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

Ajps Rebuttal

ASecurity

Use when writing the response to an American Journal of Political Science (AJPS) revise-and-resubmit. The revised manuscript stays double-blind, the response memorandum is submitted anonymized, and any new analyses must keep the replication package re-runnable for the third-party verifier at acceptance. Structures the response; it does not fabricate new results.

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

Works with

api

Security Analysis

A100/100

Scanned 6/4/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Ajps Rebuttal?

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

Security grade badge for Ajps Rebuttal
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-ajps-rebuttal/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-ajps-rebuttal)

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

Download with Pro
Files
SKILL.md
---
name: ajps-rebuttal
description: Use when writing the response to an American Journal of Political Science (AJPS) revise-and-resubmit. The revised manuscript stays double-blind, the response memorandum is submitted anonymized, and any new analyses must keep the replication package re-runnable for the third-party verifier at acceptance. Structures the response; it does not fabricate new results.
---

# R&R Rebuttal (ajps-rebuttal)

An AJPS **R&R is a real opportunity** — most accepted papers earn it through revision. The response
must convert each reviewer while keeping the editor confident the revision converges, and it carries
two AJPS-specific constraints: the **resubmission stays double-blind** (the response memorandum is
uploaded **anonymized**), and any new analysis must keep the deposited code **re-runnable**, because a
third-party verifier will re-run it at acceptance (see `ajps-replication-and-verification`).

## When to trigger

- An R&R decision arrived and you are planning the revision + response memorandum
- Reviewers disagree and you must reconcile their demands
- A reviewer requests analyses that would change the paper's claims
- Writing the cover note to the editor summarizing the revision

## Strategy

1. **Read the editor's letter as the rubric.** The editor signals which points are decisive — solve
   those first; the editor adjudicates disagreements among reviewers.
2. **One point-by-point memorandum, every comment addressed.** Quote each comment, then respond. Never
   skip one — silence reads as non-compliance.
3. **Concede or rebut explicitly, with evidence.** For each: did what was asked (say where, with the
   new text/table number), or push back **respectfully with a reason** (theory, design, evidence). A
   well-argued disagreement beats a capitulation that weakens the paper.
4. **Reconcile conflicting reviewers openly.** When R2 wants the opposite of R3, say so, choose a
   principled path, and explain the tradeoff to the editor.
5. **Protect the contribution and the identification.** Add robustness and clarifications; resist
   changes that dilute the generalizable claim or weaken the design that earned the R&R.
6. **Keep it anonymous and re-runnable.** The revised manuscript stays **double-blind** (no
   acknowledgments/funding/first-person self-cites added back in), the memorandum is uploaded
   **anonymized**, and every new exhibit must be regenerated by the master script so verification at
   acceptance will pass.

## Response-memorandum format

For each reviewer comment:

```
> [Quoted reviewer comment]

Response: [What we did / why we respectfully disagree].
Change: [Section/page/table-figure number where the revision appears].
```

Open with a short **summary of the main changes** to the editor; group by reviewer; end each entry with
the location of the change so the editor can verify quickly. Keep the memorandum anonymized.

## Anti-patterns

- Ignoring or merging away a comment without a visible response
- Capitulating to a request that breaks the paper's logic just to please a reviewer
- Defensive or dismissive tone toward reviewers
- "We thank the reviewer" with no actual change or argued reason
- De-anonymizing the resubmission (adding acknowledgments, funding, or first-person self-cites back)
- Adding analyses that the deposited code can no longer reproduce (verification will fail at acceptance)

## Output format

```
【Editor's decisive points】addressed first? [list]
【Coverage】every reviewer comment answered? [Y/N]
【Concede vs rebut】each tagged with evidence + change location
【Reviewer conflicts】reconciled and explained to editor? [Y/N]
【Contribution protected】no dilution of claim/identification? [Y/N]
【Anonymity + package】resubmission still blind; new exhibits re-runnable? [Y/N]
【Next】resubmit via Editorial Manager
```

## Supplementary resources

- [`../../resources/official-source-map.md`](../../resources/official-source-map.md) — double-blind resubmission and verification-at-acceptance policy

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 →