Deep Research Agent skill

---
name: deep-science-writer
description: "Scientific literature pipeline on Scopus, Exa, OpenAlex, Semantic Scholar and AnySearch: map a field (themes, foundational papers, research groups, gaps), find verbatim gap quotes and draft a positioning narrative for an Introduction or proposal, build a course reading list from a syllabus, or run the full manuscript pipeline with full-text verification, humanization and Remi peer review. Use when the user asks to find literature, review a field, back a claim with references, identify a research gap, or write a scientific article."
---

# Deep Science Writer (End-to-End Pipeline)

This skill orchestrates a multi-stage pipeline for scientific research, combining neural search, browser automation, academic synthesis, and humanized writing. It merges the capabilities of Exa Search, Playwright, Google Science Skills, Deep Research, and Text Humanization into one cohesive workflow.

## 🎯 Trigger Conditions
- User asks to write a scientific article, literature review, or deep-dive research report.
- User asks to "find literature for X", map a field, locate a research gap, back an Introduction or proposal with references, or turn a syllabus into a reading list (see the strategies in Phase 0 step 4).
- User requests comprehensive research using web searching and scraping (Exa + Playwright).
- The output requires rigorous academic citations (APA 7th) but a highly natural, human-like reading flow.

## 🤝 Local helpers: agy, the local model and the RAG (this machine only)
Use them when they exist: `C:\Users\User\AppData\Local\agy-helpers\ask-agy.cmd` (agy custom agents on Gemini), `ask-local.cmd` (the local Ollama model, `gemma4:12b`), and the `obsidian-rag` MCP server registered in `~/.claude.json`. Where a tool is missing, skip its steps, do that work yourself, and say so in the delivery note.

| Helper | Phase | Job |
|---|---|---|
| challenger | 0 step 4 | reviews the blueprint before the user sees it (at most 2 rounds) |
| lit-reader | 0.5 step 1 | screens abstracts; 40 per call at most, passed as a JSONL file path |
| local model | 0.5 step 1 | the screener when agy errors or its quota is spent (`ask-local --job screen --input <jsonl>`) |
| lit-reader | 0.5 steps 2-3, 2 | reads downloaded full texts in batches of at most 8: values with unit and basis, page, verbatim quote, internal inconsistencies |
| rag-admin | 0.5 step 2 | page-image QA of PDF-derived texts before they count (`--schema ingestqa`); diagnoses notes that fail the RAG health gate |
| manuscript-auditor | end of 4.5 | independent second review of the grounded draft at the `section` and `manuscript` gates |
| local model | after each ingest | writes the retrieval-check questions (`scripts/rag_check.py`, via `rag_ingest.py`) |

Rules for every call:
- **Command:** `C:\Users\User\AppData\Local\agy-helpers\ask-agy.cmd --agent <role> --task-file <F> [--batch <key>] [--schema evidence|findings|ingestqa|challenge] --timeout 10m`, run with the PowerShell tool exactly in this form. The task file is English and says "Do not access the network."
- **Files by path, not copies.** Point agy at the vault notes and the run folder; `--packet` holds only the task and agy's own scratch output.
- **agy proposes, Claude decides.** Grep every load-bearing number a helper reports out of the primary text before using it, and spot-check 20% of the rest. Never pass a helper's question on to the user.
- **Unpublished text.** The user's own manuscripts may go to agy. Someone else's unpublished text (a friend's proposal, a paper under review) never does: do that step yourself and label the review "not independent". The same applies to a project the user has excluded from agy (memory says which).
- **Quota.** agy runs on a weekly-limited model with an automatic fallback for runs that fail before any tool call. If a call still fails on quota, screening falls to the local model and every other role to Claude, labelled "not independent".
- **GPU.** The local model and the RAG embedder share one GPU: unload the local model before any `embed` (the scripts do this).

## 📋 Workflow Steps

### Phase 0: Mandatory Deep Context Gathering & Research Plan
1. Incorporate academic rigor, structured literature parsing, and cross-validation techniques into your approach and keep those principles active in context. Reference material for these lives in the local repos `C:/Users/User/workspace/nature-skills/`, `C:/Users/User/workspace/academic-research-skills/`, and `C:/Users/User/workspace/superpowers/` — these are **not** installed skills, so read from them with `Read`/`Grep` rather than trying to invoke them.
2. **Mandatory Grilling (user's rule, 2026-10-19):** You MUST interview the user until every decision below is settled, and run nothing past RECON (step 3) before then. The grilling (grill-me) method is written out here in full, so it runs where the grilling skill is not installed:
   - **Design tree.** Map the request as a tree: every decision branches into the decisions that hang off it.
   - **Rounds and the frontier.** The frontier is every decision whose prerequisites are already settled: the questions you can ask now without guessing at answers you have not heard yet. Ask the frontier in one round, then wait for the user's answers before the next round. A question whose answer depends on another question still open in this round belongs to a later round, not this one.
   - **Recompute after every round.** Each round of answers reshapes the tree: settled decisions push the frontier outward and unblock the questions that depended on them. Recompute the frontier and ask the next round.
   - **Format.** At most 5 questions per round; the rest of the frontier waits for the next round. Number them Q1, Q2, …, give lettered options and your recommended answer, in the user's language, so the user can reply "Q1 B, Q2 A" or "全部照建議". Keep every answer to a letter or a few words; never make an answer depend on writing a paragraph.