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 Results Framing

ASecurity

Use when stating the main theorem(s) of a pure-mathematics manuscript precisely, establishing their significance, and positioning them against prior work for an Annals of Mathematics submission. Crafts statements and positioning; does not write the proof (see anmath-methods).

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

Security Analysis

A100/100

Scanned 6/4/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Anmath Results Framing?

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

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

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

Download with Pro
Files
SKILL.md
---
name: anmath-results-framing
description: Use when stating the main theorem(s) of a pure-mathematics manuscript precisely, establishing their significance, and positioning them against prior work for an Annals of Mathematics submission. Crafts statements and positioning; does not write the proof (see anmath-methods).
---

# Stating the Main Theorem(s) (anmath-results-framing)

## When to trigger

- Your main result is described in a paragraph but not stated as a precise theorem
- The introduction does not make the significance unmistakable in the first page
- Readers cannot tell which statement is the headline and which are corollaries
- You have not located your theorem relative to the prior state of the art

## How to state the main theorem

A reader should be able to find the precise main theorem on or near the first page and
understand exactly what is claimed without reading the proof.

1. **State it precisely and self-containedly.** Every hypothesis explicit; every object
   defined or referenced. No "under suitable conditions" hand-waving.
2. **Quantify the advance.** Make clear what is new: which hypothesis is removed, which
   bound is sharpened, which case is now covered, which conjecture is settled.
3. **Separate headline from consequences.** One (or few) Main Theorem(s); corollaries and
   special cases stated separately so the contribution is unambiguous.
4. **Give the sharpest true statement.** Do not under-claim out of caution or over-claim
   beyond what the proof delivers; the statement and the proof must match exactly.

## Introduction architecture (Annals style)

| Element | Purpose |
|---------|---------|
| Problem and history | Why this question matters and what was known |
| Precise statement of Main Theorem | The headline, fully rigorous, early |
| What is new vs. prior work | Named comparison to the closest prior results |
| Consequences / corollaries | Why the result has reach |
| Method in one paragraph | A pointer to the proof idea (detail belongs to anmath-methods) |
| Organization of the paper | Section-by-section roadmap |

## Positioning against the literature

- Name the **closest prior results** and authors explicitly; state precisely what they
  proved and where your theorem goes beyond it (stronger hypothesis removed, sharper
  constant, new range, full generality).
- Engage carefully with **priority**: cite preprints/announcements you are aware of and
  state the relationship honestly. Claiming priority without engaging the record is a
  serious referee red flag.
- Do not rely on **unpublished or unverifiable** results for the core comparison; if a
  cited result is itself unpublished, say so and isolate your dependence on it.

## Checklist

- [ ] Main Theorem is stated precisely, with all hypotheses, near the first page
- [ ] It is clear which statement is the headline vs. corollaries
- [ ] The exact advance over prior work is quantified, not just asserted
- [ ] Closest prior results are named with authors and what they proved
- [ ] Priority relative to known preprints is engaged honestly
- [ ] The statement matches exactly what the proof delivers (no over/under-claim)
- [ ] MSC subject classification chosen to match the headline result

## Anti-patterns

- Burying the main theorem on page 8 after long preliminaries
- "We prove strong results about X" with no precise statement up front
- Claiming generality the proof does not actually establish
- Vague positioning ("improving earlier work") without naming the earlier work
- Asserting priority while ignoring a known competing announcement
- Listing five "main" theorems so the actual contribution is unclear

## Output format

```
【Main Theorem (precise)】...
【What is new vs. prior】removed-hypothesis / sharper-bound / settles-conjecture / ...
【Closest prior results】author (year): proved ...
【Corollaries / reach】...
【Priority note】no conflict / relationship to preprint X is ...
【MSC classes】primary ..., secondary ...
【Next step】anmath-methods (lay out the proof architecture)
```

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 →