evolve-agent-skills
evolve-agent-skills is a Skill creation & templates skill for AI agents, published by eunomia-bpf in the agentsight repository on GitHub. Skillspace rates evolve-agent-skills D (67/100) and it passed the safety scan; the rating is based on static analysis only.
Analyze Codex, Claude, AgentSight, or other agent trajectories to find repeated failure modes and turn them into evidence-gated skill improvements. Use when the user asks why agents keep making the same mistakes, whether a skill should change, how to learn from many sessions, how to convert repeated workflows into skills, or how to design and validate a self-improving agent or skill library. Covers source-fidelity audits, workload stratification, correction and review-priming analysis, candidate skill patches, blind baseline-versus-candidate evaluation, promotion, rollback, and versioned learning. Do not use for ordinary one-off skill creation without trajectory evidence, standalone paper review, or prose editing.
- Grade
- D
- Quality
- 67 / 100
- Safety
- Passed
- GitHub stars
- 686
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 94 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Low-risk patterns
- License
- Not declared. Check the repository before reusing it.
What the scanner flagged
- mentions secrets in text
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.