一键导入
prime-radiant-control
Control Prime Radiant directly — send commands, add GIS pins/paths, open panels, navigate nodes, and validate state via HTTP API on port 5176.
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。
菜单
Control Prime Radiant directly — send commands, add GIS pins/paths, open panels, navigate nodes, and validate state via HTTP API on port 5176.
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
Use when a pull request needs review by a different AI model than the one that authored it, or when configuring cross-model code review pipelines in CI/CD.
Run Demerzel's autonomous driver — full cycle or individual phases across all repos
Capture meaningful session state (current cursor, in-flight work, live hypotheses, open questions, do-NOT-carry-forward, success criteria) to state/digests/latest.md so the next session — including one after auto-compaction — can re-enter without re-discovering context cold. Distinct from /learnings (which captures surprises). Validates against docs/contracts/digest-schema.json.
Autonomous research scheduler — selects the most under-researched department by coverage ratio, generates questions from completeness gaps, cross-model validates, auto-produces courses at T>=0.8, rate-limited to 6 cycles/day with kill switch
Personalized AI tutor — turns any topic into a customized, progress-tracked learning course. Use when the user wants to LEARN a concept, skill, language, tool, or domain. Creates a MISSION, curated RESOURCES, iterative lessons with self-checks, and learning-records that persist across sessions. NOT for interrogating the user about their own design (use brainstorming/IDSD for that).
Run one bounded supervised autonomous cycle on the Demerzel governance repo. Picks the smallest unchecked governance slice inside allow_edit, implements it, runs the oracle (`pwsh scripts/verify.ps1`), emits cycle evidence, and stops. Refuses to run unless dev-process-overseer reports loop-eligible and the preflight passes. Use when asked to "run one supervised loop", "advance governance autonomously", or "do one cycle and stop".
| name | prime-radiant-control |
| description | Control Prime Radiant directly — send commands, add GIS pins/paths, open panels, navigate nodes, and validate state via HTTP API on port 5176. |
Drive Prime Radiant programmatically from Claude. Send commands, query state, validate results — all via HTTP to the Vite dev server on localhost:5176.
/prime-radiant-control [action] [args...]
Examples:
/prime-radiant-control state — get current PR state
/prime-radiant-control panel gis — open the GIS panel
/prime-radiant-control gis:pins governance — add governance node pins preset
/prime-radiant-control gis:path NYC London — draw a path between two points
/prime-radiant-control validate — full state validation
http://localhost:5176 (the React Prime Radiant app)usePrControl hook active in ForceRadiant (auto-connected via SSE)All endpoints are on http://localhost:5176:
| Method | Path | Description |
|---|---|---|
POST | /pr/command | Send a command {action, params} |
GET | /pr/state | Read current PR state snapshot |
GET | /pr/result?id=CMD_ID | Check result of a specific command |
GET | /pr/events | SSE stream (React connects here) |
panel:open {panelId: "gis"|"godot"|"detail"|"activity"|...}panel:closegis:add-pin {planet: "earth", pin: {id, lat, lon, label, color?, icon?, pulse?}}gis:add-pins {planet: "earth", pins: [...]}gis:add-path {planet: "earth", path: {id, points: [{lat, lon}...], color?, animated?, dashed?}}gis:clear {planet: "earth"}gis:cluster {planet: "earth", enabled: true, radius?: 10}navigate:node {nodeId: "alignment-policy"}camera:fly {x, y, z, lookAt?: {x, y, z}, durationMs?: 1200} — fly camera to coordinatesdemerzel:emotion {emotion: "calm"|"concerned"|"thinking"|"pleased"|"alert"} — set facial expressiondemerzel:speaking {speaking: true|false} — toggle speaking jaw animationstate:report — returns full state in resultixql:exec {command: "SELECT * WHERE type = 'policy'"}Claude Vite Server React (ForceRadiant)
│ │ │
├─ POST /pr/command ───────►│ │
│ {action, params} ├─ SSE push ──────────────►│
│ │ ├─ execute action
│ │◄─ POST /pr/result ───────┤
│ │◄─ POST /pr/state ────────┤
│◄─ GET /pr/state ──────────┤ │
│ (validate) │ │
# 1. Send command
curl -s -X POST http://localhost:5176/pr/command \
-H 'Content-Type: application/json' \
-d '{"action":"gis:add-pin","params":{"planet":"earth","pin":{"id":"test","lat":40.7,"lon":-74,"label":"Test","pulse":true}}}'
# 2. Wait briefly for execution
sleep 1
# 3. Validate state
curl -s http://localhost:5176/pr/state | jq '.gis.earth.pins'
# Expected: 1
When this skill is invoked, follow these steps:
Check connectivity: curl -s http://localhost:5176/pr/state — if it fails, the Vite dev server isn't running.
Parse the user's intent into one or more commands from the supported actions list.
Send each command via POST /pr/command with {action, params}.
Wait 1 second for React to execute.
Validate by reading /pr/state and checking the expected changes occurred.
Report results to the user: what was sent, what state looks like now, whether it matches expectations.
For complex operations (multiple pins, paths, panel switches), batch commands sequentially with validation between each step.
# Open GIS panel
curl -sX POST localhost:5176/pr/command -H 'Content-Type: application/json' -d '{"action":"panel:open","params":{"panelId":"gis"}}'
# Add governance pins
curl -sX POST localhost:5176/pr/command -H 'Content-Type: application/json' -d '{"action":"gis:add-pins","params":{"planet":"earth","pins":[{"id":"d","lat":40.7,"lon":-74,"label":"Demerzel","icon":"🛡","color":"#FFD700","pulse":true},{"id":"ix","lat":37.4,"lon":-122,"label":"ix","icon":"⚙","color":"#73D117"}]}}'
# Draw path
curl -sX POST localhost:5176/pr/command -H 'Content-Type: application/json' -d '{"action":"gis:add-path","params":{"planet":"earth","path":{"id":"gp1","points":[{"lat":40.7,"lon":-74},{"lat":37.4,"lon":-122}],"color":"#FFD700","animated":true,"dashed":true}}}'
# Get state
curl -s localhost:5176/pr/state | python -m json.tool
# Navigate to node
curl -sX POST localhost:5176/pr/command -H 'Content-Type: application/json' -d '{"action":"navigate:node","params":{"nodeId":"alignment-policy"}}'
For full visual validation (command -> screenshot -> state check -> corrective loop), see validate.md.
The validation loop combines:
/pr/commandScreenshot tool/pr/stateUse this when you need to prove that Prime Radiant visuals match governance state -- not just trust the API response. Includes three worked scenarios (governance pins, clustering, node navigation) and a failure taxonomy.