- name
SKILL.md
스킬 파일은 게시자의 저장소에 그대로 있습니다.
복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill debug-dashboard -a cursor -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill debug-dashboard -a claude-code -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill debug-dashboard -a codex -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill debug-dashboard -a grok -y복사한 메시지를 Grok Bot 채팅에 보냅니다. Bot이 GitHub에서 이 SKILL.md를 가져와 모든 Bot이 공유하는 스킬에 추가합니다.
Install this skill: https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/HEAD/.pi/skills/debug-dashboard게시자 제공
System-level debugging for the running pi-agent-dashboard. Three layers:
flowchart TD
L1["Layer 1 - Is the server alive?<br/>npx tsx ./scripts/health-probe.ts<br/>npx tsx ./scripts/tail-server-log.ts"]
L2["Layer 2 - Are the bridges connecting?<br/>npx tsx ./scripts/list-sessions.ts<br/>npx tsx ./scripts/tail-server-log.ts --errors"]
L3["Layer 3 - Is the UI rendering?<br/>(use the browser skill)"]
L1 --> L2 --> L3
npx tsx ./scripts/health-probe.ts # mode + uptime + version, or "not-running"
npx tsx ./scripts/tail-server-log.ts # last 50 lines of current run
npx tsx ./scripts/list-sessions.ts # connected pi sessions via REST
Scripts are TypeScript (cross-platform). All invocations use
npx tsxso they work on Linux, macOS, and Windows.tsxis already a project dep.
If health-probe says "not-running" → server isn't up. Check server.log for the most recent start banner ([bootstrap] ready ...) and what came after. The log appends with timestamped headers per start, so the last banner block is the relevant one.
Loader launch recipes: server → native register (platform/native-ts-register.mjs); jiti only for pi-hosted code. See node-inspect-debugger skill, Tier 2 / Tier 2b.
Full known-issue catalogue: references/known-issues.md.
Use the tee→grep pattern. Never rerun to inspect — capture once, grep forever:
npx tsx ./scripts/run-tests-triage.ts # all tests, tee to OS tmpdir, summarize failures
npx tsx ./scripts/run-tests-triage.ts packages/server # restrict to one package's vitest
npx tsx ./scripts/run-tests-triage.ts -t 'my test' # by test name
After it finishes, the log lives at:
/tmp/pi-test.log%TEMP%\pi-test.logYou can re-grep / re-read with custom patterns; the script prints the absolute path on each run.
Patterns + per-package vitest configs + watch mode are documented in references/test-failure-triage.md.
This skill stops at "the server says X but the UI shows Y". For visual debugging — verifying layouts, screenshotting, hunting console errors, testing responsive breakpoints — switch to the browser skill (shipped by the dashboard bridge extension to every session). Quick pointer: see references/ui-debug.md.
The live :8000 server runs MAIN-repo code — /api/restart never loads worktree edits, and a careless npm run build leaks into packages/client/dist (what live serves). To verify a UI/worktree change or serve a review mockup in full isolation (temp HOME, non-8000 ports, PI_DASHBOARD_NO_MDNS=1), see references/isolated-verification.md.
All log + config files. Worth bookmarking. See references/log-locations.md for the full map.
Before answering any "how do I X" / "why does Y happen" question:
grep -ni '<keyword>' docs/faq.md docs/*.md README.md
The FAQ already documents most recurring symptoms (Electron Node bin, Fastify crash range, tunnel watchdog, port conflicts). Reading source before grepping docs wastes tokens and risks wrong answers. Per AGENTS.md "STOP — Docs-First Gate".
browser — UI/visual issues, screenshots, console errors, responsive testing (Electron + web)implement — back to implementing once the bug is identifiedpi-dashboard — interact with the dashboard via REST (list sessions, send prompts, abort)ci-troubleshoot — when the problem only shows up in CIcode-review — review the fix before committingDiagnose problems in the running pi-agent-dashboard system: server.log, /api/health, bridge WebSocket connectivity, vitest triage, known-issue FAQ entries. Routes UI/visual issues to the browser skill
---name: debug-dashboarddescription: Diagnose problems in the running pi-agent-dashboard system: server.log, /api/health, bridge WebSocket…---# .pi/skills/debug-dashboard/SKILL.md개요
Diagnose problems in the running pi-agent-dashboard system: server.log, /api/health, bridge WebSocket connectivity, vitest triage, known-issue FAQ entries. Routes UI/visual issues to the browser skill. Use when the server seems hung, a pi session won''t connect, tests fail mysteriously, the dashboard shows a blank page, restart loops, port conflicts, or any "why isn''t X working" question.
FAQ
게시자에게서 .pi/skills/debug-dashboard/SKILL.md를 다운로드하거나 경로를 복사해 저장소를 엽니다. PlugMCP는 스킬을 목록에 올릴 뿐 파일을 호스팅하지 않습니다.
게시자가 https://github.com/BlackBeltTechnology/pi-agent-dashboard에서 관리합니다.
Claude, Cursor, Codex, Grok Build는 게시자의 저장소에서 추가한 SKILL.md를 읽을 수 있습니다. Grok Bot은 채팅에서 스킬의 GitHub 폴더 링크를 보내면 설치합니다.