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 Submission

ASecurity

Use as the final preflight before submitting to Science — a complete checklist across significance, format, figures, statistics, data, references, and required files. Bundles templates.

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

Security Analysis

A100/100

Scanned 6/6/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Sci Submission?

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

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

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

Download with Pro
Files
SKILL.md
---
name: sci-submission
description: Use as the final preflight before submitting to Science — a complete checklist across significance, format, figures, statistics, data, references, and required files. Bundles templates.
---

# Submission Preflight (sci-submission)

## When to trigger

- The manuscript is "done" and you're about to upload.
- You want a single gate that confirms every other sci-* skill's output landed.
- A revision is going back and you need to confirm nothing regressed.

## Master preflight checklist

### Significance & framing
- [ ] Clears the broad-significance / general-interest bar (`sci-fit` rung ≥ 3).
- [ ] One-sentence advance present and demonstrated (not asserted).
- [ ] Title is declarative, specific, < ~90 characters.

### Format & length
- [ ] Format chosen (Report ~2,500 w / ≤4 items, or Research Article ~4,500 w / ≤6 items).
- [ ] Main-text word count within budget; Methods in Supplementary (for Reports).
- [ ] Results ordered by argument, claim-first paragraphs.

### Abstract & summary
- [ ] One-sentence summary ≤ ~125 characters, not a title paraphrase.
- [ ] Abstract ≤ ~125 words, no subheadings/citations, ≥1 quantified result.

### Figures & display items
- [ ] Within item budget; sized to 5.5/12/18 cm; fonts ≥ 6 pt.
- [ ] Data shown (points + n); error bars defined; scale bars present.
- [ ] Colorblind-safe; uncropped key blots + source data retained.

### Statistics & reproducibility
- [ ] Each claim: effect size + CI + n + test + assumptions.
- [ ] Biological vs technical replication clear; sample-size rationale stated.
- [ ] Randomization/blinding reported or justified; multiplicity controlled.
- [ ] Analysis code public + archived (DOI).

### Data, materials, ethics
- [ ] Data deposited with accession numbers/DOIs (no "on request" for primary data).
- [ ] Data-availability statement drafted and compliant.
- [ ] Materials/reagent sharing plan; ethics approvals (IRB/IACUC/permits) as needed.

### References
- [ ] Science numbered style, ordered by appearance, one continuous list (incl. SM).
- [ ] Full author lists; journal abbreviations; all in-text numbers resolve.

### Required files & metadata
- [ ] Main text (with title, one-sentence summary, abstract, refs).
- [ ] Figures at required resolution + figure legends.
- [ ] Supplementary Materials (Materials and Methods, supp figs/tables, captions).
- [ ] Cover letter (significance-forward).
- [ ] Author list, affiliations, ORCIDs, corresponding author.
- [ ] Author contributions (CRediT), competing interests, funding.
- [ ] Suggested/opposed reviewers (if used).

## Final integrity sweep

- [ ] No over-claiming beyond the evidence (re-read the abstract and last paragraph).
- [ ] Every figure's n, error bar, and test are defined in its legend.
- [ ] All accession numbers/DOIs are live and correct.
- [ ] Manuscript is anonymized only if double-blind is requested (Science is typically single-blind — confirm).

## Templates

- `templates/checklist.md` — copyable preflight checklist.
- `templates/cover_letter_template.md` — significance-forward cover letter scaffold.

## Output format

```
【Blocking gaps】 [...]  (must fix before upload)
【Warnings】 [...]       (should fix)
【Files ready】 main / figures+legends / SM / cover letter / metadata
【Verdict】 GO / NO-GO + the top 3 fixes
【Next】 submit | sci-rebuttal (after decision)
```

## Anti-patterns

- **Do not** upload before accession numbers/DOIs exist.
- **Do not** skip the integrity sweep — over-claiming is a top rejection reason post-review.
- **Do not** rely on memory; run the checklist top to bottom.

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 →