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

Mind Review Process

ASecurity

Use to understand how Mind evaluates a submission — triple-anonymous peer review, quality as the sole criterion, the role of expert referees, and what it means for a journal that receives over 800 submissions a year. Sets expectations and shapes the paper to survive review; it does not contact editors.

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

Works with

cli

Security Analysis

A100/100

Scanned 6/6/2026

Install to Claude Code

$npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill mind-review-process --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mind Review Process?

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

Security grade badge for Mind Review Process
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-mind-review-process/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-mind-review-process)

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

Download with Pro
Files
SKILL.md
---
name: mind-review-process
description: Use to understand how Mind evaluates a submission — triple-anonymous peer review, quality as the sole criterion, the role of expert referees, and what it means for a journal that receives over 800 submissions a year. Sets expectations and shapes the paper to survive review; it does not contact editors.
---

# Review Process (mind-review-process)

Knowing how Mind screens and decides lets you pre-empt the failure modes before submitting. Mind runs a
**triple-anonymous** process, takes **quality as the sole criterion**, and receives **over 800
submissions a year** judged by expert referees. The selection is severe; the paper must be decisive on
its own terms.

## When to trigger

- Before submitting, to stress-test against the way Mind judges papers
- Interpreting a decision letter and setting realistic expectations
- Understanding why anonymization is non-negotiable here
- Deciding whether your piece is competitive at a high-rejection venue

## How Mind review works

1. **Triple-anonymous.** Author identity is **not revealed to editors or referees** unless and until
   the paper is accepted. This is stronger than ordinary double-anonymous review — neither the handling
   editor nor the referees know who you are. Prepare the manuscript accordingly (see `mind-submission`).
2. **Preparation is a gate.** Papers **not prepared for anonymous refereeing will not be read** —
   revealing acknowledgements and self-identifying references must be removed.
3. **Expert referees.** Editors seek advice from a large pool of expert referees, associate editors,
   and the Editorial Board. Assume the referee knows the debate and the strongest objection to your
   argument better than you do.
4. **Quality is the sole criterion.** No area, no style, no school is excluded — but the paper must be
   excellent: a significant thesis, a sound argument, the best objection answered.
5. **Severe selection.** With **>800 submissions a year**, most are declined. A paper that merely
   "adds something" rarely clears the bar; the argument must be decisive.

## Shape the paper to pass

- Make the **thesis and its significance** unmistakable early (avoids "not significant enough").
- **Answer the strongest objection visibly** — the referee *is* that objection (see
  `mind-objections-and-replies`).
- Engage the **best version** of the target view, not a strawman (see `mind-literature-positioning`).
- Keep technical material **glossed informally** so a non-specialist referee follows it.
- **Anonymize fully** — a non-anonymized manuscript may simply not be read.

## Anti-patterns

- Submitting a manuscript that reveals the author (it will not be read)
- A competent-but-incremental paper at a venue where quality is the sole, severe criterion
- Leaving the strongest objection for the referee to raise
- Targeting a strawman version of the view you oppose
- Assuming breadth of topic substitutes for a sharp, defended thesis

## Output format

```
【Anonymization】prepared for triple-anonymous review? [Y/N]
【Significance】thesis clearly significant, not incremental? [Y/N]
【Strongest objection】answered in the paper? [Y/N]
【Target view】engaged at its best? [Y/N]
【Realistic outcome】reject / revise / (rare) accept
【Next】mind-submission (or mind-revision-and-response if decided)
```

## Supplementary resources

- [`../../resources/official-source-map.md`](../../resources/official-source-map.md) — triple-anonymous policy, quality-only criterion, >800 submissions/year

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', ...

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.

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 →