Context Intelligence Eval Design

microsoft/amplifier-bundle-context-intelligence/skills/context-intelligence-eval-design

ai-mlResmi

Resmi Sağlayıcı Skill'iView repo

Use when designing evaluation scenarios for a context-intelligence tool signal — derives success criteria from domain-concepts.md and produces evaluation-scenarios.md entries and DTU profile templates.

Dosyalar1 dosya

SKILL.md138 satır

Loading editor…

Kurulum

Önerilen

Tek komut — ajanınız otomatik olarak devreye alır.

AI aracını seç

Kurulum komutunu görmek için yukarıdan bir AI aracı seçin.

veya

Manuel Kurulum

Daha fazla adım

Dosyayı indirin ve ajanınızın sistem istemine yapıştırın.

Skill detayları

Versiyonv1.0.0

YazarMicrosoft

Kategoriai-ml

Skill IDmicrosoft/amplifier-bundle-context-intelligence/skills/context-intelligence-eval-design

İlgili skill'ler

Blob ReadingSafe resolution of ci-blob:// URIs — extract specific fields without dumping full payloads Context Intelligence Evaluation MethodologyUse when deciding how to measure a context-intelligence tool signal — metric design across quality/efficiency/efficacy axes, artifact-metric avoidance via precursor measurement, A/B and statistical-N discipline, and test-data fidelity.Context Intelligence Graph QueryUse 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.Context Intelligence Session NavigationUse when extracting session data directly from JSONL files — the baseline path when the graph server is unavailable or when operating outside graph-analyst Context Intelligence Session ReconstructionReconstruct local Amplifier session files from the context-intelligence graph server — events.jsonl, transcript.jsonl, and metadata.json Context Intelligence Tool DesignUse when selecting a detection strategy and implementation primitive for a context-intelligence signal — classifies signals as deterministic/probabilistic/llm-evaluated/hybrid and applies the cheapest-sufficient-capability principle.