Agent skill
aget-review-agent
Review agent health and conformance
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/aget-review-agent
SKILL.md
aget-review-agent
Review a specific agent's health, conformance, and recent activity. Produces assessment with recommendations.
Instructions
When this skill is invoked:
-
Verify Agent Exists
- Check fleet registry
- Confirm in supervisor's scope
- Note portfolio
-
Assess Health
- Version currency
- Configuration validity
- Dependency status
-
Check Conformance
- Conformance level (L0-L5)
- Gap identification
- Compliance issues
-
Review Activity
- Recent sessions
- Commits/changes
- Issues/blockers
-
Generate Recommendations
- Priority improvements
- Upgrade guidance
- Risk flags
Output Format
## Agent Review: [Agent Name]
### Overview
| Field | Value |
|-------|-------|
| Agent | [Name] |
| Portfolio | [Portfolio] |
| Archetype | [Type] |
| Version | [vX.Y.Z] |
| Review Date | [YYYY-MM-DD] |
---
### Health Assessment
| Check | Status | Notes |
|-------|--------|-------|
| Version Current | [Yes/No] | [Current: X, Latest: Y] |
| Config Valid | [Yes/No] | [Issue if any] |
| Dependencies | [OK/Issues] | [Details] |
**Health Score**: [Good/Fair/Poor]
---
### Conformance
| Level | Status | Gaps |
|-------|--------|------|
| L0 (Exists) | [Pass] | — |
| L1 (Structure) | [Pass/Fail] | [Gap] |
| L2 (Identity) | [Pass/Fail] | [Gap] |
| L3 (Session) | [Pass/Fail] | [Gap] |
| L4 (Evolution) | [Pass/Fail] | [Gap] |
| L5 (Governance) | [Pass/Fail] | [Gap] |
**Conformance Level**: L[N]
---
### Recent Activity
| Period | Sessions | Commits | Issues |
|--------|----------|---------|--------|
| Last 7 days | [N] | [N] | [N] |
| Last 30 days | [N] | [N] | [N] |
---
### Blockers
1. [Blocker description]
---
### Recommendations
| Priority | Recommendation | Effort |
|----------|----------------|--------|
| P1 | [High priority action] | [Low/Med/High] |
| P2 | [Medium priority action] | [Low/Med/High] |
Constraints
- C1: NEVER review agents outside supervisor's fleet — scope boundary enforcement
- C2: NEVER modify agent during review — review is read-only
- C3: NEVER expose sensitive agent configurations — security boundary respected
Related
- SKILL-036: aget-review-agent specification
- ONTOLOGY_supervisor.yaml: Agent_Registry, Agent_Status, Fleet_Audit concepts
- CAP-SUP-002: Agent Review capability
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?