agent-self-evaluation

    Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

    Rank#2753
    affaan-mgithubDomain expertise270,322Last updated Oct 3, 2026, 12:41 PMgithub/affaan-m/ecc/pi/core/skills/agent-self-evaluation
    Created
    9 months ago
    Last commit
    2 days ago
    Latest release
    v2.2.33 days ago

    Security Findings

    Package registry name mismatch

    SuspiciousLineage

    py name 'llm-abstraction' != repo 'ecc'

    Versions

    1
    • Scanned Oct 3, 2026, 12:41 PMLow