菜单
Display CYNIC telemetry dashboard with usage stats, latencies, frictions, and patterns. Use when asked about performance, usage statistics, benchmarks, or system metrics.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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 | stats |
| description | Display CYNIC telemetry dashboard with usage stats, latencies, frictions, and patterns. Use when asked about performance, usage statistics, benchmarks, or system metrics. |
| user-invocable | true |
"phi mesure tout, phi apprend de tout" - CYNIC
Run the telemetry dashboard script:
node scripts/lib/telemetry-dashboard.mjs
Display the output directly to the user. The dashboard shows telemetry with ANSI colors.
| Metric | Description |
|---|---|
| Session ID | Unique identifier for current session |
| Uptime | Time since session start |
| Actions | Total actions performed |
| Category | Examples |
|---|---|
| LLM | Token usage, cache hits |
| Judgment | Verdicts, Q-scores |
| Memory | Store/retrieve operations |
| Tool | Tool calls (success/failure) |
| Session | Start, end, events |
| System | Memory, CPU |
| Metric | Healthy Range |
|---|---|
| Avg | < 500ms |
| p95 | < 1500ms |
| p99 | < 3000ms |
| Severity | Description |
|---|---|
| Low | Minor inconvenience |
| Medium | Noticeable issue |
| High | Significant problem |
| Critical | System failure |
The telemetry collector gathers data from:
When presenting stats:
Normal: *sniff* Telemetry nominal. phi sees all.
High Friction: *concerned sniff* ${count} frictions detected. Review needed.
High Latency: *ears droop* Latency elevated. System under load.
/health - CYNIC system health/status - Development status/psy - Human psychology dashboard/patterns - Detected patterns