// Use when writing or revising Introduction, Related Work, background, literature synthesis, or any section where references must drive claims
| name | evidence-driven-writing |
| description | Use when writing or revising Introduction, Related Work, background, literature synthesis, or any section where references must drive claims |
This skill turns a literature pool into manuscript argument. It is required for Introduction, Related Work, and any background section with citations.
Do not write the section until an evidence map and paragraph blueprint exist.
Required artifacts:
refs/evidence-map.md or plan/evidence-map.mdplan/chapter-blueprints/<section>-blueprint.mdplan/review/evidence-coverage.mdCreate one row per usable source:
| Source ID | Citation | Source type | Abstract-level finding | Usable fact | Supported claim | Citation slot | Risk |
|---|
Rules:
Risk: indirect.For each paragraph, define:
### Paragraph N
- Role: context / method landscape / limitation / gap / contribution
- Main claim:
- Evidence IDs:
- Contrast or transition:
- Forbidden content:
Only after the blueprint is complete may manuscript prose be written.
A publishable technical Introduction usually follows this chain:
For computer science / engineering SCI drafts, integrate the most relevant related-work synthesis into the Introduction unless the locked outline explicitly requires a standalone Related Work chapter. The section must read as an argument: field pressure, existing routes, unresolved bottleneck, proposed position, and contribution boundary.
Do not end the Introduction with a long mechanical chapter map. One concise manuscript-organization paragraph is enough.
Organize by theme, not by chronological paper dump:
User requirements and process notes must not enter manuscript text. Phrases such as "write naturally", "avoid generic wording", "discussion prompt", "fill later", "user should replace", and "this section is a template" belong in plan files, never in chapters.
Compression is not deletion. When shortening, preserve the claim, evidence, method condition, and limitation.
Literature-driven sections fail review if they read like a sequence of source notes. Each paragraph must synthesize at least two of the following:
If a paragraph can be converted into a table row without losing meaning, it is not yet manuscript prose.
For a reusable example of literature-driven argument structure extracted from the user's GPR passage, read references/gpr-introduction-example.md. Use it as a pattern, not as content for unrelated papers.
Use when writing academic papers, theses, or research articles - supports brainstorming, chapter writing, literature review, and LaTeX output
Use for translation, polishing, or de-AI-ification of academic text - provides ready-to-use prompt templates
Use when writing or revising academic papers, especially Chinese journal manuscripts, that need natural prose, de-AI-ification, Markdown formatting, or quality checks
Use when designing experiments, result tables, mock planning data, evaluation protocols, or results sections before real data are final
Use when creating data visualizations for papers - generates publication-quality plots with top-journal color schemes
Use when writing literature review sections - guides searching, organizing, and synthesizing academic sources