Skills for Real Engineers. Straight from my .agents directory.
aaai-author-response
Agent skill frombrycewang-stanford/Awesome-Journal-Skills
Use when drafting an AAAI author response (rebuttal) under the single short character-limited author-feedback window, the no-URL rule, no-new-results guidance, AI-generated-review handling, and the AAAI two-phase review process where Phase-2 papers receive one feedback round before SPC/AC discussion.
How to install aaai-author-response
npx skills add brycewang-stanford/Awesome-Journal-Skills# or add only this skill to Claude Code: copy the folder
AAAI-Skills/skills/aaai-author-response/
# into
~/.claude/skills/aaai-author-response/ (all projects)
.claude/skills/aaai-author-response/ (one project)
1# AAAI Author Response23Use this after AAAI reviews are released. AAAI rebuttal space is scarce: the AAAI-26 FAQ allowed a4single 2500-character response, disallowed URLs, and discouraged new results. **AAAI-27 has not yet5published its own rebuttal FAQ** — its author feedback window is 2026-10-19 to 10-25 — so treat those6limits as the prior cycle's shape and reopen the current FAQ before drafting.78## Triage910- Respond to decision-critical factual errors first.11- Address human reviews and AI-generated review points when they affect the SPC/AC decision.12- Do not spend space on tone, score fairness, or reviewer motivation.13- Do not include URLs if current rules forbid them.14- Do not introduce new experiments or results. Explain existing evidence, clarify omissions, or15 state why requested experiments are not needed.16- If supplementary files were missing or corrupted, acknowledge the limitation; AAAI has not17 permitted updates at rebuttal time, and the supplementary deadline (2026-07-31 for AAAI-27) closed18 months before feedback opens.1920## What moves an AAAI score2122Author feedback at AAAI is read by human reviewers and weighed in SPC/AC discussion, not by the23non-decisional AI review. With one short response and no second round, spend every character on the24concern most likely to flip a borderline decision. Triage each reviewer point into a lane:2526- Factual error that, if uncorrected, sinks the paper: answer first, cite the submitted anchor.27…
Excerpt shown under the repository's MIT license.
More skills in Awesome-Journal-Skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
