Query MemoryGraph session-metrics and haiku-eval entries to compile performance data.
npx skills add https://github.com/ste-bah/archon --skill self-assess
Please help me install this Agent Skill. Skill: self-assess Source: https://github.com/ste-bah/archon/tree/main/.claude/skills/self-assess Command: npx skills add https://github.com/ste-bah/archon --skill self-assess
Archon aggregates and interprets performance metrics from MemoryGraph to provide actionable insights about corrections, cost, pattern compliance, and blind spots in a read-only context.
Run /self-assess to generate Archon performance insights from MemoryGraph.
High-intent search queries and answers about installing and using this skill.
You can assess performance by querying MemoryGraph for session-metrics and haiku-eval entries to compute trend directions for corrections, cost per day, and pattern compliance. This generates a structured read-only self-assessment report identifying blind spots for operational review.
A self-assessment report compiles aggregated performance metrics, such as corrections and pattern compliance, from MemoryGraph to identify blind spots and external evaluations. It provides decision-makers with actionable insights into operational health without modifying stored memories.
Compute cost per day and pattern compliance by querying MemoryGraph for session-metrics entries. The system aggregates this performance data across sessions to calculate trend directions, returning a formatted read-only report for administrators reviewing operational health.
The performance evaluation process does not modify stored memories in MemoryGraph. It is a strictly read-only operation that queries session-metrics and haiku-eval entries to generate a formatted self-assessment report while preserving data integrity.
You need to run a self-assessment after a sprint or operational cycle to review memory utilization, accuracy, and overall performance trends. It queries MemoryGraph to identify blind spots and pattern compliance issues for decision-makers evaluating operational health.
dogearedCollect navigation timing metrics and resource usage to benchmark web application performance.
bluegitterDiagnose an AI Agent's MBTI personality type and generate a comparative report.
8GG-GitGenerate and refine company-specific data analysis skills from analyst knowledge.
netanel-abergelLog skill invocations and generate daily and weekly usage summaries.
