kayba-ai/agentic-context-engine
9 skills · 1 total installs
$npx skills add kayba-ai/agentic-context-engineSkillInstalls
kayba-pipelineEnd-to-end agent evaluation and improvement pipeline. Takes a traces folder and optional HITL flag, then orchestrates sub-agents through 7 stages — each stage…kayba-aceThis skill ships learnfromtraces.py, a script that reads OpenClaw session transcripts, feeds them through the ACE learning pipeline, and writes an updated…stage-1-api-analysisFetch pre-computed insights from the Kayba API and build a structured summary.stage-2-domain-contextGather domain context about the repository and agent — system prompt, tool definitions, domain docs, and behavior patterns from traces.stage-3-metricsDefine metrics from Kayba insights, implement them as Python measurement code, run against traces, and iterate until the metrics are clean and meaningful.stage-4-rubricOrganize computed metrics into a tiered evaluation rubric with leading, lagging, and quality indicators.stage-5-action-planTriage each insight into discard/code-fix/prompt-fix and produce a prioritized action plan with specific recommendations.stage-6-hitlHuman-In-The-Loop gate that presents the action plan with full context, collects an informed approval/modification/rejection decision, and records the outcome.stage-7-fixerImplement the approved fixes from the action plan and log all changes.