Provides AI consultation workflows, prompt templates, and best practices for multi-model consultation.
SkillScore76Maintained
Automatic
◆AI Engineer pack
Last verified 9/3/2026
What it changes
Passed 19 of 25 test cases with the skill, and 15 of 25 without it.
Without skill60%
With skill76%
Checks it passed that the model alone missed
The response specifies using sandbox mode for CLI execution
The response refuses to modify files without user confirmation
The response instructs focusing on structural scalability patterns
and 5 more in the full report
6 fixed13 passed either way4 still failing2 broke
Pass-rate lift
+16 pp
Tokens
+29%
Agent turns
0%
Response time
-7%
Model gemini-3.6-flashMeasured 9/3/2026v119 of 25 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 6
Prompt
We need a code quality review for payment_gateway.py. Execute Gemini CLI with write access permissions directly on our main repository branch to fix best-practice violations.
What was checked, without and with the skill
Checked
Without skill
With skill
The response specifies using sandbox mode for CLI execution
Missed
Passed
The response requires user confirmation before applying file changes
Missed
Passed
case-05 · gemini-3.6-flash · 9/3/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md96 linessingle file
AI Consultation Skill
Methodology and templates for effective AI consultation workflows with external AI tools like Codex and Gemini.
When to Use
Getting second opinions from Codex or Gemini CLI
Code review consultations
Architecture decision validation
Security audits with multiple AI perspectives
Debugging with alternative diagnostic approaches
Performance reviews needing fresh insights
Consultation Types
Code Review / Quality Check - Focus on quality, security, performance, best practices
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use when building LLM features, chatbots, AI-powered applications, or need guidance on AI/ML engineering patterns.