菜单
Build or validate provider dry-run packets before any paid media provider call. Use when a storyboard, reference sheets, story contract, or visual packet needs to become a locked provider request with hashes, readiness checks, and explicit paid-call blocking.
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
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 | provider-packet |
| description | Build or validate provider dry-run packets before any paid media provider call. Use when a storyboard, reference sheets, story contract, or visual packet needs to become a locked provider request with hashes, readiness checks, and explicit paid-call blocking. |
| triggers | ["provider packet","provider-packet","kling prompt packet","dry-run provider request","final provider prompt"] |
| provides | ["provider-request-dry-run","referenced-artifacts-lock","readiness-receipt"] |
| composes | ["persona-dream","create-storyboard","contact-sheet"] |
| complies | ["best-practices-skills","best-practices-python"] |
| taxonomy | ["video","provider","receipt","fail-closed"] |
Validate or build the boundary between accepted storyboard/reference artifacts and a live media provider runner.
This skill is deliberately dry-run first. It must not upload files, create paid jobs, poll provider queues, download videos, or claim render acceptance.
Own:
final_kling_prompt.mdprovider_request_dry_run.jsonreferenced_artifacts.lock.jsonreadiness_receipt.jsonDo not own:
Validate an existing packet:
cd skills/provider-packet
./run.sh validate \
--packet-dir /mnt/storage12tb/skills/persona-dream/outputs/<run-id>/provider_packet \
--root /mnt/storage12tb/skills/persona-dream/outputs/<run-id>
The command writes:
provider_packet_validation_receipt.json
Automated acceptance requires:
provider_request_dry_run.json exists and uses schema
persona_dream.provider_request_dry_run.v1.referenced_artifacts.lock.json exists and every locked path exists.readiness_receipt.json exists.paid_call_performed is false.live_call_authorized is false.BLOCKED unless manual review receipts and paid approval
have been supplied by a separate workflow.Validating a dry-run packet is not live provider readiness. It is proof that the packet is inspectable and cannot accidentally perform a paid call.