Context Intelligence Eval Design
microsoft/amplifier-bundle-context-intelligence/skills/context-intelligence-eval-design
ai-mlOfficial
Official Provider SkillView 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.
Files1 files
SKILL.md138 lines
Loading editor…
Install
RecommendedOne command — your agent picks it up automatically.
Select an AI agent above to see the install command.
or
Manual Install
More stepsDownload the file and paste it into your agent's system prompt.
Skill details
Versionv1.0.0
AuthorMicrosoft
Categoryai-ml
Skill IDmicrosoft/amplifier-bundle-context-intelligence/skills/context-intelligence-eval-design
Related skills
Blob ReadingSafe resolution of ci-blob:// URIs — extract specific fields without dumping full payloadsContext 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-analystContext Intelligence Session ReconstructionReconstruct local Amplifier session files from the context-intelligence graph server — events.jsonl, transcript.jsonl, and metadata.jsonContext 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.