菜单
Deep research using ChatGPT + NotebookLM + domain knowledge — cross-model validation for high-quality answers and continuous improvement
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 | seldon-research |
| description | Deep research using ChatGPT + NotebookLM + domain knowledge — cross-model validation for high-quality answers and continuous improvement |
Combines ChatGPT (second opinion), NotebookLM (institutional memory), and GA domain knowledge to produce high-quality, validated answers. Every research interaction compounds back into the governance framework.
/seldon research [question] — full research pipeline
/seldon research quick [question] — fast answer without cross-model validation
1. Classify question (governance/experiential/domain)
↓
2. Check NotebookLM for existing knowledge
↓
3. Query GA domain skills if music-related
↓
4. Cross-validate with ChatGPT (GPT-4o-mini)
↓
5. Assess confidence via tetravalent logic
↓
6. Deliver answer with full agentic trace
↓
7. Compound: log interaction, update evolution, detect patterns
Determine knowledge layer:
Query the most relevant notebook:
mcp__notebooklm__ask_question({
question: "[processed question]",
notebook_id: "[best match]" // compound-the-compounding, probabilistic-grammars, etc.
})
If the notebook has relevant context, incorporate it into the answer with citations.
For music theory questions, invoke GA skills conceptually:
These produce deterministic answers (confidence 1.0).
For non-trivial questions, ask GPT-4o-mini to validate:
mcp__openai-chat__openai_chat({
model: "gpt-4o-mini",
messages: [
{ role: "system", content: "You are a music theory expert. Verify this answer is accurate. Be concise." },
{ role: "user", content: "[answer to validate]" }
]
})
Rate the answer:
Include full agentic trace showing which sources were used, which models validated, and confidence level.
Every research interaction feeds back:
personas/seldon.persona.yaml, policies/streeling-policy.yaml, policies/scientific-objectivity-policy.yaml (confidence calibration)