メニュー
Launch and validate canonical UX Lab adapters and shared UI owned by agent-skills.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Create receipt-backed persona dream packets from memory residue. Use when a persona should dream, reflect, or turn recent memories into persona insight; when create-movie/dream.py feels too heavy for the goal; when the desired output is a prompt, frame prompts, contact sheet, reflection, and memory write receipt rather than a full movie; or when a downstream movie workflow needs a dream_packet.json input.
Use when the user asks to query project memory, ask an oracle, use supported browser-backed reviewers, run Tau roundtable/single-handler workflows, run persona/deep-review workflows, generate image prompts, check OS/project health through composed skills, or run an ask DAG. This skill is the executable /ask runtime; do not replace it with an informal subagent, plain web search, or hand-written review.
Build structured evidence cases using Claims-Arguments-Evidence (CAE) trees. AGENT-DRIVEN composable orchestrator: the agent decomposes the question, calls existing skills for data collection and verification, then DECIDES the verdict. Python runner.py is a thin data collector and persistence layer.
Monitor Herdr-visible Codex/Claude agent panes for stalled, blocked, unknown, or confused state, then ask each stalled agent whether it needs human intervention or can self-unblock with brave-search or webgpt.
Internal Tau-owned LLM proxy on localhost:4001. Surfaces: chat/batch completions, scillm exec, OpenCode serve (coding delegate), OpenCode transport (DAG/SSE), standing Codex agents. Chutes, Gemini, Claude/Codex OAuth, OpenCode Go, Ollama. Auto-routes by model name. ZIP/PDF, JSON repair, batch pools. Project agents must not call this skill directly unless the human explicitly asks to operate SciLLM or the work is Tau/SciLLM maintenance.
Operate and verify the local T'au project at ${HOME}/workspace/experiments/tau. Use for Tau loop, harness, watchdog cron, GitHub issue orchestration, TUI, Memory-first chat, and E2E proof/status tasks. This skill is a light wrapper around the Tau repo and must report mocked/live proof boundaries explicitly.
| name | ux-lab |
| description | Launch and validate canonical UX Lab adapters and shared UI owned by agent-skills. |
| allowed-tools | Bash, Read |
Canonical UX Lab shared UI source is agent-skills/skills/ux-lab/ui.
Canonical UX Lab project housing is agent-skills/skills/ux-lab/projects.v1.json.
UX Lab is a light multi-project wrapper: it discovers project surfaces, serves
a small project hub, and delegates runtime ownership to each project.
Canonical Sparta Explorer source and runtime ownership remains
experiments/sparta/explorer. Canonical Tau DAG viewer source and runtime
ownership remains experiments/tau.
Canonical Persona Dream source and runtime ownership remains
agent-skills/skills/persona-dream. UX Lab must list Persona Dream as a
first-class project even when the legacy http://127.0.0.1:3002/#dream route
is not mounted by the currently running project app.
For Tau DAG viewing, this skill is a launcher and capability-check wrapper only. It contains no Tau DAG React application, DAG schemas, journal reader, or state reducer.
./run.sh or ./run.sh serve./run.sh list./run.sh url persona-dream hub./run.sh status./run.sh start-project sparta-explorer./run.sh tau-dag-view --run-dir /path/to/run./sanity.shcd ui && npm ci && npm run typecheckhttp://127.0.0.1:3002/http://127.0.0.1:3002/?project=persona-dreamhttp://127.0.0.1:3002/#sparta-explorer/threat-matrixhttp://127.0.0.1:3001/api/f36/explorer-projectionThe Tau wrapper validates tau.dag_viewer_capabilities.v1 with
read_only: true, then delegates unchanged to tau dag-view. Any discrepancy
is resolved in favor of Tau's emitted contracts.