crucix-intelligence-dashboard — Claude Code skill: OSINT dashboard
A skill that walks your agent through setting up Crucix: a self-hosted terminal with 27 open data feeds, Telegram and Discord bots, and LLM-written analysis.
npx skills add reason-machines/trending-skills --skill crucix-intelligence-dashboard -a claude-codeWhat crucix-intelligence-dashboard does
The skill takes the agent through a Crucix install: clone the repo, pull dependencies, fill .env with source keys, start the server on http://localhost:3117. Every 15 minutes the project queries 27 open feeds, including satellite fire detections, flight tracking, radiation, conflict events, market prices and maritime AIS, then draws them on a WebGL globe. Alerts land in Telegram or Discord and an LLM writes the analysis.
Node.js 22+ is the only hard requirement, since the code relies on native fetch and ESM. Keys for FRED, FIRMS and EIA widen coverage considerably; everything else is optional. Pick a provider in LLM_PROVIDER — anthropic, openai, gemini or codex. The codex route skips the API key but needs a one-time npx @openai/codex login. LLM trouble is not fatal: alert scoring falls back to rules and the sweep keeps running.
Discord has two modes. With discord.js installed you get slash commands and rich embeds. Without it Crucix only posts through DISCORD_WEBHOOK_URL. If npm run dev exits without a word, run node server.mjs directly, or run node diag.mjs to check the Node version, imports and port availability.
What it helps with
- run a local OSINT dashboard with a 3D globe
- push Telegram alerts for events that cross a threshold
- watch many public feeds in one place
- hook an LLM up to the delta between sweeps
- use Discord webhook alerts without a full bot
Example prompts for the agent
- Set up Crucix from the skill and bring the dashboard up at
http://localhost:3117 - Put
FIRMS_MAP_KEYandFRED_API_KEYinto.env, then start it withnpm run dev - Wire the Telegram bot with
TELEGRAM_BOT_TOKENandTELEGRAM_CHAT_ID, then check/status
How to install crucix-intelligence-dashboard
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill crucix-intelligence-dashboard -a claude-code2Manually: put the files in place
~/.claude/skills/crucix-intelligence-dashboard/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/crucix-intelligence-dashboard/
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill crucix-intelligence-dashboard -a codex2Manually: put the files in place
.agents/skills/crucix-intelligence-dashboard/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill crucix-intelligence-dashboard -a cursor2Manually: put the files in place
.cursor/skills/crucix-intelligence-dashboard/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/trending-skills crucix-intelligence-dashboard2Manually: put the files in place
.github/skills/crucix-intelligence-dashboard/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill crucix-intelligence-dashboard -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/trending-skills --path skills/crucix-intelligence-dashboardManually: put the files in place
.devin/skills/crucix-intelligence-dashboard/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill crucix-intelligence-dashboard -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about crucix-intelligence-dashboard
How do I install crucix-intelligence-dashboard in Claude Code?
Run npx skills add reason-machines/trending-skills --skill crucix-intelligence-dashboard -a claude-code. The file then sits at ~/.claude/skills/crucix-intelligence-dashboard/SKILL.md.
What does crucix-intelligence-dashboard do?
It guides an agent through deploying the Crucix terminal: 27 open feeds, a WebGL globe, Telegram and Discord alerts, plus LLM analysis of each sweep.
What does the dashboard need to run?
Node.js 22+. FRED, FIRMS and EIA keys improve data coverage, and the LLM step needs a provider with a key unless you use codex.