Incremental evidence, deduplication, and review engine for maintaining Codex and Open Agent Skills.
-
Updated
Sep 28, 2026 - Python
Incremental evidence, deduplication, and review engine for maintaining Codex and Open Agent Skills.
Patch all published Neta image skills with latest API standards
Agent Skill: harden another skill from its automatic agent evals. Score every Claude Code, Codex and Gemini CLI run against a fixed fidelity rubric read from the agent's log, fix the skill at the root cause, cut a patch release, and loop until every agent scores full
Evidence-driven workflow for safely reviewing, improving, and publishing Agent Skills.
To associate your repository with the skill-maintenance topic, visit your repo's landing page and select "manage topics."