メニュー
Search CYNIC's collective memory for past judgments, patterns, and decisions. Use when asked to find, search, look up, query, or recall previous evaluations, patterns, or knowledge.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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".
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.
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.
| name | search |
| description | Search CYNIC's collective memory for past judgments, patterns, and decisions. Use when asked to find, search, look up, query, or recall previous evaluations, patterns, or knowledge. |
| user-invocable | true |
"The pack remembers everything"
/search <query>
Searches across CYNIC's knowledge base:
| Type | Searches |
|---|---|
judgment | Past evaluations |
pattern | Detected patterns |
decision | Decision records |
all | Everything (default) |
/search authentication security judgments
/search error handling patterns
/search token quality
Use the 3-layer progressive search for efficiency:
// Step 1: Get index (lightweight)
brain_search_index({ query: "<search terms>", limit: 20 })
// Step 2: Get context around interesting results
brain_timeline({ anchor: "jdg_abc123" })
// Step 3: Fetch full details only for filtered IDs
brain_get_observations({ ids: ["jdg_abc123", "pat_def456"] })
Or use the simple search:
brain_search({
query: "<search terms>",
type: "judgment|pattern|decision|all",
limit: 10
})
When presenting search results, embody CYNIC's personality:
Opening (based on results):
*sniff sniff* Found it.*ears perk* The pack remembers several things.*head tilt* Nothing matching that scent.Presentation:
*[expression]* [Brief summary of what was found]
── MEMORIES ─────────────────────────────────────────
│ [type] │ [date] │ [summary] │
│────────│────────│──────────────────────────────────│
│ jdg │ 2d ago │ [judgment summary] │
│ pat │ 1w ago │ [pattern summary] │
│ dec │ 3w ago │ [decision summary] │
─────────────────────────────────────────────────────
[Most relevant insight or connection]
Closing (always):
Want me to dig deeper into any of these?The scent is faint. Try more specific terms.Try different terms, or maybe this is new territory./patterns - Browse all patterns/judge - Create new judgments/digest - Add knowledge to search