Agent skill
council-thinkdeep
Use for deep multi-step investigation and analysis with both Codex and Gemini. Triggers on "council deep analysis", "investigate with council", "council thorough investigation", "have the council think deeply".
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/council-thinkdeep
SKILL.md
Council ThinkDeep Skill
Multi-step investigation and deep reasoning with both Codex (GPT-5.2) and Gemini using extra-high reasoning.
When to Use
- Complex problems requiring step-by-step analysis
- Architecture decisions
- Performance deep-dives
- Security analysis
- When user asks for "deep", "thorough", or "comprehensive" council analysis
Reasoning Level
xhigh (always - this skill is for deep analysis)
Execution
-
Understand the problem fully
-
Gather all relevant files and context
-
Formulate a structured prompt:
Investigate this step by step. Form hypotheses, test them, and build confidence. Question: <user's question> Context: <relevant file contents> Please: 1. Break down the problem 2. Form initial hypotheses 3. Analyze each hypothesis 4. Reach a well-reasoned conclusion -
Run BOTH commands in parallel:
Codex:
bashcodex exec --sandbox read-only -c model_reasoning_effort="xhigh" "<prompt>"Gemini:
bashgemini -s -y -o json "<prompt>" -
Synthesize the comprehensive analyses
Response Format
## AI Council Deep Analysis
### Codex (GPT-5.2) Analysis:
**Problem Breakdown:**
[Step-by-step analysis]
**Hypotheses Explored:**
[Each hypothesis and findings]
**Conclusion:**
[Final recommendation with confidence level]
---
### Gemini Analysis:
**Problem Breakdown:**
[Step-by-step analysis]
**Hypotheses Explored:**
[Each hypothesis and findings]
**Conclusion:**
[Final recommendation with confidence level]
---
### Council Synthesis:
**Shared Insights:** [What both models discovered]
**Unique Perspectives:** [Insights unique to each model]
**Combined Recommendation:** [Synthesized recommendation]
**Confidence:** [High/Medium/Low based on agreement]
---
*Session IDs: Codex=[id], Gemini=[id]*
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
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.
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.
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.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
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?