[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-braintrust-braintrust-write-agent-behavior-spec":3,"mdc-8tdoxk-key":38,"related-org-braintrust-braintrust-write-agent-behavior-spec":283,"related-repo-braintrust-braintrust-write-agent-behavior-spec":460},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":27,"repoUrl":28,"updatedAt":29,"license":30,"forks":31,"topics":32,"repo":33,"sourceUrl":36,"mdContent":37},"braintrust-write-agent-behavior-spec","define and manage agent behavior specifications","Create, edit, audit, or compare versioned Agent Behavior specifications in .agents\u002Fbehaviors\u002F\u003Cname>\u002FBEHAVIOR.md. Use when a user wants to define recurring agent conduct, write a behavioral contract, make implicit trace-review expectations explicit, specify how an agent should handle uncertainty, destructive actions, or recovery, or describe intent, applicability, evidence, decision, execution, recovery, and failure modes. Also use to review or diff an existing BEHAVIOR.md. Do not use to implement system prompts, tool definitions, or scorer code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"braintrust","Braintrust","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fbraintrust.png","braintrustdata",[13,17,20,23,26],{"name":14,"slug":15,"type":16},"Documentation","documentation","tag",{"name":18,"slug":19,"type":16},"Best Practices","best-practices",{"name":21,"slug":22,"type":16},"Agents","agents",{"name":24,"slug":25,"type":16},"Technical Writing","technical-writing",{"name":9,"slug":8,"type":16},7,"https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Feval-library","2026-08-20T03:53:14.829935",null,0,[],{"repoUrl":28,"stars":27,"forks":31,"topics":34,"description":35},[],"Braintrust eval skills library","https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Feval-library\u002Ftree\u002FHEAD\u002Fskills\u002Fbraintrust-write-agent-behavior-spec","---\nname: braintrust-write-agent-behavior-spec\ndescription: >-\n  Create, edit, audit, or compare versioned Agent Behavior specifications in\n  .agents\u002Fbehaviors\u002F\u003Cname>\u002FBEHAVIOR.md. Use when a user wants to define recurring agent\n  conduct, write a behavioral contract, make implicit trace-review expectations explicit,\n  specify how an agent should handle uncertainty, destructive actions, or recovery, or\n  describe intent, applicability, evidence, decision, execution, recovery, and failure modes.\n  Also use to review or diff an existing BEHAVIOR.md. Do not use to implement system prompts,\n  tool definitions, or scorer code.\n---\n\n# Write an agent behavior spec\n\nContract: `references\u002Finteraction-contract.md`. Calibration, templates, provenance: `references\u002Fbehavior-spec-template.md`.\n\n## Trigger\n\n- Requests naming `BEHAVIOR.md`, a behavioral contract, or recurring agent conduct.\n- Review expectations that live only in reviewers' heads.\n- A failure class recurring across prompts and models — the standard is missing, not the prompt.\n\n## Do\n\n1. Name the recurring behavior and why mistakes matter. If traces exist, infer the spec from\n   them before asking anything.\n2. Write the seven sections in `reference.md`: intent, applicability, evidence, decision,\n   execution, recovery, failure modes.\n3. Write every clause so a reviewer could mark it satisfied or violated **from a trace alone**.\n   Replace \"handles uncertainty well\" with \"states the ambiguity and asks before writing files.\"\n4. Keep clauses durable across a prompt rewrite or model swap. Anything that would not survive\n   one belongs in the prompt, not the spec.\n5. Version and date it, then emit the observable review questions the spec implies — the contract\n   that evidence mapping and scorer work consume.\n\n## Avoid\n\n- Do not turn the spec into a system prompt, tool manual, or task instruction; it outlives all\n  three.\n- Do not encode tool names, model strings, or prompt wording into durable clauses.\n- Do not enumerate every situation; specify the decision rule and its boundaries.\n- Do not let the agent's author write the failure-modes section.\n\n## Check\n\n- All seven sections present; every clause observable in a trace and capable of being violated.\n- Failure modes named and distinct, not a generic \"does the wrong thing.\"\n- Versioned, dated, paired with review questions for the next skill.\n\n## Risk\n\n- Vague conduct produces subjective review, and subjective review produces disagreement that\n  gets misread as model variance.\n- Over-specification makes the standard brittle: a spec pinned to today's tool set fails the\n  day a tool is renamed.\n- An orphaned spec is the common failure — written, admired, never scored against. The review\n  questions are what prevent it.\n\n## Braintrust\n\nA spec is not a platform object; its clauses become three that are. Each **review question**\nbecomes a per-criterion score in a **human review queue** with free-text notes — this is how\nthe spec starts producing labels instead of sitting in a doc. Each **failure mode** becomes its\nown scorer (`references\u002Fplatform-mechanics.md` §5), so a regression in one mode is its own\ncolumn rather than averaged away. Applied to live traffic, violations become **trace classifications** you can\nalert and slice on. Tag the spec version in scorer span metadata, and treat a spec-version\nboundary like a scorer-version boundary: do not compare across it. When a review queue surfaces\na violation the spec does not cover, that is a spec gap — route it back here rather than\nwidening a scorer.\n",{"data":39,"body":40},{"name":4,"description":6},{"type":41,"children":42},"root",[43,52,75,82,110,116,161,167,190,196,214,220,238,242],{"type":44,"tag":45,"props":46,"children":48},"element","h1",{"id":47},"write-an-agent-behavior-spec",[49],{"type":50,"value":51},"text","Write an agent behavior spec",{"type":44,"tag":53,"props":54,"children":55},"p",{},[56,58,65,67,73],{"type":50,"value":57},"Contract: ",{"type":44,"tag":59,"props":60,"children":62},"code",{"className":61},[],[63],{"type":50,"value":64},"references\u002Finteraction-contract.md",{"type":50,"value":66},". Calibration, templates, provenance: ",{"type":44,"tag":59,"props":68,"children":70},{"className":69},[],[71],{"type":50,"value":72},"references\u002Fbehavior-spec-template.md",{"type":50,"value":74},".",{"type":44,"tag":76,"props":77,"children":79},"h2",{"id":78},"trigger",[80],{"type":50,"value":81},"Trigger",{"type":44,"tag":83,"props":84,"children":85},"ul",{},[86,100,105],{"type":44,"tag":87,"props":88,"children":89},"li",{},[90,92,98],{"type":50,"value":91},"Requests naming ",{"type":44,"tag":59,"props":93,"children":95},{"className":94},[],[96],{"type":50,"value":97},"BEHAVIOR.md",{"type":50,"value":99},", a behavioral contract, or recurring agent conduct.",{"type":44,"tag":87,"props":101,"children":102},{},[103],{"type":50,"value":104},"Review expectations that live only in reviewers' heads.",{"type":44,"tag":87,"props":106,"children":107},{},[108],{"type":50,"value":109},"A failure class recurring across prompts and models — the standard is missing, not the prompt.",{"type":44,"tag":76,"props":111,"children":113},{"id":112},"do",[114],{"type":50,"value":115},"Do",{"type":44,"tag":117,"props":118,"children":119},"ol",{},[120,125,138,151,156],{"type":44,"tag":87,"props":121,"children":122},{},[123],{"type":50,"value":124},"Name the recurring behavior and why mistakes matter. If traces exist, infer the spec from\nthem before asking anything.",{"type":44,"tag":87,"props":126,"children":127},{},[128,130,136],{"type":50,"value":129},"Write the seven sections in ",{"type":44,"tag":59,"props":131,"children":133},{"className":132},[],[134],{"type":50,"value":135},"reference.md",{"type":50,"value":137},": intent, applicability, evidence, decision,\nexecution, recovery, failure modes.",{"type":44,"tag":87,"props":139,"children":140},{},[141,143,149],{"type":50,"value":142},"Write every clause so a reviewer could mark it satisfied or violated ",{"type":44,"tag":144,"props":145,"children":146},"strong",{},[147],{"type":50,"value":148},"from a trace alone",{"type":50,"value":150},".\nReplace \"handles uncertainty well\" with \"states the ambiguity and asks before writing files.\"",{"type":44,"tag":87,"props":152,"children":153},{},[154],{"type":50,"value":155},"Keep clauses durable across a prompt rewrite or model swap. Anything that would not survive\none belongs in the prompt, not the spec.",{"type":44,"tag":87,"props":157,"children":158},{},[159],{"type":50,"value":160},"Version and date it, then emit the observable review questions the spec implies — the contract\nthat evidence mapping and scorer work consume.",{"type":44,"tag":76,"props":162,"children":164},{"id":163},"avoid",[165],{"type":50,"value":166},"Avoid",{"type":44,"tag":83,"props":168,"children":169},{},[170,175,180,185],{"type":44,"tag":87,"props":171,"children":172},{},[173],{"type":50,"value":174},"Do not turn the spec into a system prompt, tool manual, or task instruction; it outlives all\nthree.",{"type":44,"tag":87,"props":176,"children":177},{},[178],{"type":50,"value":179},"Do not encode tool names, model strings, or prompt wording into durable clauses.",{"type":44,"tag":87,"props":181,"children":182},{},[183],{"type":50,"value":184},"Do not enumerate every situation; specify the decision rule and its boundaries.",{"type":44,"tag":87,"props":186,"children":187},{},[188],{"type":50,"value":189},"Do not let the agent's author write the failure-modes section.",{"type":44,"tag":76,"props":191,"children":193},{"id":192},"check",[194],{"type":50,"value":195},"Check",{"type":44,"tag":83,"props":197,"children":198},{},[199,204,209],{"type":44,"tag":87,"props":200,"children":201},{},[202],{"type":50,"value":203},"All seven sections present; every clause observable in a trace and capable of being violated.",{"type":44,"tag":87,"props":205,"children":206},{},[207],{"type":50,"value":208},"Failure modes named and distinct, not a generic \"does the wrong thing.\"",{"type":44,"tag":87,"props":210,"children":211},{},[212],{"type":50,"value":213},"Versioned, dated, paired with review questions for the next skill.",{"type":44,"tag":76,"props":215,"children":217},{"id":216},"risk",[218],{"type":50,"value":219},"Risk",{"type":44,"tag":83,"props":221,"children":222},{},[223,228,233],{"type":44,"tag":87,"props":224,"children":225},{},[226],{"type":50,"value":227},"Vague conduct produces subjective review, and subjective review produces disagreement that\ngets misread as model variance.",{"type":44,"tag":87,"props":229,"children":230},{},[231],{"type":50,"value":232},"Over-specification makes the standard brittle: a spec pinned to today's tool set fails the\nday a tool is renamed.",{"type":44,"tag":87,"props":234,"children":235},{},[236],{"type":50,"value":237},"An orphaned spec is the common failure — written, admired, never scored against. The review\nquestions are what prevent it.",{"type":44,"tag":76,"props":239,"children":240},{"id":8},[241],{"type":50,"value":9},{"type":44,"tag":53,"props":243,"children":244},{},[245,247,252,254,259,261,266,268,274,276,281],{"type":50,"value":246},"A spec is not a platform object; its clauses become three that are. Each ",{"type":44,"tag":144,"props":248,"children":249},{},[250],{"type":50,"value":251},"review question",{"type":50,"value":253},"\nbecomes a per-criterion score in a ",{"type":44,"tag":144,"props":255,"children":256},{},[257],{"type":50,"value":258},"human review queue",{"type":50,"value":260}," with free-text notes — this is how\nthe spec starts producing labels instead of sitting in a doc. Each ",{"type":44,"tag":144,"props":262,"children":263},{},[264],{"type":50,"value":265},"failure mode",{"type":50,"value":267}," becomes its\nown scorer (",{"type":44,"tag":59,"props":269,"children":271},{"className":270},[],[272],{"type":50,"value":273},"references\u002Fplatform-mechanics.md",{"type":50,"value":275}," §5), so a regression in one mode is its own\ncolumn rather than averaged away. Applied to live traffic, violations become ",{"type":44,"tag":144,"props":277,"children":278},{},[279],{"type":50,"value":280},"trace classifications",{"type":50,"value":282}," you can\nalert and slice on. Tag the spec version in scorer span metadata, and treat a spec-version\nboundary like a scorer-version boundary: do not compare across it. When a review queue surfaces\na violation the spec does not cover, that is a spec gap — route it back here rather than\nwidening a scorer.",{"items":284,"total":459},[285,301,321,335,349,365,379,391,405,421,433,445],{"slug":286,"name":286,"fn":287,"description":288,"org":289,"tags":290,"stars":298,"repoUrl":299,"updatedAt":300},"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},[291,292,295],{"name":9,"slug":8,"type":16},{"name":293,"slug":294,"type":16},"Debugging","debugging",{"name":296,"slug":297,"type":16},"MCP","mcp",18,"https:\u002F\u002Fgithub.com\u002Fbraintrustdata\u002Fbraintrust-claude-plugin","2026-07-12T08:36:13.889274",{"slug":302,"name":302,"fn":303,"description":304,"org":305,"tags":306,"stars":27,"repoUrl":28,"updatedAt":320},"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},[307,310,311,314,317],{"name":308,"slug":309,"type":16},"Analysis","analysis",{"name":9,"slug":8,"type":16},{"name":312,"slug":313,"type":16},"Evals","evals",{"name":315,"slug":316,"type":16},"LLM","llm",{"name":318,"slug":319,"type":16},"Statistics","statistics","2026-08-20T03:53:01.13806",{"slug":322,"name":322,"fn":323,"description":324,"org":325,"tags":326,"stars":27,"repoUrl":28,"updatedAt":334},"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},[327,328,329,330,331],{"name":308,"slug":309,"type":16},{"name":9,"slug":8,"type":16},{"name":312,"slug":313,"type":16},{"name":315,"slug":316,"type":16},{"name":332,"slug":333,"type":16},"Performance","performance","2026-08-20T03:53:40.036077",{"slug":336,"name":336,"fn":337,"description":338,"org":339,"tags":340,"stars":27,"repoUrl":28,"updatedAt":348},"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},[341,342,343,346,347],{"name":21,"slug":22,"type":16},{"name":9,"slug":8,"type":16},{"name":344,"slug":345,"type":16},"Datasets","datasets",{"name":312,"slug":313,"type":16},{"name":315,"slug":316,"type":16},"2026-08-20T03:53:33.304815",{"slug":350,"name":350,"fn":351,"description":352,"org":353,"tags":354,"stars":27,"repoUrl":28,"updatedAt":364},"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},[355,356,357,358,361],{"name":9,"slug":8,"type":16},{"name":312,"slug":313,"type":16},{"name":315,"slug":316,"type":16},{"name":359,"slug":360,"type":16},"Product Management","product-management",{"name":362,"slug":363,"type":16},"Strategy","strategy","2026-08-20T03:53:00.07097",{"slug":366,"name":366,"fn":367,"description":368,"org":369,"tags":370,"stars":27,"repoUrl":28,"updatedAt":378},"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},[371,372,373,376,377],{"name":21,"slug":22,"type":16},{"name":9,"slug":8,"type":16},{"name":374,"slug":375,"type":16},"CI\u002FCD","ci-cd",{"name":312,"slug":313,"type":16},{"name":315,"slug":316,"type":16},"2026-08-20T03:53:15.686158",{"slug":380,"name":380,"fn":381,"description":382,"org":383,"tags":384,"stars":27,"repoUrl":28,"updatedAt":390},"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},[385,386,389],{"name":9,"slug":8,"type":16},{"name":387,"slug":388,"type":16},"Deployment","deployment",{"name":312,"slug":313,"type":16},"2026-08-20T03:53:32.558937",{"slug":392,"name":392,"fn":393,"description":394,"org":395,"tags":396,"stars":27,"repoUrl":28,"updatedAt":404},"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},[397,398,399,402,403],{"name":9,"slug":8,"type":16},{"name":312,"slug":313,"type":16},{"name":400,"slug":401,"type":16},"Experiments","experiments",{"name":315,"slug":316,"type":16},{"name":362,"slug":363,"type":16},"2026-08-20T03:53:36.534554",{"slug":406,"name":406,"fn":407,"description":408,"org":409,"tags":410,"stars":27,"repoUrl":28,"updatedAt":420},"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},[411,412,413,414,417],{"name":9,"slug":8,"type":16},{"name":344,"slug":345,"type":16},{"name":312,"slug":313,"type":16},{"name":415,"slug":416,"type":16},"Observability","observability",{"name":418,"slug":419,"type":16},"Tracing","tracing","2026-08-20T03:53:37.274703",{"slug":422,"name":422,"fn":423,"description":424,"org":425,"tags":426,"stars":27,"repoUrl":28,"updatedAt":432},"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},[427,428,429,430,431],{"name":21,"slug":22,"type":16},{"name":9,"slug":8,"type":16},{"name":312,"slug":313,"type":16},{"name":315,"slug":316,"type":16},{"name":332,"slug":333,"type":16},"2026-08-20T03:53:16.078609",{"slug":434,"name":434,"fn":435,"description":436,"org":437,"tags":438,"stars":27,"repoUrl":28,"updatedAt":444},"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},[439,440,441,442,443],{"name":21,"slug":22,"type":16},{"name":9,"slug":8,"type":16},{"name":344,"slug":345,"type":16},{"name":312,"slug":313,"type":16},{"name":315,"slug":316,"type":16},"2026-08-20T03:53:36.900129",{"slug":446,"name":446,"fn":447,"description":448,"org":449,"tags":450,"stars":27,"repoUrl":28,"updatedAt":458},"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},[451,452,453,454,455],{"name":21,"slug":22,"type":16},{"name":9,"slug":8,"type":16},{"name":293,"slug":294,"type":16},{"name":312,"slug":313,"type":16},{"name":456,"slug":457,"type":16},"Triage","triage","2026-08-20T03:53:00.423941",27,{"items":461,"total":516},[462,470,478,486,494,502,508],{"slug":302,"name":302,"fn":303,"description":304,"org":463,"tags":464,"stars":27,"repoUrl":28,"updatedAt":320},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[465,466,467,468,469],{"name":308,"slug":309,"type":16},{"name":9,"slug":8,"type":16},{"name":312,"slug":313,"type":16},{"name":315,"slug":316,"type":16},{"name":318,"slug":319,"type":16},{"slug":322,"name":322,"fn":323,"description":324,"org":471,"tags":472,"stars":27,"repoUrl":28,"updatedAt":334},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[473,474,475,476,477],{"name":308,"slug":309,"type":16},{"name":9,"slug":8,"type":16},{"name":312,"slug":313,"type":16},{"name":315,"slug":316,"type":16},{"name":332,"slug":333,"type":16},{"slug":336,"name":336,"fn":337,"description":338,"org":479,"tags":480,"stars":27,"repoUrl":28,"updatedAt":348},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[481,482,483,484,485],{"name":21,"slug":22,"type":16},{"name":9,"slug":8,"type":16},{"name":344,"slug":345,"type":16},{"name":312,"slug":313,"type":16},{"name":315,"slug":316,"type":16},{"slug":350,"name":350,"fn":351,"description":352,"org":487,"tags":488,"stars":27,"repoUrl":28,"updatedAt":364},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[489,490,491,492,493],{"name":9,"slug":8,"type":16},{"name":312,"slug":313,"type":16},{"name":315,"slug":316,"type":16},{"name":359,"slug":360,"type":16},{"name":362,"slug":363,"type":16},{"slug":366,"name":366,"fn":367,"description":368,"org":495,"tags":496,"stars":27,"repoUrl":28,"updatedAt":378},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[497,498,499,500,501],{"name":21,"slug":22,"type":16},{"name":9,"slug":8,"type":16},{"name":374,"slug":375,"type":16},{"name":312,"slug":313,"type":16},{"name":315,"slug":316,"type":16},{"slug":380,"name":380,"fn":381,"description":382,"org":503,"tags":504,"stars":27,"repoUrl":28,"updatedAt":390},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[505,506,507],{"name":9,"slug":8,"type":16},{"name":387,"slug":388,"type":16},{"name":312,"slug":313,"type":16},{"slug":392,"name":392,"fn":393,"description":394,"org":509,"tags":510,"stars":27,"repoUrl":28,"updatedAt":404},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[511,512,513,514,515],{"name":9,"slug":8,"type":16},{"name":312,"slug":313,"type":16},{"name":400,"slug":401,"type":16},{"name":315,"slug":316,"type":16},{"name":362,"slug":363,"type":16},24]