Context Intelligence Evaluation Methodology
microsoft/amplifier-bundle-context-intelligence/skills/context-intelligence-evaluation-methodology
analysisOfficial
Official Provider SkillView repo
Use when deciding how to measure a context-intelligence tool signal. Covers metric design across quality/efficiency/efficacy axes, artifact-metric avoidance via precursor measurement, A/B and statistical-N discipline, and test-data fidelity.
Files1 files
SKILL.md62 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
Categoryanalysis
Skill IDmicrosoft/amplifier-bundle-context-intelligence/skills/context-intelligence-evaluation-methodology
Related skills
Context Intelligence Derived MetricsUse when a graph query returns structurally-identical rows hiding different intent — many delegations all "none/conversation", look-alike sessions, identical tool calls. Derives an INTERPRETIVE metric by joining a second graph layer onto the blanket shape (flagship: transport × sub-session skill payload = "flavour"). Complements graph-query (READ the graph) by making blanket reads MEAN something.Context Intelligence Eval DesignUse when designing evaluation scenarios for a context-intelligence tool signal. Derives success criteria from domain-concepts.md and produces evaluation-scenarios.md entries plus DTU profile templates.Context Intelligence GdsUse when about to write naive Cypher for a graph-topology question — pathfinding, reachability, centrality/influence, community/clustering, structural similarity, or similar event paths/trajectories (with/without time) — reach for Neo4j GDS or APOC instead of hand-rolling traversals one hop at a time. WHEN/WHY layer; graph-query's "Push Work to the Database" section is the HOW.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 Hill ClimbingUse when an investigation needs more than one step — track it in todo as a hill climb so progress and dead leads leave an audit trail. Governs HOW you track the climb, not how you query or extract — that stays in graph-query / session-navigation.Context Intelligence Server Data OpsExact step order, wording, and the "session details" block format for the delete flows the server-data-ops agent drives — delete the current session, clean up every session from the current working directory, find-then-delete a session by description, and delete a session someone else created.