,"props":482,"children":483},{"style":110},[484],{"type":45,"value":113},{"type":39,"tag":97,"props":486,"children":487},{"style":110},[488],{"type":45,"value":489}," get",{"type":39,"tag":97,"props":491,"children":492},{"style":110},[493],{"type":45,"value":494}," KEY\n",{"type":39,"tag":54,"props":496,"children":498},{"id":497},"after-changes",[499],{"type":45,"value":500},"After Changes",{"type":39,"tag":48,"props":502,"children":503},{},[504,506,511,512,517,519,524,526,532],{"type":45,"value":505},"After setting ",{"type":39,"tag":66,"props":507,"children":509},{"className":508},[],[510],{"type":45,"value":217},{"type":45,"value":439},{"type":39,"tag":66,"props":513,"children":515},{"className":514},[],[516],{"type":45,"value":247},{"type":45,"value":518},", or ",{"type":39,"tag":66,"props":520,"children":522},{"className":521},[],[523],{"type":45,"value":273},{"type":45,"value":525},", run ",{"type":39,"tag":66,"props":527,"children":529},{"className":528},[],[530],{"type":45,"value":531},"weave-claude-code config show",{"type":45,"value":533}," to confirm the new value.",{"type":39,"tag":48,"props":535,"children":536},{},[537,539,544],{"type":45,"value":538},"The daemon reads these once at startup and persists across Claude Code sessions, so a change is ",{"type":39,"tag":354,"props":540,"children":541},{},[542],{"type":45,"value":543},"not",{"type":45,"value":545}," picked up by a daemon that is already running. Apply it with:",{"type":39,"tag":86,"props":547,"children":549},{"className":88,"code":548,"language":90,"meta":91,"style":91},"weave-claude-code restart\n",[550],{"type":39,"tag":66,"props":551,"children":552},{"__ignoreMap":91},[553],{"type":39,"tag":97,"props":554,"children":555},{"class":99,"line":100},[556,560],{"type":39,"tag":97,"props":557,"children":558},{"style":104},[559],{"type":45,"value":107},{"type":39,"tag":97,"props":561,"children":562},{"style":110},[563],{"type":45,"value":564}," restart\n",{"type":39,"tag":48,"props":566,"children":567},{},[568],{"type":45,"value":569},"This stops the running daemon and starts a fresh one. (If none is running, the next Claude Code session starts one with the updated config.)",{"type":39,"tag":571,"props":572,"children":573},"style",{},[574],{"type":45,"value":575},"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":577,"total":22},[578,595,619,625,637,647,662,675,686],{"slug":579,"name":579,"fn":580,"description":581,"org":582,"tags":583,"stars":592,"repoUrl":593,"updatedAt":594},"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},[584,587,590,591],{"name":585,"slug":586,"type":16},"Agents","agents",{"name":588,"slug":589,"type":16},"LLM","llm",{"name":14,"slug":15,"type":16},{"name":9,"slug":21,"type":16},1104,"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fweave","2026-07-17T06:07:25.81154",{"slug":596,"name":596,"fn":597,"description":598,"org":599,"tags":600,"stars":616,"repoUrl":617,"updatedAt":618},"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},[601,604,607,610,613],{"name":602,"slug":603,"type":16},"Data Analysis","data-analysis",{"name":605,"slug":606,"type":16},"Evals","evals",{"name":608,"slug":609,"type":16},"MLOps","mlops",{"name":611,"slug":612,"type":16},"Monitoring","monitoring",{"name":614,"slug":615,"type":16},"Tracing","tracing",60,"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fskills","2026-07-17T06:06:35.194929",{"slug":4,"name":4,"fn":5,"description":6,"org":620,"tags":621,"stars":22,"repoUrl":23,"updatedAt":24},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[622,623,624],{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":9,"slug":21,"type":16},{"slug":626,"name":626,"fn":627,"description":628,"org":629,"tags":630,"stars":22,"repoUrl":23,"updatedAt":636},"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},[631,633,634,635],{"name":632,"slug":424,"type":16},"Claude Code",{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":9,"slug":21,"type":16},"2026-07-17T06:06:35.660384",{"slug":638,"name":638,"fn":639,"description":640,"org":641,"tags":642,"stars":22,"repoUrl":23,"updatedAt":646},"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},[643,644,645],{"name":611,"slug":612,"type":16},{"name":14,"slug":15,"type":16},{"name":9,"slug":21,"type":16},"2026-07-17T06:07:58.961737",{"slug":648,"name":648,"fn":649,"description":650,"org":651,"tags":652,"stars":659,"repoUrl":660,"updatedAt":661},"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},[653,654,655,658],{"name":585,"slug":586,"type":16},{"name":605,"slug":606,"type":16},{"name":656,"slug":657,"type":16},"Prompt Engineering","prompt-engineering",{"name":9,"slug":21,"type":16},2,"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fdiscovery-forge","2026-07-17T06:06:36.008062",{"slug":663,"name":663,"fn":664,"description":665,"org":666,"tags":667,"stars":659,"repoUrl":660,"updatedAt":674},"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},[668,669,672,673],{"name":602,"slug":603,"type":16},{"name":670,"slug":671,"type":16},"Datasets","datasets",{"name":605,"slug":606,"type":16},{"name":9,"slug":21,"type":16},"2026-07-17T06:07:59.30763",{"slug":676,"name":676,"fn":677,"description":678,"org":679,"tags":680,"stars":659,"repoUrl":660,"updatedAt":685},"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},[681,682,683,684],{"name":585,"slug":586,"type":16},{"name":670,"slug":671,"type":16},{"name":605,"slug":606,"type":16},{"name":9,"slug":21,"type":16},"2026-07-17T06:07:26.501045",{"slug":687,"name":687,"fn":688,"description":689,"org":690,"tags":691,"stars":659,"repoUrl":698,"updatedAt":699},"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},[692,695,696,697],{"name":693,"slug":694,"type":16},"Instrumentation","instrumentation",{"name":14,"slug":15,"type":16},{"name":614,"slug":615,"type":16},{"name":9,"slug":21,"type":16},"https:\u002F\u002Fgithub.com\u002Fwandb\u002Fweave-integration-skills","2026-07-17T06:07:59.666449",{"items":701,"total":721},[702,708,715],{"slug":4,"name":4,"fn":5,"description":6,"org":703,"tags":704,"stars":22,"repoUrl":23,"updatedAt":24},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[705,706,707],{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":9,"slug":21,"type":16},{"slug":626,"name":626,"fn":627,"description":628,"org":709,"tags":710,"stars":22,"repoUrl":23,"updatedAt":636},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[711,712,713,714],{"name":632,"slug":424,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":9,"slug":21,"type":16},{"slug":638,"name":638,"fn":639,"description":640,"org":716,"tags":717,"stars":22,"repoUrl":23,"updatedAt":646},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[718,719,720],{"name":611,"slug":612,"type":16},{"name":14,"slug":15,"type":16},{"name":9,"slug":21,"type":16},3]