New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Evidence Driven Writing

by Norman-bury in Norman-bury/research-writing-skill

A skill your agent uses when writing or revising Introduction, Related Work, background, literature synthesis, or any section where references must drive claims

MITAuto-check passedResearch & Science

Install Evidence Driven Writing

skills CLI
$ npx skills add Norman-bury/research-writing-skill --skill evidence-driven-writing -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Norman-bury/research-writing-skill evidence-driven-writing --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Norman-bury/research-writing-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/evidence-driven-writing .claude/skills/evidence-driven-writing && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
evidence-driven-writing
GitHub stars
3.4k
Token cost
~952 tokens
SKILL.md length
465 words
Files
2 (incl. references)
Skills in repo
20
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when writing or revising Introduction, Related Work, background, literature synthesis, or any section where references must drive claims

  • Works in 5 steps: Application context and why the problem… → Existing technical routes, grouped by… → Bottleneck cascade: what each route… → …
  • Revising Introduction
  • SKILL.md covers Hard Gate, Evidence Map, Paragraph Blueprint and Introduction Pattern, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Evidence Driven Writing is an agent skill from Norman-bury/research-writing-skill. Use when writing or revising Introduction, Related Work, background, literature synthesis, or any section where references must drive claims

Its SKILL.md is about 950 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/gpr-introduction-example.md`).

It sits in Research & Science, covering Literature review. The repository describes itself as: 科研写作助手 (Research Writing Assistant). The licence is MIT.

When your agent uses it

  • Revising Introduction
  • Literature synthesis
  • Any section where references must drive claims

Example prompts

  • “/evidence-driven-writing”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Application context and why the problem matters, supported by foundational or survey citations.
  2. Existing technical routes, grouped by method family rather than by paper list.
  3. Bottleneck cascade: what each route solves and what remains unsolved.
  4. Specific research gap that the proposed method can realistically address.
  5. Contributions written as prose or a short list only if the target style allows it.

What it can do on your machine

Read from SKILL.md and the folder at commit 6f79595. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Evidence Driven Writing loads about 952 tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 41 tokens; SKILL.md has 465 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~952
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Norman-bury/research-writing-skill at commit 6f79595, republished under its MIT licence (© Norman-bury). 465 words, ~952 tokens.

Download SKILL.mdSave it as .claude/skills/evidence-driven-writing/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
evidence-driven-writing
description
Use when writing or revising Introduction, Related Work, background, literature synthesis, or any section where references must drive claims

Evidence-Driven Writing

This skill turns a literature pool into manuscript argument. It is required for Introduction, Related Work, and any background section with citations.

Hard Gate

Do not write the section until an evidence map and paragraph blueprint exist.

Required artifacts:

  • refs/evidence-map.md or plan/evidence-map.md
  • plan/chapter-blueprints/<section>-blueprint.md
  • plan/review/evidence-coverage.md

Evidence Map

Create one row per usable source:

Source IDCitationSource typeAbstract-level findingUsable factSupported claimCitation slotRisk

Rules:

  • Use the user's literature pool first.
  • Use only information present in title, abstract, DOI metadata, or user-provided notes unless full text is available.
  • One citation must support one concrete claim, not a vague field statement.
  • Mark weak or indirect support as Risk: indirect.

Paragraph Blueprint

For each paragraph, define:

markdown
### 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.

Introduction Pattern

A publishable technical Introduction usually follows this chain:

  1. Application context and why the problem matters, supported by foundational or survey citations.
  2. Existing technical routes, grouped by method family rather than by paper list.
  3. Bottleneck cascade: what each route solves and what remains unsolved.
  4. Specific research gap that the proposed method can realistically address.
  5. Contributions written as prose or a short list only if the target style allows it.

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.

Show full SKILL.md (200 more words)Show less

Organize by theme, not by chronological paper dump:

  • Theme opening: define the method family or research stream.
  • Evidence synthesis: compare 2-4 sources in the same paragraph.
  • Critical boundary: state what the theme does not solve.
  • Bridge: explain why the next theme or the proposed method is needed.

Body Contamination Firewall

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.

Anti-Enumeration Gate

Literature-driven sections fail review if they read like a sequence of source notes. Each paragraph must synthesize at least two of the following:

  • a problem condition;
  • a method family;
  • a limitation shared by multiple studies;
  • a direct bridge to the proposed method;
  • a citation-backed boundary.

If a paragraph can be converted into a table row without losing meaning, it is not yet manuscript prose.

GPR Sample

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.

© Norman-bury, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/evidence-driven-writing of Norman-bury/research-writing-skill.

  • SKILL.md
  • references/gpr-introduction-example.md

Open the folder on GitHubat commit 6f79595

Compare with similar skills

Evidence Driven Writing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Evidence Driven Writing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Evidence Driven Writing this skillNorman-bury/research-writing-skill3.4k—~952Automated safety check: PassMIT
Nature Paper CardYuan1z0825/nature-skills47k2 repos~2.1kAutomated safety check: PassApache-2.0
Systematic Review ScreenerImbad0202/academic-research-skills51k—~8.4kAutomated safety check: PassCustom licence
Literature Reviewneflibata-feng/MyArxiv-Agent12620 repos~5.9kAutomated safety check: NotesMIT
Preprint Search on bioRxivLigphiDonk/Oh-my--paper73912 repos~3.7kAutomated safety check: PassMIT
Academic Paper Writing PipelineImbad0202/academic-research-skills51k—~16kAutomated safety check: PassCustom licence

Similar skills

  • Nature Paper Card

    Yuan1z0825/nature-skills

    Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.

    47k GitHub starsUsed in 2 repos~2.1k tokens
    Research & ScienceAuto-check passed

  • Systematic Review Screener

    Imbad0202/academic-research-skills

    Screens records for systematic, scoping and rapid reviews against fixed eligibility rules, using two blinded AI reviewers and a third adjudicator, with traceable PRISMA counts.

    51k GitHub stars~8.4k tokensUpdated yesterday
    Research & ScienceAuto-check passed

  • Literature Review

    neflibata-feng/MyArxiv-Agent

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).

    126 GitHub starsUsed in 20 repos~5.9k tokens
    Research & ScienceAuto-check: notes

  • Preprint Search on bioRxiv

    LigphiDonk/Oh-my--paper

    Searches bioRxiv life sciences preprints by keyword, author, date range or category with a Python script, returning JSON metadata and optional PDF downloads.

    739 GitHub starsUsed in 12 repos~3.7k tokens
    Research & ScienceAuto-check passed

  • Academic Paper Writing Pipeline

    Imbad0202/academic-research-skills

    Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.

    51k GitHub stars~16k tokensUpdated yesterday
    Research & ScienceAuto-check passed

  • Deep Research Workflow

    TokenRhythm/opensquilla

    Runs multi-round research in three stages with a persisted state file, evidence tracking and a long-form report with per-claim citations.

    7.1k GitHub stars~1.3k tokensUpdated yesterday
    Research & ScienceAuto-check passed

More from Norman-bury/research-writing-skill

All 20 skills in this repo

  • Environment Setup

    Norman-bury/research-writing-skill

    A skill your agent uses when Python environment setup is needed for data visualization or conda installation is required

    3.4k GitHub stars~840 tokensUpdated 4 mo ago
    Auto-check passed

  • Experiment Results Planning

    Norman-bury/research-writing-skill

    A skill your agent uses when designing experiments, result tables, mock planning data, evaluation protocols, or results sections before real data are final

    3.4k GitHub stars~990 tokensUpdated 4 mo ago
    Auto-check passed

  • Figures Diagram

    Norman-bury/research-writing-skill

    A skill your agent uses when creating flowcharts, architecture diagrams, or conceptual diagrams - generates prompts for image AI

    3.4k GitHub stars~548 tokensUpdated 4 mo ago
    Auto-check passed

  • Figures Python

    Norman-bury/research-writing-skill

    A skill your agent uses when creating data visualizations for papers - generates publication-quality plots with top-journal color schemes

    3.4k GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed

  • Latex Output

    Norman-bury/research-writing-skill

    A skill your agent uses when user requests LaTeX format output or has provided school/journal LaTeX templates

    3.4k GitHub stars~977 tokensUpdated 4 mo ago
    Auto-check passed

  • Literature Review

    Norman-bury/research-writing-skill

    A skill your agent uses when writing literature review sections - guides searching, organizing, and synthesizing academic sources

    3.4k GitHub stars~2.2k tokensUpdated 4 mo ago
    Auto-check: notes

Categories

Questions about Evidence Driven Writing

What does Evidence Driven Writing do?

A skill your agent uses when writing or revising Introduction, Related Work, background, literature synthesis, or any section where references must drive claims. Evidence Driven Writing is an agent skill from Norman-bury/research-writing-skill.

When should I use Evidence Driven Writing?

Evidence Driven Writing fits situations like: revising Introduction; literature synthesis; any section where references must drive claims.

How do I install Evidence Driven Writing in Claude Code?

Run `npx skills add Norman-bury/research-writing-skill --skill evidence-driven-writing -a claude-code`. Or copy the skill folder (skills/evidence-driven-writing in Norman-bury/research-writing-skill) into .claude/skills/evidence-driven-writing in your project. Claude Code loads it when a task matches its description.

How do I install Evidence Driven Writing in Codex?

Run `npx skills add Norman-bury/research-writing-skill --skill evidence-driven-writing -a codex`. Or copy the skill folder (skills/evidence-driven-writing in Norman-bury/research-writing-skill) into .agents/skills/evidence-driven-writing in your project. Codex loads it when a task matches its description.

Can I use Evidence Driven Writing in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Norman-bury/research-writing-skill --skill evidence-driven-writing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/evidence-driven-writing, .gemini/skills/evidence-driven-writing, .github/skills/evidence-driven-writing and .opencode/skills/evidence-driven-writing in your project.

What does Evidence Driven Writing need to run?

SKILL.md names no scripts, command-line tools or credentials: Evidence Driven Writing is instructions for the agent only.

Does Evidence Driven Writing access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Evidence Driven Writing safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Evidence Driven Writing use?

Evidence Driven Writing is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Evidence Driven Writing use?

About 952 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 861 tokens, read only when the agent opens those files.

What are the alternatives to Evidence Driven Writing?

Skills that share tags, products or a category with Evidence Driven Writing: Nature Paper Card (Yuan1z0825/nature-skills, 47k stars), Systematic Review Screener (Imbad0202/academic-research-skills, 51k stars), Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars) and Preprint Search on bioRxiv (LigphiDonk/Oh-my--paper, 739 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Evidence Driven Writing?

Norman-bury (a GitHub user) maintains it in Norman-bury/research-writing-skill, which has 3,384 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on June 10, 2026.

Source: Norman-bury/research-writing-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.