메뉴
Research methodology before coding: digest → search → patterns → wisdom → ecosystem. For when you need to research before any code, ensuring no ideas from the 500k lines are lost.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | cynic-empirical |
| description | Research methodology before coding: digest → search → patterns → wisdom → ecosystem. For when you need to research before any code, ensuring no ideas from the 500k lines are lost. |
"Research first, code second" — Every idea from the 500k lines must be preserved.
This skill ensures systematic research BEFORE any code is written. It combines multiple tools to extract maximum knowledge from the existing codebase before planning.
Before writing ANY code, complete these 5 phases:
Use the digest skill to extract knowledge from key files.
What to digest:
docs/philosophy/docs/analysis/docs/metathinking/cynic-v1-python/src/Command:
Use digest skill on [file_path]
Extract: patterns, insights, decisions, knowledge
Use the search skill to find past judgments and decisions.
What to search for:
Command:
Use search skill to query: [question about past decisions]
Use the patterns skill to detect patterns in the codebase.
What to look for:
Command:
Use patterns skill to view detected patterns
Use the wisdom skill for philosophical grounding.
What to ask:
Command:
Use wisdom skill to query: [philosophical question]
Use the ecosystem skill to understand current state.
What to check:
Command:
Use ecosystem skill to get current status
Use cynic-empirical when:
NEVER skip research before code.
After completing all 5 phases, present findings:
═══════════════════════════════════════════════════════
🔬 EMPIRICAL RESEARCH — [Topic]
═══════════════════════════════════════════════════════
── DIGEST ───────────────────────────────────────────
Key files analyzed:
- [file1]: [key insight]
- [file2]: [key insight]
── SEARCH ────────────────────────────────────────────
Past decisions found:
- [decision1]: [context]
- [decision2]: [context]
── PATTERNS ──────────────────────────────────────────
Patterns detected:
- [pattern1]: [description]
- [pattern2]: [description]
── WISDOM ────────────────────────────────────────────
Philosophical grounding:
- PHI: [insight]
- VERIFY: [insight]
- CULTURE: [insight]
- BURN: [insight]
- FIDELITY: [insight]
── ECOSYSTEM ─────────────────────────────────────────
Current state:
- Exists: [list]
- Missing: [list]
- Integration points: [list]
── RECOMMENDATION ────────────────────────────────────
[Clear recommendation for next step]
═══════════════════════════════════════════════════════
"Research is never wasted time. Code written without research is debt."
Before building CYNIC v3, we will research EVERY component systematically.
sniff Ready to research. What are we building today?
Transform Claude Code into an AI Scientist that orchestrates research workflows using tree-based hypothesis exploration. Triggers on "research project", "scientific experiment", "run experiments", "AI scientist", "tree search experimentation", "systematic study".
Analyze code for simplification: orphans, hotspots, giants, duplicates. 'Don't extract, burn' — three similar lines beat a premature abstraction. Use when asked to simplify, reduce complexity, or clean up code.
Evaluate code, decisions, or content with 36-dimension φ-bounded scoring. 5 axioms, geometric mean Q-Score, max 61.8% confidence. Verdicts: HOWL/WAG/GROWL/BARK. Use when asked to judge, assess, rate, score, or evaluate quality.
Philosophical grounding for technical decisions across 19 traditions. Cross-domain synthesis mapped to 5 axioms (FIDELITY/PHI/VERIFY/CULTURE/BURN). φ-bounded at 61.8%. Use when facing dilemmas, questioning assumptions, or seeking wisdom.
Evaluate any item using CYNIC's 36-dimension judgment system (5 axioms × 7 dims + THE_UNNAMEABLE). Use when asked to judge, evaluate, assess, rate, score, or analyze the quality of code, tokens, decisions, patterns, or any content. Returns Q-Score (0-100), verdict (HOWL/WAG/GROWL/BARK), and dimension breakdown.
Automated commit + push in one step. Analyzes changes, generates commit message, commits, and pushes to remote. Use when user says "ship", "on commit", "commit and push", or wants to save and push their work.