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 Revision

ASecurity

Use when responding to an Annals of Mathematics referee report — revising the manuscript to close gaps or strengthen results and writing a point-by-point reply. Drafts the revision and response after the text is fixed; does not invent significance the result lacks (see anmath-scope-fit).

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

Security Analysis

A100/100

Scanned 6/4/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Anmath Revision?

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

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

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

Download with Pro
Files
SKILL.md
---
name: anmath-revision
description: Use when responding to an Annals of Mathematics referee report — revising the manuscript to close gaps or strengthen results and writing a point-by-point reply. Drafts the revision and response after the text is fixed; does not invent significance the result lacks (see anmath-scope-fit).
---

# Revision and Response (anmath-revision)

## When to trigger

- A referee report has arrived (revision requested, or queries to address)
- A referee found a gap, a questionable step, or a missing citation
- You need to revise the manuscript and write a point-by-point reply
- A correction is needed and you must show exactly what changed

> Math reviews are slow and thorough. A report may identify a genuine gap; the right
> response is to **fix the mathematics first**, then explain — never to argue a gap away.

## Order of operations

1. **Fix the text first.** Resolve every gap, error, or imprecision in the manuscript
   before drafting a single line of reply. The reply describes changes that already exist.
2. **Triage the report.** Classify each point: (a) genuine gap/error — must fix; (b)
   request for clarification — add exposition; (c) disagreement — respond with a precise
   mathematical argument, respectfully.
3. **Verify the fix does not break anything.** A repaired step must be re-checked against
   the whole argument (re-run the self-adversarial pass from anmath-referee-strategy).
4. **Then write the reply**, point by point, pointing to exact locations in the revision.

## Point-by-point reply structure

| Element | Content |
|---------|---------|
| Opening | Brief thanks; summary of the main changes |
| Each point | Quote the referee remark, then state the change and where it appears (section/line/Lemma) |
| Gaps/errors | Acknowledge plainly, give the corrected argument, point to the new text |
| Disagreements | A precise, courteous mathematical rebuttal; concede where the referee is right |
| Marked-up version | Provide a `latexdiff` PDF so changes are easy to verify |

## Handling a real gap

- If the gap is **fixable**, fix it fully and show the new argument; do not paper over it.
- If the fix **weakens the theorem** (e.g. an extra hypothesis is needed), state the new,
  correct theorem honestly and explain the change — a correct weaker result beats a wrong
  strong one.
- If the gap is **not fixable**, the honest course may be withdrawal or a substantially
  scaled-back result; consult anmath-scope-fit on whether the salvaged result still fits.
- Never respond to a gap with "it is easy to see" — that is what created the problem.

## Tone and conduct

- Respectful and precise. Referees give a great deal of unpaid time on long reviews.
- Concede points the referee gets right; defend points you are sure of with mathematics,
  not assertion.
- Address **every** point; silence on a remark reads as evasion.

## Checklist

- [ ] Every referee point is classified (gap / clarification / disagreement)
- [ ] All genuine gaps and errors are fixed in the manuscript first
- [ ] Each fix re-checked against the whole argument (no new gap introduced)
- [ ] Reply addresses every point, pointing to exact locations in the revision
- [ ] Any weakened/corrected theorem is stated honestly with the change explained
- [ ] A `latexdiff` marked-up version is included
- [ ] Tone is respectful; defenses are mathematical, not rhetorical
- [ ] If unfixable, scope/withdrawal reconsidered via anmath-scope-fit

## Anti-patterns

- Writing the reply before actually fixing the mathematics
- Arguing a genuine gap away instead of repairing it
- Patching a gap with "it is easy to see" — the original sin, repeated
- Silently ignoring a referee remark you find inconvenient
- Claiming the original (now-known-wrong) theorem still holds without a valid proof
- Defensive or dismissive tone toward a careful, time-intensive review

## Output format

```
【Report points】N total → gaps: a; clarifications: b; disagreements: c
【Gaps fixed】point i: corrected by ..., now in §...
【Theorem changed?】no / now reads ... (honest restatement)
【Re-check after fix】no new gap / FIX
【Reply drafted】point-by-point, with locations
【latexdiff attached】yes
【If unfixable】reconsider via anmath-scope-fit
【Next step】resubmit revision + response
```

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 →