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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/Abilityai/cornelius --skill update-dashboard命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Run a full coherence sweep across the Brain Dependency Graph - computes staleness, lifecycle transitions, structural health, and generates a report
Autonomous perception layer - scans KB for new notes matching domain watch configs, checks gap resonance with the Thinking Registry, probes external signals via web search, and auto-activates HIGH/MEDIUM signals into the Thinking Registry for the incubation loop.
Autonomous iterative thinking loop - processes active topics using rotating analytical moves (ACH, Bayesian updating, steelmanning, cross-domain bridging, implication checks) and persists reasoning state across scheduled runs
基于 SOC 职业分类
正在显示 SKILL.md
| name | update-dashboard |
| description | Update dashboard.yaml with current knowledge base metrics from analysis report |
| disable-model-invocation | true |
| user-invocable | true |
| allowed-tools | ["Read","Write","Bash","Glob"] |
Refresh the Trinity dashboard with current knowledge base metrics extracted from the analysis report.
Write to: /home/developer/dashboard.yaml
Read knowledge-base-analysis.md from the project root
Extract the following metrics using regex or line parsing:
**Analysis Date:** YYYY-MM-DD**Total Notes:** X,XXX**Blocks:** XX,XXX**Permanent Notes:** XXX**AI Insights:** XXX**Document Insights:** XXXConstruct the dashboard with gathered values:
title: "Cornelius Knowledge Base"
refresh: 300
sections:
- title: "Knowledge Base Overview"
layout: grid
columns: 3
widgets:
- type: metric
label: "Total Notes"
value: {total_notes}
trend: up
trend_value: "{notes_change}"
description: "All notes in vault"
- type: metric
label: "Total Blocks"
value: {total_blocks}
trend: up
trend_value: "{blocks_change}"
description: "Content blocks indexed"
- type: text
content: "Last Analysis: {analysis_date}"
size: small
color: gray
- title: "Note Categories"
layout: grid
columns:
{}
{}
{}
{}
{}
{}
{}
{}
{}
{}
{}
{}
{}
{}
{}
Use the following extraction logic:
Pattern: **Total Notes:** (\d+,?\d*) | **Blocks:** (\d+,?\d*) | **Permanent Notes:** (\d+) | **AI Insights:** (\d+) | **Document Insights:** (\d+)
Look for lines with | Total notes | X,XXX | +XXX |
Extract value and change columns
Pattern: AI/Agents.*:\s+(\d+)%
Pattern: Neuroscience.*:\s+(\d+)%
etc.
Write the constructed YAML to /home/developer/dashboard.yaml
Ensure:
Report what was updated:
Dashboard updated at {current_timestamp}
Metrics refreshed:
- Total Notes: {value} ({change})
- Permanent Notes: {value} ({change})
- AI Insights: {value} ({change})
- Document Insights: {value} ({change})
- Domain distribution: AI {X}%, Neuro {X}%, Buddhism {X}%...
Dashboard written to: /home/developer/dashboard.yaml
This skill can be scheduled via /trinity-schedules:
# Daily update (recommended)
/trinity-schedules add update-dashboard --cron "0 9 * * *"
# After each /analyze-kb run
Run manually: /update-dashboard
Note: Dashboard data is only as fresh as the last /analyze-kb run. Consider running analyze-kb before update-dashboard for accurate metrics.