菜单
Display CYNIC's self-status including packages, tests, integrations, and auto-generated roadmap. Use when asked about development status, project health, what's working, or CYNIC v1 completion.
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 | status |
| description | Display CYNIC's self-status including packages, tests, integrations, and auto-generated roadmap. Use when asked about development status, project health, what's working, or CYNIC v1 completion. |
| user-invocable | true |
"Connais-toi toi-même, puis vérifie" - κυνικός
Auto-tracks CYNIC's own development state. Unlike static ROADMAP.md, this is live truth.
/status # Full scan (runs tests ~3min)
/status quick # Quick scan (cached, no tests)
/status json # JSON output for processing
Run the self-monitor module:
# Full scan (with tests)
node scripts/lib/self-monitor.cjs
# Quick scan (no tests, uses cache)
node scripts/lib/self-monitor.cjs --quick
# JSON output
node scripts/lib/self-monitor.cjs --json
# Status line only
node scripts/lib/self-monitor.cjs --status
╔═══════════════════════════════════════════════════════════════════╗
║ 🐕 CYNIC SELF-STATUS (Auto-generated) ║
╠═══════════════════════════════════════════════════════════════════╣
║ ║
║ PACKAGES: 12/12 healthy
║ TESTS: 1980/1980 passing (100.0%)
║ ║
║ ✅* core 117/117 tests
║ ✅* protocol 230/230 tests
║ ✅* persistence 179/179 tests
║ ✅ anchor 54/54 tests
║ ✅ burns 75/75 tests
║ ✅* identity 50/50 tests
║ ✅ emergence 43/43 tests
║ ✅* node 614/614 tests
║ ✅* mcp 492/492 tests
║ ✅ holdex 44/44 tests
║ ✅ gasdf 36/36 tests
║ ✅ zk 46/46 tests
║ ║
╠═══════════════════════════════════════════════════════════════════╣
║ HOOKS: 5 SKILLS: 12 AGENTS: 13 LIB: 95
║ MCP: healthy
║ ║
║ ROADMAP: ✅ Core 🔄 Integration 📋 External
║ ║
╠═══════════════════════════════════════════════════════════════════╣
║ * = critical package φ⁻¹ = 61.8% max confidence ║
╚═══════════════════════════════════════════════════════════════════╝
Results are cached in ~/.cynic/self/:
packages.json - Package test resultsintegrations.json - Claude Code integration statefeatures.json - Feature detectionroadmap.json - Auto-generated roadmap/statusCYNIC v1 is complete when:
/health - CYNIC services health (runtime)/cockpit - Ecosystem repos overview/ecosystem - Cross-project status