Agent skill · Security

science-research-writing

Use when researchers need to plan, draft, revise, or audit an empirical research paper from their own materials, including Introduction, Methods, Results, Discussion, Conclusion, Abstract, and Title, with evidence-preserving and target-journal-aware guidance.

Yila-AIgithub.com/Yila-AIGitHub ↗
claude-codecodexships scriptsApache-2.0
Install
npx skills add Yila-AI/sci-ssci-skills --skill science-research-writing --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 17
SKILL.md size: 8 KB
Bundled scripts: yes
Path: skills/science-research-writing/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 78
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Science Research Writing Turn the author's research materials into the next useful manuscript deliverable. Guide the writing process without replacing scientific judgment or inventing intellectual content. ## Load only what is needed - Always read `references/input-output-contract.md` and `references/certainty-and-claim-strength.md`. - Read `references/reverse-engineering-protocol.md` when target papers are supplied or the user requests journal adaptation. - Read only the relevant section reference: `introduction.md`, `methods.md`, `results.md`, `discussion.md`, `conclusion.md`, `abstract.md`, or `title.md`. - Use `assets/section-function-map.md` for planning, `assets/evidence-ledger.csv` for provenance-sensitive drafting, and `assets/target-journal-model.json` for target-paper modeling. ## First response: inspect before asking Read all supplied materials first. Identify: - manuscript stage: idea, research materials, partial draft, or full draft; - primary job: `lookup`, `learn`, `model`, `plan`, `draft`, `revise`, or `audit`; - paper section and empirical design when inferable; - facts, numbers, citations, technical terms, null findings, limitations, and author judgments that mu

What's inside
Steps it walks through
  1. Load only what is needed
  2. First response: inspect before asking
  3. Route the task
  4. Idea stage
  5. Research-materials stage
  6. Partial-draft stage
  7. Full-draft stage
  8. Target papers supplied
  9. Build an evidence ledger
  10. Write by information function
  11. Audit every draft
  12. Refusal boundary
  13. Return a novice-readable result
Ships with 16 files
  • agents/openai.yaml
  • assets/evidence-ledger.csv
  • assets/section-function-map.md
  • assets/target-journal-model.json
  • references/abstract.md
  • references/certainty-and-claim-strength.md
  • references/conclusion.md
  • references/discussion.md
  • references/input-output-contract.md
  • references/introduction.md
  • references/methods.md
  • references/results.md
  • references/reverse-engineering-protocol.md
  • references/title.md
  • scripts/check_draft_invariants.py
  • scripts/validate_writing_model.py
More from sci-ssci-skills
All skills →
About this skill
What does the science-research-writing skill do?

Use when researchers need to plan, draft, revise, or audit an empirical research paper from their own materials, including Introduction, Methods, Results, Discussion, Conclusion, Abstract, and Title, with evidence-preserving and target-journal-aware guidance.

How do I install it?

Run `npx skills add Yila-AI/sci-ssci-skills --skill science-research-writing --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From Yila-AI/sci-ssci-skills, a repository with 78 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going