[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-braintrust-braintrust-plan-agent-eval":3,"mdc-7tf3dv-key":32,"related-org-braintrust-braintrust-plan-agent-eval":286,"related-repo-braintrust-braintrust-plan-agent-eval":461},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":21,"repoUrl":22,"updatedAt":23,"license":24,"forks":25,"topics":26,"repo":27,"sourceUrl":30,"mdContent":31},"braintrust-plan-agent-eval","plan evaluation workflows for LLM applications","Plan an evaluation workflow for an LLM application or agent by identifying the product decision, expected behavior, target population, evidence, datasets, scorers, validation, analysis, and release criteria. Use for broad or early-stage requests such as \"help me evaluate this agent,\" \"design an eval strategy,\" \"where do we start with evals,\" or when a user describes an agent, a product goal, or a production failure without naming an eval artifact. Do not use when the user already names a behavior spec, dataset, sample size, scorer, human review, experiment, analysis, release gate, or report — route to that skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"braintrust","Braintrust","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fbraintrust.png","braintrustdata",[13,17,20],{"name":14,"slug":15,"type":16},"LLM","llm","tag",{"name":18,"slug":19,"type":16},"Evals","evals",{"name":9,"slug":8,"type":16},7,"https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Feval-library","2026-08-20T03:52:55.941828",null,0,[],{"repoUrl":22,"stars":21,"forks":25,"topics":28,"description":29},[],"Braintrust eval skills library","https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Feval-library\u002Ftree\u002FHEAD\u002Fskills\u002Fbraintrust-plan-agent-eval","---\nname: braintrust-plan-agent-eval\ndescription: >-\n  Plan an evaluation workflow for an LLM application or agent by identifying the product\n  decision, expected behavior, target population, evidence, datasets, scorers, validation,\n  analysis, and release criteria. Use for broad or early-stage requests such as \"help me\n  evaluate this agent,\" \"design an eval strategy,\" \"where do we start with evals,\" or when a\n  user describes an agent, a product goal, or a production failure without naming an eval\n  artifact. Do not use when the user already names a behavior spec, dataset, sample size,\n  scorer, human review, experiment, analysis, release gate, or report — route to that skill.\n---\n\n# Plan an agent eval\n\nContract: `references\u002Finteraction-contract.md`. Calibration, templates, provenance: `references\u002Flifecycle-inventory.md`.\n\n## Trigger\n\n- Broad eval requests naming no artifact and no stage.\n- An agent, goal, or incident described with no eval scaffolding.\n- A stalled effort: metrics exist, but nobody can say which decision they serve.\n\n## Do\n\n1. Restate the product decision in one sentence. Every downstream choice serves it.\n2. Inventory existing artifacts against the staged lifecycle in `references\u002Flifecycle-inventory.md`,\n   labeling each stage `Confirmed` \u002F `Assumed` \u002F `Needs decision` \u002F `Not yet measurable`.\n3. Name the **earliest** missing artifact, not the most interesting one. A gap upstream makes\n   every downstream number uninterpretable.\n4. Check the two prerequisites teams skip: is the system instrumented well enough to reconstruct\n   a failure, and can anyone state what \"good\" means?\n5. Hand off the one stage to do next, its concrete first action, and the reason it blocks the rest.\n\n## Avoid\n\n- Do not walk the whole lifecycle in one pass or produce every artifact at once.\n- Do not intercept a request that already names an artifact.\n- Do not propose a public benchmark as the starting point; it measures its own construct.\n- Do not manufacture process for a low-stakes, reversible decision — say so instead.\n\n## Check\n\n- Decision stated; construct and population named or flagged unknown.\n- Every lifecycle stage carries a status label.\n- Exactly one recommended next stage, with its blocking reason.\n- Assumptions listed separately from confirmed facts.\n\n## Risk\n\n- A broad router over-triggers: it will invent process for someone who asked a narrow question.\n  Whenever the request already names an artifact, that artifact's own stage owns the work.\n- The earliest gap is usually unglamorous — instrumentation, population definition — and gets\n  skipped for scorer work.\n- Plans go stale as soon as the product changes. Date it; it is a map, not a contract.\n\n## Braintrust\n\nRead the project before asking — most planning questions answer themselves. Which of the four\nobjects (`references\u002Fplatform-mechanics.md` §1) already exist, and in what state? Are datasets\n**versioned** (§3)? Are scorers named consistently across experiments, or renamed per run (§5)?\nDo experiments record independent variables in metadata, or only scores (§4)? Is anything\nscoring production traffic?\n\nEach \"no\" is a lifecycle gap. Record it in the inventory rather than acting on it here — and\nnote that the §3 and §4 gaps are the ones with no retroactive fix, which usually makes them the\nearliest missing artifact even when they are not the most interesting one.\n",{"data":33,"body":34},{"name":4,"description":6},{"type":35,"children":36},"root",[37,46,69,76,96,102,175,181,204,210,233,239,257,261,281],{"type":38,"tag":39,"props":40,"children":42},"element","h1",{"id":41},"plan-an-agent-eval",[43],{"type":44,"value":45},"text","Plan an agent eval",{"type":38,"tag":47,"props":48,"children":49},"p",{},[50,52,59,61,67],{"type":44,"value":51},"Contract: ",{"type":38,"tag":53,"props":54,"children":56},"code",{"className":55},[],[57],{"type":44,"value":58},"references\u002Finteraction-contract.md",{"type":44,"value":60},". Calibration, templates, provenance: ",{"type":38,"tag":53,"props":62,"children":64},{"className":63},[],[65],{"type":44,"value":66},"references\u002Flifecycle-inventory.md",{"type":44,"value":68},".",{"type":38,"tag":70,"props":71,"children":73},"h2",{"id":72},"trigger",[74],{"type":44,"value":75},"Trigger",{"type":38,"tag":77,"props":78,"children":79},"ul",{},[80,86,91],{"type":38,"tag":81,"props":82,"children":83},"li",{},[84],{"type":44,"value":85},"Broad eval requests naming no artifact and no stage.",{"type":38,"tag":81,"props":87,"children":88},{},[89],{"type":44,"value":90},"An agent, goal, or incident described with no eval scaffolding.",{"type":38,"tag":81,"props":92,"children":93},{},[94],{"type":44,"value":95},"A stalled effort: metrics exist, but nobody can say which decision they serve.",{"type":38,"tag":70,"props":97,"children":99},{"id":98},"do",[100],{"type":44,"value":101},"Do",{"type":38,"tag":103,"props":104,"children":105},"ol",{},[106,111,152,165,170],{"type":38,"tag":81,"props":107,"children":108},{},[109],{"type":44,"value":110},"Restate the product decision in one sentence. Every downstream choice serves it.",{"type":38,"tag":81,"props":112,"children":113},{},[114,116,121,123,129,131,137,138,144,145,151],{"type":44,"value":115},"Inventory existing artifacts against the staged lifecycle in ",{"type":38,"tag":53,"props":117,"children":119},{"className":118},[],[120],{"type":44,"value":66},{"type":44,"value":122},",\nlabeling each stage ",{"type":38,"tag":53,"props":124,"children":126},{"className":125},[],[127],{"type":44,"value":128},"Confirmed",{"type":44,"value":130}," \u002F ",{"type":38,"tag":53,"props":132,"children":134},{"className":133},[],[135],{"type":44,"value":136},"Assumed",{"type":44,"value":130},{"type":38,"tag":53,"props":139,"children":141},{"className":140},[],[142],{"type":44,"value":143},"Needs decision",{"type":44,"value":130},{"type":38,"tag":53,"props":146,"children":148},{"className":147},[],[149],{"type":44,"value":150},"Not yet measurable",{"type":44,"value":68},{"type":38,"tag":81,"props":153,"children":154},{},[155,157,163],{"type":44,"value":156},"Name the ",{"type":38,"tag":158,"props":159,"children":160},"strong",{},[161],{"type":44,"value":162},"earliest",{"type":44,"value":164}," missing artifact, not the most interesting one. A gap upstream makes\nevery downstream number uninterpretable.",{"type":38,"tag":81,"props":166,"children":167},{},[168],{"type":44,"value":169},"Check the two prerequisites teams skip: is the system instrumented well enough to reconstruct\na failure, and can anyone state what \"good\" means?",{"type":38,"tag":81,"props":171,"children":172},{},[173],{"type":44,"value":174},"Hand off the one stage to do next, its concrete first action, and the reason it blocks the rest.",{"type":38,"tag":70,"props":176,"children":178},{"id":177},"avoid",[179],{"type":44,"value":180},"Avoid",{"type":38,"tag":77,"props":182,"children":183},{},[184,189,194,199],{"type":38,"tag":81,"props":185,"children":186},{},[187],{"type":44,"value":188},"Do not walk the whole lifecycle in one pass or produce every artifact at once.",{"type":38,"tag":81,"props":190,"children":191},{},[192],{"type":44,"value":193},"Do not intercept a request that already names an artifact.",{"type":38,"tag":81,"props":195,"children":196},{},[197],{"type":44,"value":198},"Do not propose a public benchmark as the starting point; it measures its own construct.",{"type":38,"tag":81,"props":200,"children":201},{},[202],{"type":44,"value":203},"Do not manufacture process for a low-stakes, reversible decision — say so instead.",{"type":38,"tag":70,"props":205,"children":207},{"id":206},"check",[208],{"type":44,"value":209},"Check",{"type":38,"tag":77,"props":211,"children":212},{},[213,218,223,228],{"type":38,"tag":81,"props":214,"children":215},{},[216],{"type":44,"value":217},"Decision stated; construct and population named or flagged unknown.",{"type":38,"tag":81,"props":219,"children":220},{},[221],{"type":44,"value":222},"Every lifecycle stage carries a status label.",{"type":38,"tag":81,"props":224,"children":225},{},[226],{"type":44,"value":227},"Exactly one recommended next stage, with its blocking reason.",{"type":38,"tag":81,"props":229,"children":230},{},[231],{"type":44,"value":232},"Assumptions listed separately from confirmed facts.",{"type":38,"tag":70,"props":234,"children":236},{"id":235},"risk",[237],{"type":44,"value":238},"Risk",{"type":38,"tag":77,"props":240,"children":241},{},[242,247,252],{"type":38,"tag":81,"props":243,"children":244},{},[245],{"type":44,"value":246},"A broad router over-triggers: it will invent process for someone who asked a narrow question.\nWhenever the request already names an artifact, that artifact's own stage owns the work.",{"type":38,"tag":81,"props":248,"children":249},{},[250],{"type":44,"value":251},"The earliest gap is usually unglamorous — instrumentation, population definition — and gets\nskipped for scorer work.",{"type":38,"tag":81,"props":253,"children":254},{},[255],{"type":44,"value":256},"Plans go stale as soon as the product changes. Date it; it is a map, not a contract.",{"type":38,"tag":70,"props":258,"children":259},{"id":8},[260],{"type":44,"value":9},{"type":38,"tag":47,"props":262,"children":263},{},[264,266,272,274,279],{"type":44,"value":265},"Read the project before asking — most planning questions answer themselves. Which of the four\nobjects (",{"type":38,"tag":53,"props":267,"children":269},{"className":268},[],[270],{"type":44,"value":271},"references\u002Fplatform-mechanics.md",{"type":44,"value":273}," §1) already exist, and in what state? Are datasets\n",{"type":38,"tag":158,"props":275,"children":276},{},[277],{"type":44,"value":278},"versioned",{"type":44,"value":280}," (§3)? Are scorers named consistently across experiments, or renamed per run (§5)?\nDo experiments record independent variables in metadata, or only scores (§4)? Is anything\nscoring production traffic?",{"type":38,"tag":47,"props":282,"children":283},{},[284],{"type":44,"value":285},"Each \"no\" is a lifecycle gap. Record it in the inventory rather than acting on it here — and\nnote that the §3 and §4 gaps are the ones with no retroactive fix, which usually makes them the\nearliest missing artifact even when they are not the most interesting one.",{"items":287,"total":460},[288,304,320,334,350,366,380,392,406,422,434,446],{"slug":289,"name":289,"fn":290,"description":291,"org":292,"tags":293,"stars":301,"repoUrl":302,"updatedAt":303},"troubleshoot-braintrust-mcp","configure and troubleshoot Braintrust MCP servers","This plugin auto-configures a \"braintrust\" MCP server. If you can't see it or reach it, activate this skill\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[294,295,298],{"name":9,"slug":8,"type":16},{"name":296,"slug":297,"type":16},"Debugging","debugging",{"name":299,"slug":300,"type":16},"MCP","mcp",18,"https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Fbraintrust-claude-plugin","2026-07-12T08:36:13.889274",{"slug":305,"name":305,"fn":306,"description":307,"org":308,"tags":309,"stars":21,"repoUrl":22,"updatedAt":319},"braintrust-analyze-eval-experiment","analyze LLM and agent eval experiments","Analyze completed LLM or agent eval experiments using uncertainty-aware and decision-relevant methods. Use to audit run completeness and pairing, calculate confidence intervals, run paired comparisons, report wins, losses, and ties, incorporate run-to-run variance, handle multiple comparisons, inspect subgroup performance, and test fragility to favorable slices. Use when results already exist and someone asks what they mean, whether a difference is real, or which model won. Do not use to design an experiment that has not yet collected results.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[310,313,314,315,316],{"name":311,"slug":312,"type":16},"Analysis","analysis",{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":317,"slug":318,"type":16},"Statistics","statistics","2026-08-20T03:53:01.13806",{"slug":321,"name":321,"fn":322,"description":323,"org":324,"tags":325,"stars":21,"repoUrl":22,"updatedAt":333},"braintrust-attribute-multi-variable-change","attribute performance changes to multiple variables","Attribute an observed change when several things moved at once — model plus prompt plus tools, a provider migration, a framework upgrade, or a vendor swap that bundles serving stack with model. Use when asked which part of a change caused the result, when a comparison's arms differ in more than one way, when a treatment has no uniform implementation across vendors, or when a serving-stack difference is confounded with a model difference. Do not use for a clean single-variable comparison, or to design an experiment that has not yet run.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[326,327,328,329,330],{"name":311,"slug":312,"type":16},{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":331,"slug":332,"type":16},"Performance","performance","2026-08-20T03:53:40.036077",{"slug":335,"name":335,"fn":336,"description":337,"org":338,"tags":339,"stars":21,"repoUrl":22,"updatedAt":349},"braintrust-build-eval-dataset","create and manage LLM eval datasets","Create, edit, audit, or compare eval datasets for LLM applications and agents, including target-population definition, case sourcing from production traces, stratified sampling, label provenance and label audits, expected values as constraints for open-ended tasks, dev\u002Ftest splits, contamination and leakage controls, headroom checks, refresh policy, and datasheets. Use when working on the content or lifecycle of an eval dataset. Do not use for sample-size or power calculations, scorer implementation, or open-ended adversarial failure discovery.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[340,343,344,347,348],{"name":341,"slug":342,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":345,"slug":346,"type":16},"Datasets","datasets",{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},"2026-08-20T03:53:33.304815",{"slug":351,"name":351,"fn":352,"description":353,"org":354,"tags":355,"stars":21,"repoUrl":22,"updatedAt":365},"braintrust-define-eval-objective","define LLM evaluation objectives","Create, edit, or audit an eval objective by working backward from a product decision to the target outcome, construct, population, intended claim, and verification-versus-validation questions. Use when a team is unsure what an eval should establish, asks \"what are we actually trying to measure,\" \"is this eval measuring the right thing,\" \"does this benchmark support our claim,\" or needs to turn a product goal into an eval objective and state which claims are out of scope. Do not use to select detailed metrics, design datasets, or implement scorers.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[356,357,358,359,362],{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":360,"slug":361,"type":16},"Product Management","product-management",{"name":363,"slug":364,"type":16},"Strategy","strategy","2026-08-20T03:53:00.07097",{"slug":367,"name":367,"fn":368,"description":369,"org":370,"tags":371,"stars":21,"repoUrl":22,"updatedAt":379},"braintrust-define-eval-release-gate","configure release gates for LLM applications","Create, edit, audit, or apply release gates for LLM applications and agents. Use to combine minimum meaningful improvement, statistical significance, regression rate, subgroup consistency, worst-run stability, all-attempts reliability, safety upper bounds, latency, and cost into an explicit ship-or-hold policy, to turn metrics into a CI gate, or to explain why a candidate failed a gate and what evidence would justify reconsideration. Do not use for general result analysis without a deployment decision.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[372,373,374,377,378],{"name":341,"slug":342,"type":16},{"name":9,"slug":8,"type":16},{"name":375,"slug":376,"type":16},"CI\u002FCD","ci-cd",{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},"2026-08-20T03:53:15.686158",{"slug":381,"name":381,"fn":382,"description":383,"org":384,"tags":385,"stars":21,"repoUrl":22,"updatedAt":391},"braintrust-deploy-evaluator","deploy evaluators to Braintrust","Take a validated scorer or classifier from definition to running instrument in Braintrust — scope selection, inline testing before saving, saving as an evaluator, attaching an online-scoring rule, activating it for new traffic, and backfilling history with a rewind. Use when a scorer needs to actually run against production logs, when an online-scoring rule needs to be created or changed, or when historical traces need scoring. Do not use to decide what the scorer should measure, to write its rubric, or to establish that it agrees with human judgment.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[386,387,390],{"name":9,"slug":8,"type":16},{"name":388,"slug":389,"type":16},"Deployment","deployment",{"name":18,"slug":19,"type":16},"2026-08-20T03:53:32.558937",{"slug":393,"name":393,"fn":394,"description":395,"org":396,"tags":397,"stars":21,"repoUrl":22,"updatedAt":405},"braintrust-design-eval-experiment","design controlled LLM eval experiments","Design or audit controlled eval experiments for model, prompt, retrieval, tool, guardrail, or agent-architecture changes. Use before data collection to state directional and minimum-effect hypotheses, name independent, dependent, and control variables including the serving environment and tool surface, choose paired designs, set repetitions and allocation, distinguish exploratory from confirmatory comparisons, and pre-specify stopping, exclusion, multiplicity, and analysis rules. Do not use primarily to analyze results already collected.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[398,399,400,403,404],{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":401,"slug":402,"type":16},"Experiments","experiments",{"name":14,"slug":15,"type":16},{"name":363,"slug":364,"type":16},"2026-08-20T03:53:36.534554",{"slug":407,"name":407,"fn":408,"description":409,"org":410,"tags":411,"stars":21,"repoUrl":22,"updatedAt":421},"braintrust-design-eval-instrumentation","design trace and evaluation dataset schemas","Design the trace and eval-dataset schema for an LLM app or agent, and wire the system to emit it. Use when deciding what to log, designing a trace schema, setting up tracing or observability before evals, or when failures cannot be debugged or sliced from existing traces — covering inputs, outputs, spans for tool and LLM calls, state changes, metadata, resolved configuration, serving path, tool manifest, per-item status, attachments, and subgroup variables. Do not use to decide what the evidence should mean, or to write scorers.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[412,413,414,415,418],{"name":9,"slug":8,"type":16},{"name":345,"slug":346,"type":16},{"name":18,"slug":19,"type":16},{"name":416,"slug":417,"type":16},"Observability","observability",{"name":419,"slug":420,"type":16},"Tracing","tracing","2026-08-20T03:53:37.274703",{"slug":423,"name":423,"fn":424,"description":425,"org":426,"tags":427,"stars":21,"repoUrl":22,"updatedAt":433},"braintrust-design-eval-metric-bundle","create multi-objective evaluation metric bundles","Create, edit, audit, or compare a multi-objective eval metric bundle covering product quality, safety, reliability, latency, and cost. Use to choose metrics for an eval, define a goodness bundle, distinguish optimization metrics from non-regression guardrails, expose tradeoffs, audit a KPI or single composite score for Goodhart and metric-gaming risk, or answer \"what should improve and what must not regress.\" Do not use to design trace schemas, build datasets, or implement scoring methods.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[428,429,430,431,432],{"name":341,"slug":342,"type":16},{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":331,"slug":332,"type":16},"2026-08-20T03:53:16.078609",{"slug":435,"name":435,"fn":436,"description":437,"org":438,"tags":439,"stars":21,"repoUrl":22,"updatedAt":445},"braintrust-design-human-eval-review","design human evaluation and review workflows","Design or audit human evaluation workflows and golden datasets for LLM applications and agents. Use to set up expert review, select review cases, write reviewer instructions, assign raters, capture rationales and confidence, measure inter-rater agreement with kappa or alpha, adjudicate disagreements, and preserve reviewed examples with provenance as a versioned reference set. Do not use to elicit the criteria or rubric in the first place, to validate a scorer once reference labels exist, or to implement the scorer.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[440,441,442,443,444],{"name":341,"slug":342,"type":16},{"name":9,"slug":8,"type":16},{"name":345,"slug":346,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},"2026-08-20T03:53:36.900129",{"slug":447,"name":447,"fn":448,"description":449,"org":450,"tags":451,"stars":21,"repoUrl":22,"updatedAt":459},"braintrust-discover-agent-failures","identify and classify agent failure modes","Search open-endedly for unanticipated agent failure modes and convert them into a named taxonomy and durable regression items. Use for requests to find out what goes wrong, surface unknown or silent failures, do error analysis over traces, cluster and triage production failures, or build a failure taxonomy — where the goal is discovering modes nobody thought to test rather than measuring a predefined criterion. Produces datasets and taxonomies, not headline scores. Do not use for adversarial attacks against a threat model, or to measure a known criterion.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[452,453,454,455,456],{"name":341,"slug":342,"type":16},{"name":9,"slug":8,"type":16},{"name":296,"slug":297,"type":16},{"name":18,"slug":19,"type":16},{"name":457,"slug":458,"type":16},"Triage","triage","2026-08-20T03:53:00.423941",27,{"items":462,"total":517},[463,471,479,487,495,503,509],{"slug":305,"name":305,"fn":306,"description":307,"org":464,"tags":465,"stars":21,"repoUrl":22,"updatedAt":319},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[466,467,468,469,470],{"name":311,"slug":312,"type":16},{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":317,"slug":318,"type":16},{"slug":321,"name":321,"fn":322,"description":323,"org":472,"tags":473,"stars":21,"repoUrl":22,"updatedAt":333},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[474,475,476,477,478],{"name":311,"slug":312,"type":16},{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":331,"slug":332,"type":16},{"slug":335,"name":335,"fn":336,"description":337,"org":480,"tags":481,"stars":21,"repoUrl":22,"updatedAt":349},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[482,483,484,485,486],{"name":341,"slug":342,"type":16},{"name":9,"slug":8,"type":16},{"name":345,"slug":346,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"slug":351,"name":351,"fn":352,"description":353,"org":488,"tags":489,"stars":21,"repoUrl":22,"updatedAt":365},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[490,491,492,493,494],{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":360,"slug":361,"type":16},{"name":363,"slug":364,"type":16},{"slug":367,"name":367,"fn":368,"description":369,"org":496,"tags":497,"stars":21,"repoUrl":22,"updatedAt":379},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[498,499,500,501,502],{"name":341,"slug":342,"type":16},{"name":9,"slug":8,"type":16},{"name":375,"slug":376,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"slug":381,"name":381,"fn":382,"description":383,"org":504,"tags":505,"stars":21,"repoUrl":22,"updatedAt":391},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[506,507,508],{"name":9,"slug":8,"type":16},{"name":388,"slug":389,"type":16},{"name":18,"slug":19,"type":16},{"slug":393,"name":393,"fn":394,"description":395,"org":510,"tags":511,"stars":21,"repoUrl":22,"updatedAt":405},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[512,513,514,515,516],{"name":9,"slug":8,"type":16},{"name":18,"slug":19,"type":16},{"name":401,"slug":402,"type":16},{"name":14,"slug":15,"type":16},{"name":363,"slug":364,"type":16},24]