Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Sci Citation

ASecurity

Use to convert references to Science's numbered citation style — cited in order of appearance, combined main+SM list, full author lists, abbreviated journal titles. Late-stage style pass.

1,052 stars
0 votes
0 copies
0 views
Added 6/6/2026
ai-agents

Security Analysis

A100/100

Scanned 6/6/2026

Install to Claude Code

$npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill sci-citation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Sci Citation?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Sci Citation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-sci-citation/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-sci-citation)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: sci-citation
description: Use to convert references to Science's numbered citation style — cited in order of appearance, combined main+SM list, full author lists, abbreviated journal titles. Late-stage style pass.
---

# Reference Style (sci-citation)

## When to trigger

- References are in author–date (APA/Harvard) or Nature style and must become Science style.
- The reference list is not ordered by citation appearance.
- Author lists are truncated with "et al." in the bibliography.
- Notes and references are split when Science combines them.

## Science citation mechanics

- **Numbered, in order of appearance** in the text, as italic numbers in parentheses: *(1)*, *(2, 3)*, *(4–6)*.
- A **single reference list** numbered consecutively; in Science, **main text and Supplementary Materials share one continuous numbering** (the SM continues the count). Confirm against current guidelines, but design for one list.
- **Notes and references are combined** — explanatory notes get a number in the same list.
- The reference list gives **full author lists** (Science does not truncate to "et al." in the bibliography for typical author counts).
- **Journal titles abbreviated** (per standard abbreviations); include volume, page (or article number), year.

## Reference formats (shape)

- **Journal article:**
  `A. B. Author, C. D. Author, E. F. Author, Title of the article. *Journal Abbrev.* **Volume**, page (year).`
- **Book:**
  `A. B. Author, *Book Title* (Publisher, ed., year), pp. xx–yy.`
- **Chapter:**
  `A. B. Author, in *Book Title*, C. Editor, Ed. (Publisher, year), pp. xx–yy.`
- **Dataset/code:** cite with repository, accession/DOI, and year (consistent with `sci-data`).
- **Preprint:** include the repository and DOI/identifier.

> Initials precede surnames; titles are in sentence case; journal in italics; volume in bold. Use a reference manager style file for Science to enforce this mechanically.

## Common conversion fixes

| From                              | To (Science)                                  |
|-----------------------------------|-----------------------------------------------|
| "(Smith et al., 2021)"            | "*(12)*"                                       |
| "Smith, J. (2021)."               | "J. Smith, …"                                 |
| Truncated "et al." in biblio      | full author list                              |
| Alphabetical reference list       | ordered by first appearance                   |
| Separate "Notes" section          | merged into the numbered list                 |

## Tooling

- Use Zotero/EndNote with the **Science** CSL/style; do a final manual pass on abbreviations and author-list completeness (managers often truncate).
- Verify every in-text number resolves and the list has no gaps/duplicates after the SM merge.

## Output format

```
【Style detected】 author-date / Nature / other → Science
【Numbering】 by appearance? single continuous list incl SM? yes/no
【Author lists】 full (not et al.) in biblio? yes/no
【Journal abbreviations】 applied? yes/no
【Unresolved/duplicate refs】 [...]
【Next】 sci-cover-letter
```

## Anti-patterns

- **Do not** leave author–date citations anywhere in a Science manuscript.
- **Do not** alphabetize the reference list — order is by appearance.
- **Do not** truncate author lists with "et al." in the bibliography.
- **Do not** keep separate main-text and SM reference numbering if guidelines call for one continuous list.

Attribution

brycewang-stanfordbrycewang-stanford
View sourceMore from brycewang-stanford →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →