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

Anmath Submission

ASecurity

Use when running the final pre-submission preflight for an Annals of Mathematics manuscript — AMS-LaTeX compile, theorem environments, abstract and MSC, references, arXiv, figures, and portal logistics. Checks readiness; does not assess significance (anmath-scope-fit) or correctness (anmath-referee-strategy).

1,052 stars
0 votes
0 copies
0 views
Added 6/4/2026
ai-agents

Works with

cli

Security Analysis

A100/100

Scanned 6/4/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Anmath Submission?

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

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

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

Download with Pro
Files
SKILL.md
---
name: anmath-submission
description: Use when running the final pre-submission preflight for an Annals of Mathematics manuscript — AMS-LaTeX compile, theorem environments, abstract and MSC, references, arXiv, figures, and portal logistics. Checks readiness; does not assess significance (anmath-scope-fit) or correctness (anmath-referee-strategy).
---

# Pre-Submission Preflight (anmath-submission)

## When to trigger

- "I'm submitting tomorrow"
- Final check before clicking submit on the portal
- Unsure what files and metadata the submission system needs

> Verify all volatile specifics (portal URL, accepted formats, length expectations, whether
> a cover letter is collected) on the journal's official submission page first — these change.

## Preflight checklist

### TeX and format

- [ ] Source compiles cleanly with a standard distribution; no errors, no missing refs
- [ ] AMS environments used (`amsthm` for theorem/lemma/proposition/definition/remark/proof)
- [ ] A single, consistent theorem-numbering scheme throughout
- [ ] All cross-references (`\cref`/`\eqref`) resolve; no "??" in the PDF
- [ ] Submitted PDF is the version produced by the source you will provide on acceptance

### Front matter

- [ ] Title, author(s), affiliations, and contact consistent with portal entries
- [ ] Abstract present, self-contained, states the Main Theorem in plain terms
- [ ] MSC subject classification: primary + secondary, matching the headline result
- [ ] Keywords (if requested) chosen to match the area
- [ ] Acknowledgments and funding stated as the journal requires

### Mathematical content

- [ ] Main Theorem stated precisely and early (see anmath-results-framing)
- [ ] Proof complete and gap-free; no unresolved "clearly"/"it is easy to see"
- [ ] Every external result invoked is published and precisely cited
- [ ] No essential step rests on an unpublished/unverifiable claim
- [ ] Computer-assisted steps (if any) documented with archived code/data

### References

- [ ] Bibliography uses consistent style (BibTeX, MathSciNet abbreviations / `\MR`)
- [ ] Every citation in text appears in the bibliography and vice versa
- [ ] Preprints labeled as such; replace with version-of-record where available
- [ ] Closest prior results cited with correct authors and statements

### Figures / diagrams (if any)

- [ ] Vector format (PDF/EPS); labeled; referenced in text; genuinely necessary
- [ ] Commutative diagrams typeset with `tikz-cd`/`amscd`, arrows consistent

### Logistics

- [ ] arXiv preprint id ready to declare (if you posted one)
- [ ] Cover letter prepared if the portal requests it (see anmath-cover-letter)
- [ ] File size / format within portal limits
- [ ] Coauthors have approved the final version

## Submission system notes (verify currency)

- Submission is electronic; check the official page for the current portal and the exact
  upload format (compiled PDF for review; TeX source typically requested on acceptance).
- Be prepared for a long review — detailed proof verification can take a year or more.
- Keep the exact submitted source under version control for later `latexdiff` revisions.

## Anti-patterns

- Submitting a PDF that does not match the source you will later provide
- Broken cross-references ("Theorem ??") left in the compiled file
- Missing or mismatched MSC classification
- Bibliography in a default reference-manager style, inconsistent abbreviations
- Citing a preprint for an essential step that has since been superseded or withdrawn
- Discovering the portal wanted a cover letter only at the upload step

## Output format

```
【Compiles cleanly】yes / no
【Abstract + MSC】present / missing: ...
【Proof gaps】none / BLOCKER: ...
【References】in-text↔bib reconciled; preprints labeled
【Figures/diagrams】none / vector & referenced
【arXiv id】... / none
【Cover letter】prepared / not required
【Next step】anmath-referee-strategy (stress-test) → submit; then await report → anmath-revision
```

## Associated resources

- [`templates/manuscript_template.md`](templates/manuscript_template.md) — AMS-style manuscript skeleton (front matter, theorem environments, sectioning, references)
- [`templates/checklist.md`](templates/checklist.md) — 8-section pre-submission self-check
- [`../../resources/external_tools.md`](../../resources/external_tools.md) — TeX/AMS packages, MathSciNet/zbMATH, proof assistants, diagram tools

Attribution

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

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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".

1074701 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', ...

693161 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.

691 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 →