[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-microsoft-context-intelligence-evaluation-methodology":3,"mdc-x6ujqh-key":34,"related-org-microsoft-context-intelligence-evaluation-methodology":355,"related-repo-microsoft-context-intelligence-evaluation-methodology":550},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":32,"mdContent":33},"context-intelligence-evaluation-methodology","design evaluation metrics for tool signals","Use when deciding how to measure a context-intelligence tool signal — metric design across quality\u002Fefficiency\u002Fefficacy axes, artifact-metric avoidance via precursor measurement, A\u002FB and statistical-N discipline, and test-data fidelity.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"microsoft","Microsoft","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fmicrosoft.png",[12,16,19,20],{"name":13,"slug":14,"type":15},"Evals","evals","tag",{"name":17,"slug":18,"type":15},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"Statistics","statistics",3,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-bundle-context-intelligence","2026-07-07T06:52:41.770083","MIT",4,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"Context Intelligence bundle for the Amplifier project","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-bundle-context-intelligence\u002Ftree\u002FHEAD\u002Fskills\u002Fcontext-intelligence-evaluation-methodology","---\nname: context-intelligence-evaluation-methodology\nversion: 1.0.0\ndescription: Use when deciding how to measure a context-intelligence tool signal — metric design across quality\u002Fefficiency\u002Fefficacy axes, artifact-metric avoidance via precursor measurement, A\u002FB and statistical-N discipline, and test-data fidelity.\nuser-invocable: false\nallowed-tools: read_file, glob, grep, delegate, load_skill, todo\nmodel_role: reasoning\nlicense: MIT\n---\n\n# Context Intelligence Evaluation Methodology\n\nMode-only skill for *how to measure*. It complements — and never restates —\n`context-intelligence-eval-design` (which owns scenario mechanics and the two-layer\nstructural\u002Fbehavioral structure) and `digital-twin-universe` (which owns the DTU machinery).\n\n## Scope\n\n### In scope\n\n- **Metric design.** Choose metrics across three axes: **quality** (did it detect what the user\n  means?), **efficiency** (token\u002Ftool cost to detect), **efficacy** (does detection drive the\n  right outcome?).\n- **Measure the precursor, not only the failure.** Prefer leading indicators (e.g. bounded vs\n  climbing context growth) over lagging ones (e.g. a final timeout). The precursor is testable\n  in a short window; the full failure often is not.\n- **A\u002FB + statistical-N discipline.** A single green run is not proof of a behavioral change.\n  Compare a control arm against a treatment arm; require N independent trials and report the\n  pass rate, not a single anecdote.\n- **Test data fidelity.** Validate on **real sessions** where available, or on **faithfully\n  modeled synthetic** corpora that preserve the distribution that matters (e.g. heavy-tail file\n  sizes), never on data hand-shaped to pass.\n\n### Out of scope (point elsewhere — do not restate)\n\n- **Scenario mechanics, the two-layer structure, DTU profile templates \u002F Gitea URL rewrite** →\n  `context-intelligence-eval-design`.\n- **DTU lifecycle, launch\u002Fexec\u002Fprofiles** → the `digital-twin-universe` skill.\n- **\"DTU-as-default\" rationale and the \"artifact-as-success\" anti-pattern** → already authoritative\n  in `context-intelligence-eval-design` and\n  `context-intelligence:context\u002Fcontext-intelligence-primitives-reference.md`. Reference them;\n  do not repeat them.\n\n## Method\n\n1. **Name the user-meaningful outcome** the metric must reflect (from `domain-concepts.md`),\n   not what a detector happens to emit.\n2. **Pick the cheapest axis that discriminates.** If a deterministic efficiency signal (token\n   growth, tool-call count) separates good from bad behavior, prefer it over an LLM-judged\n   quality rubric.\n3. **Identify the precursor.** Ask: what climbs *before* the failure? Measure that in a bounded\n   window.\n4. **Design the A\u002FB.** Control = current behavior; treatment = the change. Hold everything else\n   identical. Decide N and the pass threshold *before* running.\n5. **Choose the corpus.** Real sessions if available; otherwise synthetic that preserves the\n   load-bearing distribution. State the fidelity assumption explicitly.\n\n> **Apply (do not restate) the event-semantics principle:** when a metric depends on what an\n> event *means*, consult the authoritative ecosystem expert agents for that event's semantics —\n> the principle is named once in\n> `context-intelligence:context\u002Fcontext-intelligence-strategy.md`. Do not restate it here.\n",{"data":35,"body":40},{"name":4,"version":36,"description":6,"user-invocable":37,"allowed-tools":38,"model_role":39,"license":26},"1.0.0",false,"read_file, glob, grep, delegate, load_skill, todo","reasoning",{"type":41,"children":42},"root",[43,51,82,89,96,177,183,245,251,326],{"type":44,"tag":45,"props":46,"children":47},"element","h1",{"id":4},[48],{"type":49,"value":50},"text","Context Intelligence Evaluation Methodology",{"type":44,"tag":52,"props":53,"children":54},"p",{},[55,57,63,65,72,74,80],{"type":49,"value":56},"Mode-only skill for ",{"type":44,"tag":58,"props":59,"children":60},"em",{},[61],{"type":49,"value":62},"how to measure",{"type":49,"value":64},". It complements — and never restates —\n",{"type":44,"tag":66,"props":67,"children":69},"code",{"className":68},[],[70],{"type":49,"value":71},"context-intelligence-eval-design",{"type":49,"value":73}," (which owns scenario mechanics and the two-layer\nstructural\u002Fbehavioral structure) and ",{"type":44,"tag":66,"props":75,"children":77},{"className":76},[],[78],{"type":49,"value":79},"digital-twin-universe",{"type":49,"value":81}," (which owns the DTU machinery).",{"type":44,"tag":83,"props":84,"children":86},"h2",{"id":85},"scope",[87],{"type":49,"value":88},"Scope",{"type":44,"tag":90,"props":91,"children":93},"h3",{"id":92},"in-scope",[94],{"type":49,"value":95},"In scope",{"type":44,"tag":97,"props":98,"children":99},"ul",{},[100,133,143,153],{"type":44,"tag":101,"props":102,"children":103},"li",{},[104,110,112,117,119,124,126,131],{"type":44,"tag":105,"props":106,"children":107},"strong",{},[108],{"type":49,"value":109},"Metric design.",{"type":49,"value":111}," Choose metrics across three axes: ",{"type":44,"tag":105,"props":113,"children":114},{},[115],{"type":49,"value":116},"quality",{"type":49,"value":118}," (did it detect what the user\nmeans?), ",{"type":44,"tag":105,"props":120,"children":121},{},[122],{"type":49,"value":123},"efficiency",{"type":49,"value":125}," (token\u002Ftool cost to detect), ",{"type":44,"tag":105,"props":127,"children":128},{},[129],{"type":49,"value":130},"efficacy",{"type":49,"value":132}," (does detection drive the\nright outcome?).",{"type":44,"tag":101,"props":134,"children":135},{},[136,141],{"type":44,"tag":105,"props":137,"children":138},{},[139],{"type":49,"value":140},"Measure the precursor, not only the failure.",{"type":49,"value":142}," Prefer leading indicators (e.g. bounded vs\nclimbing context growth) over lagging ones (e.g. a final timeout). The precursor is testable\nin a short window; the full failure often is not.",{"type":44,"tag":101,"props":144,"children":145},{},[146,151],{"type":44,"tag":105,"props":147,"children":148},{},[149],{"type":49,"value":150},"A\u002FB + statistical-N discipline.",{"type":49,"value":152}," A single green run is not proof of a behavioral change.\nCompare a control arm against a treatment arm; require N independent trials and report the\npass rate, not a single anecdote.",{"type":44,"tag":101,"props":154,"children":155},{},[156,161,163,168,170,175],{"type":44,"tag":105,"props":157,"children":158},{},[159],{"type":49,"value":160},"Test data fidelity.",{"type":49,"value":162}," Validate on ",{"type":44,"tag":105,"props":164,"children":165},{},[166],{"type":49,"value":167},"real sessions",{"type":49,"value":169}," where available, or on ",{"type":44,"tag":105,"props":171,"children":172},{},[173],{"type":49,"value":174},"faithfully\nmodeled synthetic",{"type":49,"value":176}," corpora that preserve the distribution that matters (e.g. heavy-tail file\nsizes), never on data hand-shaped to pass.",{"type":44,"tag":90,"props":178,"children":180},{"id":179},"out-of-scope-point-elsewhere-do-not-restate",[181],{"type":49,"value":182},"Out of scope (point elsewhere — do not restate)",{"type":44,"tag":97,"props":184,"children":185},{},[186,203,220],{"type":44,"tag":101,"props":187,"children":188},{},[189,194,196,201],{"type":44,"tag":105,"props":190,"children":191},{},[192],{"type":49,"value":193},"Scenario mechanics, the two-layer structure, DTU profile templates \u002F Gitea URL rewrite",{"type":49,"value":195}," →\n",{"type":44,"tag":66,"props":197,"children":199},{"className":198},[],[200],{"type":49,"value":71},{"type":49,"value":202},".",{"type":44,"tag":101,"props":204,"children":205},{},[206,211,213,218],{"type":44,"tag":105,"props":207,"children":208},{},[209],{"type":49,"value":210},"DTU lifecycle, launch\u002Fexec\u002Fprofiles",{"type":49,"value":212}," → the ",{"type":44,"tag":66,"props":214,"children":216},{"className":215},[],[217],{"type":49,"value":79},{"type":49,"value":219}," skill.",{"type":44,"tag":101,"props":221,"children":222},{},[223,228,230,235,237,243],{"type":44,"tag":105,"props":224,"children":225},{},[226],{"type":49,"value":227},"\"DTU-as-default\" rationale and the \"artifact-as-success\" anti-pattern",{"type":49,"value":229}," → already authoritative\nin ",{"type":44,"tag":66,"props":231,"children":233},{"className":232},[],[234],{"type":49,"value":71},{"type":49,"value":236}," and\n",{"type":44,"tag":66,"props":238,"children":240},{"className":239},[],[241],{"type":49,"value":242},"context-intelligence:context\u002Fcontext-intelligence-primitives-reference.md",{"type":49,"value":244},". Reference them;\ndo not repeat them.",{"type":44,"tag":83,"props":246,"children":248},{"id":247},"method",[249],{"type":49,"value":250},"Method",{"type":44,"tag":252,"props":253,"children":254},"ol",{},[255,273,283,300,316],{"type":44,"tag":101,"props":256,"children":257},{},[258,263,265,271],{"type":44,"tag":105,"props":259,"children":260},{},[261],{"type":49,"value":262},"Name the user-meaningful outcome",{"type":49,"value":264}," the metric must reflect (from ",{"type":44,"tag":66,"props":266,"children":268},{"className":267},[],[269],{"type":49,"value":270},"domain-concepts.md",{"type":49,"value":272},"),\nnot what a detector happens to emit.",{"type":44,"tag":101,"props":274,"children":275},{},[276,281],{"type":44,"tag":105,"props":277,"children":278},{},[279],{"type":49,"value":280},"Pick the cheapest axis that discriminates.",{"type":49,"value":282}," If a deterministic efficiency signal (token\ngrowth, tool-call count) separates good from bad behavior, prefer it over an LLM-judged\nquality rubric.",{"type":44,"tag":101,"props":284,"children":285},{},[286,291,293,298],{"type":44,"tag":105,"props":287,"children":288},{},[289],{"type":49,"value":290},"Identify the precursor.",{"type":49,"value":292}," Ask: what climbs ",{"type":44,"tag":58,"props":294,"children":295},{},[296],{"type":49,"value":297},"before",{"type":49,"value":299}," the failure? Measure that in a bounded\nwindow.",{"type":44,"tag":101,"props":301,"children":302},{},[303,308,310,314],{"type":44,"tag":105,"props":304,"children":305},{},[306],{"type":49,"value":307},"Design the A\u002FB.",{"type":49,"value":309}," Control = current behavior; treatment = the change. Hold everything else\nidentical. Decide N and the pass threshold ",{"type":44,"tag":58,"props":311,"children":312},{},[313],{"type":49,"value":297},{"type":49,"value":315}," running.",{"type":44,"tag":101,"props":317,"children":318},{},[319,324],{"type":44,"tag":105,"props":320,"children":321},{},[322],{"type":49,"value":323},"Choose the corpus.",{"type":49,"value":325}," Real sessions if available; otherwise synthetic that preserves the\nload-bearing distribution. State the fidelity assumption explicitly.",{"type":44,"tag":327,"props":328,"children":329},"blockquote",{},[330],{"type":44,"tag":52,"props":331,"children":332},{},[333,338,340,345,347,353],{"type":44,"tag":105,"props":334,"children":335},{},[336],{"type":49,"value":337},"Apply (do not restate) the event-semantics principle:",{"type":49,"value":339}," when a metric depends on what an\nevent ",{"type":44,"tag":58,"props":341,"children":342},{},[343],{"type":49,"value":344},"means",{"type":49,"value":346},", consult the authoritative ecosystem expert agents for that event's semantics —\nthe principle is named once in\n",{"type":44,"tag":66,"props":348,"children":350},{"className":349},[],[351],{"type":49,"value":352},"context-intelligence:context\u002Fcontext-intelligence-strategy.md",{"type":49,"value":354},". Do not restate it here.",{"items":356,"total":549},[357,379,400,419,434,451,462,475,490,505,524,537],{"slug":358,"name":358,"fn":359,"description":360,"org":361,"tags":362,"stars":376,"repoUrl":377,"updatedAt":378},"rushstack-best-practices","manage Rush monorepos with best practices","Provides best practices and guidance for working with Rush monorepos. Use when the user is working in a Rush-based repository, asks about Rush commands (install, update, build, rebuild), needs help with project selection, dependency management, build caching, subspace configuration, or troubleshooting Rush-specific issues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[363,366,369,370,373],{"name":364,"slug":365,"type":15},"Engineering","engineering",{"name":367,"slug":368,"type":15},"Local Development","local-development",{"name":9,"slug":8,"type":15},{"name":371,"slug":372,"type":15},"Project Management","project-management",{"name":374,"slug":375,"type":15},"Rush","rush",6484,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Frushstack","2026-04-06T18:34:44.965032",{"slug":380,"name":380,"fn":381,"description":382,"org":383,"tags":384,"stars":397,"repoUrl":398,"updatedAt":399},"azure-ai-agents-persistent-dotnet","build AI agents with Azure .NET SDK","Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: \"PersistentAgentsClient\", \"persistent agents\", \"agent threads\", \"agent runs\", \"streaming agents\", \"function calling agents .NET\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[385,388,391,394],{"name":386,"slug":387,"type":15},".NET","net",{"name":389,"slug":390,"type":15},"Agents","agents",{"name":392,"slug":393,"type":15},"Azure","azure",{"name":395,"slug":396,"type":15},"LLM","llm",2804,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","2026-07-03T16:32:10.297433",{"slug":401,"name":401,"fn":402,"description":403,"org":404,"tags":405,"stars":397,"repoUrl":398,"updatedAt":418},"azure-ai-anomalydetector-java","build anomaly detection applications with Java","Build anomaly detection applications with Azure AI Anomaly Detector SDK for Java. Use when implementing univariate\u002Fmultivariate anomaly detection, time-series analysis, or AI-powered monitoring.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[406,409,410,411,414,415],{"name":407,"slug":408,"type":15},"Analytics","analytics",{"name":392,"slug":393,"type":15},{"name":17,"slug":18,"type":15},{"name":412,"slug":413,"type":15},"Java","java",{"name":9,"slug":8,"type":15},{"name":416,"slug":417,"type":15},"Monitoring","monitoring","2026-05-13T06:14:16.261754",{"slug":420,"name":420,"fn":421,"description":422,"org":423,"tags":424,"stars":397,"repoUrl":398,"updatedAt":433},"azure-ai-contentsafety-java","build content moderation applications with Azure AI","Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text\u002Fimage analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[425,428,429,430],{"name":426,"slug":427,"type":15},"AI Infrastructure","ai-infrastructure",{"name":392,"slug":393,"type":15},{"name":412,"slug":413,"type":15},{"name":431,"slug":432,"type":15},"Security","security","2026-07-07T06:53:31.293235",{"slug":435,"name":435,"fn":436,"description":437,"org":438,"tags":439,"stars":397,"repoUrl":398,"updatedAt":450},"azure-ai-contentsafety-py","detect harmful content with Azure AI Content Safety","Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.\nTriggers: \"azure-ai-contentsafety\", \"ContentSafetyClient\", \"content moderation\", \"harmful content\", \"text analysis\", \"image analysis\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[440,441,444,445,446,449],{"name":392,"slug":393,"type":15},{"name":442,"slug":443,"type":15},"Compliance","compliance",{"name":395,"slug":396,"type":15},{"name":9,"slug":8,"type":15},{"name":447,"slug":448,"type":15},"Python","python",{"name":431,"slug":432,"type":15},"2026-07-18T05:14:23.017504",{"slug":452,"name":452,"fn":453,"description":454,"org":455,"tags":456,"stars":397,"repoUrl":398,"updatedAt":461},"azure-ai-language-conversations-py","implement conversational language understanding with Python","Implement Conversational Language Understanding (CLU) using the azure-ai-language-conversations Python SDK. Use when working with ConversationAnalysisClient to analyze conversation intent and entities, building NLP features, or integrating language understanding into applications.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[457,458,459,460],{"name":407,"slug":408,"type":15},{"name":392,"slug":393,"type":15},{"name":395,"slug":396,"type":15},{"name":447,"slug":448,"type":15},"2026-07-31T05:54:29.068751",{"slug":463,"name":463,"fn":464,"description":465,"org":466,"tags":467,"stars":397,"repoUrl":398,"updatedAt":474},"azure-ai-translation-text-py","translate text using Azure AI services","Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications.\nTriggers: \"text translation\", \"translator\", \"translate text\", \"transliterate\", \"TextTranslationClient\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[468,471,472,473],{"name":469,"slug":470,"type":15},"API Development","api-development",{"name":392,"slug":393,"type":15},{"name":9,"slug":8,"type":15},{"name":447,"slug":448,"type":15},"2026-07-18T05:14:16.988376",{"slug":476,"name":476,"fn":477,"description":478,"org":479,"tags":480,"stars":397,"repoUrl":398,"updatedAt":489},"azure-ai-vision-imageanalysis-py","analyze images with Azure AI Vision","Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping. Use for computer vision and image understanding tasks.\nTriggers: \"image analysis\", \"computer vision\", \"OCR\", \"object detection\", \"ImageAnalysisClient\", \"image caption\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[481,482,485,488],{"name":392,"slug":393,"type":15},{"name":483,"slug":484,"type":15},"Computer Vision","computer-vision",{"name":486,"slug":487,"type":15},"Images","images",{"name":447,"slug":448,"type":15},"2026-07-18T05:14:18.007737",{"slug":491,"name":491,"fn":492,"description":493,"org":494,"tags":495,"stars":397,"repoUrl":398,"updatedAt":504},"azure-appconfiguration-java","manage configuration with Azure App Configuration","Azure App Configuration SDK for Java. Centralized application configuration management with key-value settings, feature flags, and snapshots.\nTriggers: \"ConfigurationClient java\", \"app configuration java\", \"feature flag java\", \"configuration setting java\", \"azure config java\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[496,497,500,503],{"name":392,"slug":393,"type":15},{"name":498,"slug":499,"type":15},"Configuration","configuration",{"name":501,"slug":502,"type":15},"Feature Flags","feature-flags",{"name":412,"slug":413,"type":15},"2026-07-03T16:32:01.278468",{"slug":506,"name":506,"fn":507,"description":508,"org":509,"tags":510,"stars":397,"repoUrl":398,"updatedAt":523},"azure-cosmos-rust","build applications with Azure Cosmos DB","Azure Cosmos DB library for Rust (NoSQL API). Document CRUD, containers, and globally distributed data.\nTriggers: \"cosmos db rust\", \"CosmosClient rust\", \"document crud rust\", \"NoSQL rust\", \"partition key rust\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[511,514,517,520],{"name":512,"slug":513,"type":15},"Cosmos DB","cosmos-db",{"name":515,"slug":516,"type":15},"Database","database",{"name":518,"slug":519,"type":15},"NoSQL","nosql",{"name":521,"slug":522,"type":15},"Rust","rust","2026-07-31T05:54:27.021432",{"slug":525,"name":525,"fn":507,"description":526,"org":527,"tags":528,"stars":397,"repoUrl":398,"updatedAt":536},"azure-cosmos-ts","Azure Cosmos DB JavaScript\u002FTypeScript SDK (@azure\u002Fcosmos) for data plane operations. Use for CRUD operations on documents, queries, bulk operations, and container management. Triggers: \"Cosmos DB\", \"@azure\u002Fcosmos\", \"CosmosClient\", \"document CRUD\", \"NoSQL queries\", \"bulk operations\", \"partition key\", \"container.items\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[529,530,531,532,533],{"name":512,"slug":513,"type":15},{"name":515,"slug":516,"type":15},{"name":9,"slug":8,"type":15},{"name":518,"slug":519,"type":15},{"name":534,"slug":535,"type":15},"TypeScript","typescript","2026-07-03T16:31:19.368382",{"slug":538,"name":538,"fn":539,"description":540,"org":541,"tags":542,"stars":397,"repoUrl":398,"updatedAt":548},"azure-data-tables-java","build table storage applications with Java","Build table storage applications with Azure Tables SDK for Java. Use when working with Azure Table Storage or Cosmos DB Table API for NoSQL key-value data, schemaless storage, or structured data at scale.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[543,544,545,546,547],{"name":392,"slug":393,"type":15},{"name":512,"slug":513,"type":15},{"name":515,"slug":516,"type":15},{"name":412,"slug":413,"type":15},{"name":518,"slug":519,"type":15},"2026-05-13T06:14:17.582229",267,{"items":551,"total":628},[552,566,573,586,596,613],{"slug":553,"name":553,"fn":554,"description":555,"org":556,"tags":557,"stars":23,"repoUrl":24,"updatedAt":565},"blob-reading","extract fields from blob URIs","Safe resolution of ci-blob:\u002F\u002F URIs — extract specific fields without dumping full payloads",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[558,561,564],{"name":559,"slug":560,"type":15},"Data Engineering","data-engineering",{"name":562,"slug":563,"type":15},"File Storage","file-storage",{"name":9,"slug":8,"type":15},"2026-07-07T06:52:39.196485",{"slug":4,"name":4,"fn":5,"description":6,"org":567,"tags":568,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[569,570,571,572],{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},{"slug":574,"name":574,"fn":575,"description":576,"org":577,"tags":578,"stars":23,"repoUrl":24,"updatedAt":585},"context-intelligence-graph-query","query context intelligence property graphs","Use when querying the context-intelligence property graph for session history, tool call traces, LLM iteration analysis, execution scale metrics, agent delegation trees, skill loading, and recipe orchestration. Covers all graph layers, cross-layer SOURCED_FROM joins, SST navigation, blob handling, and verified Cypher patterns.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[579,580,581,584],{"name":389,"slug":390,"type":15},{"name":17,"slug":18,"type":15},{"name":582,"slug":583,"type":15},"Graph Analysis","graph-analysis",{"name":9,"slug":8,"type":15},"2026-07-07T06:52:37.897652",{"slug":587,"name":587,"fn":588,"description":589,"org":590,"tags":591,"stars":23,"repoUrl":24,"updatedAt":595},"context-intelligence-session-navigation","navigate and extract session data","Use when extracting session data directly from JSONL files — the baseline path when the graph server is unavailable or when operating outside graph-analyst",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[592,593,594],{"name":389,"slug":390,"type":15},{"name":17,"slug":18,"type":15},{"name":9,"slug":8,"type":15},"2026-07-07T06:52:40.507052",{"slug":597,"name":597,"fn":598,"description":599,"org":600,"tags":601,"stars":23,"repoUrl":24,"updatedAt":612},"context-intelligence-session-reconstruction","reconstruct local Amplifier session files","Reconstruct local Amplifier session files from the context-intelligence graph server — events.jsonl, transcript.jsonl, and metadata.json",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[602,605,608,609],{"name":603,"slug":604,"type":15},"Amplifier","amplifier",{"name":606,"slug":607,"type":15},"Metadata","metadata",{"name":9,"slug":8,"type":15},{"name":610,"slug":611,"type":15},"Observability","observability","2026-07-03T16:31:03.605475",{"slug":614,"name":614,"fn":615,"description":616,"org":617,"tags":618,"stars":23,"repoUrl":24,"updatedAt":627},"workflow-pattern-analysis","analyze workflow success and failure patterns","Analyse failure and success patterns across many runs of a specific workflow using context-intelligence session data. Use when you want to answer: \"How is \u003Cworkflow> failing?\", \"What does a successful run look like vs a failing one?\", \"Which steps are the most common failure points?\", or \"What patterns appear consistently across sessions?\" Triggers on: workflow failure patterns, session failure analysis, compare successful and failing runs, what patterns appear across sessions, session behaviour investigation, how is the workflow failing, success patterns, failure signals, identify session signals.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[619,620,623,624],{"name":17,"slug":18,"type":15},{"name":621,"slug":622,"type":15},"Debugging","debugging",{"name":9,"slug":8,"type":15},{"name":625,"slug":626,"type":15},"Workflow Automation","workflow-automation","2026-07-07T06:52:43.061859",6]