Literature Survey

Literature Survey

Overview

End-to-end literature survey builder. Single stage, full quality from the start. The agent (Claude Code / Cursor / Aider / Codex / …) does the entire build using its own tools (WebFetch, WebSearch, Write, Bash). This SKILL is procedure + reference playbooks + LaTeX template — no Python runtime, no LLM SDK.

The substantive work is decomposed into reference playbooks under references/:

Read the relevant reference before writing, not after. The full pass does not fit in a single turn — references/00-incremental-execution.md is the only execution mode that completes.

When to Use

• User asks for a "survey" / "review" on a specific topic.
• User has a research topic and wants a structured map of the field with citations.
• User needs background reading curated for a thesis chapter or grant section.

When NOT to Use

• User wants original research with experiments → paper-writer.
• User wants only an outline / topic exploration → research-explorer.
• User wants experiment code → experiment-suite.
• Topic is too broad (e.g., "all of AI") — narrow it before starting.

Workflow

Step 1 — Understand the topic and scope

Confirm with the user:

• Topic — specific research area (e.g., "federated learning in healthcare"). If too broad, narrow it first.
• Scope — broad survey of a field vs. focused review of a sub-area.
• Citation budget — minimum 60 unique entries; aim for 100+ (push higher for a broad survey).
• Language — default Chinese in conversation; the LaTeX paper is English unless requested otherwise.

Always tell the user that human review by a domain expert is recommended before publication or production use.

Step 2 — Set up the run directory

TOPIC="<topic>"
SLUG=$(python3 -c "import re,hashlib,sys; t=sys.argv[1]; n=re.sub(r'[\\s_]+','-',re.sub(r'[^\\w\\s-]','',t.lower().strip())).strip('-')[:40].rstrip('-'); h=hashlib.sha1(t.encode()).hexdigest()[:8]; print(f'{n}-{h}')" "$TOPIC")
TS=$(date +%Y-%m-%d_%H%M%S)
RUN=output/literature-survey/$SLUG/$TS/survey_paper

mkdir -p "$RUN/sections" "$RUN/figures"
cp -r literature-survey/templates/survey/. "$RUN/"
ln -sfn "$TS" "output/literature-survey/$SLUG/latest"

In commands below $RUN = output/literature-survey/<slug>/latest/survey_paper.

Step 3 — Build the survey (REQUIRED — this is the whole job)

Open references/00-incremental-execution.md first. Then carry out the five tracks below across many turns, persisting state to $RUN/ after every batch.

3.1 Bibliography — 60+ real entries (100+ recommended)

Open: references/01-bibliography-expansion.md.

First (§0 of that reference): read the topic's temporal/scope intent and pick a search posture. AI4S and similarly fast-moving fields default to at least 60% of references from the current calendar year and previous two years. If the topic names a year or says "latest/recent", use the stricter recency-led profile. Historical/theoretical surveys retain a timeline-spanning exception.

Then plan 12–20 query angles, weighted by the posture. For each angle: WebSearch → triage → WebFetch each kept candidate's abstract URL → extract canonical title/authors/year/venue/url → append a BibTeX entry to $RUN/bibliography.bib. Every entry must originate from a URL fetched in this session. Memory entries forbidden.

Hard stop: do not draft prose until the bibliography has ≥ 60 entries (100+ recommended) and passes check_bibliography_freshness.py for the recorded profile.

3.2 Figures — 6–10 survey-shaped

Open: references/02-survey-figures.md.

A survey is defined by how well it organises a field. Choose 6–10 topic-specific figures from the families that the evidence supports:

• taxonomy / classification diagram when the field has defensible branches;
• timeline when chronology explains a change in the field;
• area / capability matrix when comparable coverage data exists;
• architecture / mechanism diagram when a shared mechanism needs explanation;
• quantitative trend plots when extracted data supports them;
• citation network or paradigm comparison when the relationship itself matters.

Never force a family to fill a slot. Save each figure into $RUN/figures/ with reproducible source alongside.