skill-system-research-inbox

Skill System Research Inbox

Queue deep research prompts for Arthur/Oracle to run in ChatGPT Pro Deep Research.

Rule

If a question needs broad survey work, multi-hop source synthesis, literature review, or more than about 20 minutes of agent web searching, write a prompt into:

/share/nas165/arthur0824hao/Work/.tkt/research-inbox/inbox/queued/

This is the free external research lane. It saves live agent tokens and money, but it uses Oracle attention, so do not spam.

Quick Start

python3 Project/skills/skills/skill-system-research-inbox/scripts/research_queue.py queue \
  --title "Agent memory consolidation survey" \
  --requested-by lark \
  --for "BH-CNS Dream B-bhcns-08" \
  --prompt-file /tmp/deep-research-prompt.md \
  --json

python3 Project/skills/skills/skill-system-research-inbox/scripts/research_queue.py list --json

Prompt Contract

Each queued prompt must include:

• Context: what decision, paper, bundle, or organ design it feeds.
• Task: numbered sub-questions.
• Constraints: preferred sources, excluded sources, citation format.
• Output schema: markdown structure for the answer.
• Counter-evidence: critiques, failure modes, or explicit no-findings statement.
• Success criteria: what makes the result usable.
• Not in scope: what the research must not wander into.

Lark Cortex Use

Lark may queue prompts while doing external-search / system-evolution work. The queue is not dispatch and not progress by itself. It is a durable request for Oracle-mediated deep research.

{
  "schema_version": "2.0",
  "id": "skill-system-research-inbox",
  "version": "0.1.0",
  "capabilities": [
    "research-queue",
    "gpt-pro-deepresearch-prompt",
    "external-survey-queue"
  ],
  "effects": ["fs.read", "fs.write"],
  "operations": {
    "queue": {
      "description": "Write a structured GPT Pro Deep Research prompt into the research inbox queued directory.",
      "input": {
        "title": {"type": "string", "required": true, "description": "Prompt title."},
        "prompt": {"type": "string", "required": false, "description": "Prompt body; can be supplied by --prompt-file or stdin."},
        "requested_by": {"type": "string", "required": false, "description": "Requesting agent."},
        "for": {"type": "string", "required": false, "description": "Target decision, bundle, paper, or organ design."},
        "priority": {"type": "string", "required": false, "description": "low, normal, high, or urgent."}
      },
      "output": {
        "description": "Queued prompt path and paste-back target.",
        "fields": {"status": "string", "path": "string", "result_path": "string", "id": "string"}
      },
      "entrypoints": {
        "unix": ["python3", "scripts/research_queue.py", "queue", "--title", "...", "--prompt-file", "...", "--json"]
      }
    },
    "list": {
      "description": "List queued deep research prompts.",
      "input": {
        "status": {"type": "string", "required": false, "description": "queued, processed, outbox, or all."}
      },
      "output": {
        "description": "Research prompt entries.",
        "fields": {"status": "string", "entry_count": "integer", "entries": "array"}
      },
      "entrypoints": {
        "unix": ["python3", "scripts/research_queue.py", "list", "--json"]
      }
    }
  }
}