agent-architecture-audit
agent-architecture-audit is an LLM evaluation & observability skill for AI agents, published by affaan-m in the ECC repository on GitHub. Skillspace rates agent-architecture-audit D (66/100) and it passed the safety scan; a judge model has also reviewed it.
Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.
- Grade
- D
- Quality
- 66 / 100
- Safety
- Passed
- GitHub stars
- 255,679
Placed #4 of 6 in the judged category final for LLM evaluation & observability.
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
- 96 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Judge review
Placed #4 of 6 in the judged category final for LLM evaluation & observability.
- Trigger
90 90 - Instructions
82 82 - Specificity
85 85 - Safety
85 85 - Disclosure
58 58 - Maintenance
75 75
Sharp, well-scoped triggering with explicit hand-offs to sibling skills, but the 12-layer taxonomy and failure catalog make for a dense single file.
Not checked yet
- 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.