/aaai-supplementary
Use when organizing AAAI supplementary material, including the technical appendix, multimedia appendix, and code/data ZIPs, while respecting that AAAI supplements are due with the paper, treated as immutable after submission, must stay double-blind, and should never hide
$ npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill aaai-supplementary --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/aaai-supplementary
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when organizing AAAI supplementary material, including the technical appendix, multimedia appendix, and code/data ZIPs, while respecting that AAAI supplements are due with the paper, treated as immutable after submission, must stay double-blind, and should never hide
SKILL.md
aaai-supplementary.SKILL.mdname: aaai-supplementary
description: Use when organizing AAAI supplementary material, including the technical appendix, multimedia appendix, and code/data ZIPs, while respecting that AAAI supplements are due with the paper, treated as immutable after submission, must stay double-blind, and should never hide main-paper-critical evidence from reviewers who skim the appendix.
AAAI Supplementary
Use this when deciding what belongs in the main paper, technical appendix, multimedia appendix, or code/data ZIP. AAAI supplementary material is due with the paper and should be treated as immutable once submitted unless current instructions say otherwise.
Supplement structure
- Keep the central contribution, method, core results, and checklist-relevant evidence in the main
paper.
- Put proofs, extra ablations, extended qualitative examples, implementation details, and additional
error analysis in the technical appendix.
- Put videos, audio, interactive demos, or visualizations in a multimedia appendix only when they are
technically necessary.
- Put scripts, datasets, logs, model configs, and checkpoints in code/data ZIPs.
- Add a compact appendix map so reviewers can find support for each disputed claim.
Anonymity and immutability
- Remove identity from file names, metadata, paths, Git history, author comments, and license
headers.
- Do not use web pointers for extra material if current AAAI rules disallow them.
- Submit final, uncorrupted files. Do not rely on rebuttal to repair missing content.
- Keep the supplement consistent with the reproducibility checklist.
Where each item belongs
A broad-AI reviewer will skim the appendix, not study it, so placement decides whether evidence is actually seen. Anything a claim depends on belongs in the main paper; the appendix only deepens it.
| Material | Main paper | Technical appendix | Multimedia | Code/data ZIP | | --- | --- | --- | --- | --- | | Core result | yes | no | no | no | | Full proof | sketch | full | no | no | | Extra ablation | summary | detail | no | no | | Demo of behavior | no | no | yes | no | | Scripts and configs | no | no | no | yes |
Reviewer-pushback patterns
- "The key result is only in the appendix." Fix: promote it to the main paper; AAAI reviewers are not
obligated to find a load-bearing claim buried in supplement.
- "Supplement contradicts the checklist." Fix: reconcile every appendix number with the checklist
before submission, since neither can be edited later.
- "Multimedia is huge but adds nothing." Fix: drop spectacle clips; include video only when it is the
evidence, not decoration.
Worked vignette
A vision paper hides its ablation table in the ZIP and leaves only a teaser figure in the paper. The navigation map exposes the gap: a disputed claim points to a file a skimming reviewer will miss. The fix moves the ablation summary into the main paper, keeps full per-class numbers in the technical appendix, and scrubs the ZIP's metadata so nothing deanonymizes the immutable supplement.
Output format
[Supplement plan] technical appendix / multimedia appendix / code-data ZIP / none
[Main-paper dependencies] <material that must not be hidden in supplement>
[Navigation map] <claim -> supplement file/section>
[Anonymity risks] <paths, metadata, links, ownership>
[Submission risk] <missing/corrupt/too large/not allowed>
Read more
name: aaai-supplementary description: Use when organizing AAAI supplementary material, including the technical appendix, multimedia appendix, and code/data ZIPs, while respecting that AAAI supplements are due with the paper, treated as immutable after submission, must stay double-blind, and should never hide main-paper-critical evidence from reviewers who skim the appendix.
AAAI Supplementary
Use this when deciding what belongs in the main paper, technical appendix, multimedia appendix, or code/data ZIP. AAAI supplementary material is due with the paper and should be treated as immutable once submitted unless current instructions say otherwise.
Supplement structure
- Keep the central contribution, method, core results, and checklist-relevant evidence in the main
paper.
- Put proofs, extra ablations, extended qualitative examples, implementation details, and additional
error analysis in the technical appendix.
- Put videos, audio, interactive demos, or visualizations in a multimedia appendix only when they are
technically necessary.
- Put scripts, datasets, logs, model configs, and checkpoints in code/data ZIPs.
- Add a compact appendix map so reviewers can find support for each disputed claim.
Anonymity and immutability
- Remove identity from file names, metadata, paths, Git history, author comments, and license
headers.
- Do not use web pointers for extra material if current AAAI rules disallow them.
- Submit final, uncorrupted files. Do not rely on rebuttal to repair missing content.
- Keep the supplement consistent with the reproducibility checklist.
Where each item belongs
A broad-AI reviewer will skim the appendix, not study it, so placement decides whether evidence is actually seen. Anything a claim depends on belongs in the main paper; the appendix only deepens it.
| Material | Main paper | Technical appendix | Multimedia | Code/data ZIP | | --- | --- | --- | --- | --- | | Core result | yes | no | no | no | | Full proof | sketch | full | no | no | | Extra ablation | summary | detail | no | no | | Demo of behavior | no | no | yes | no | | Scripts and configs | no | no | no | yes |
Reviewer-pushback patterns
- "The key result is only in the appendix." Fix: promote it to the main paper; AAAI reviewers are not
obligated to find a load-bearing claim buried in supplement.
- "Supplement contradicts the checklist." Fix: reconcile every appendix number with the checklist
before submission, since neither can be edited later.
- "Multimedia is huge but adds nothing." Fix: drop spectacle clips; include video only when it is the
evidence, not decoration.
Worked vignette
A vision paper hides its ablation table in the ZIP and leaves only a teaser figure in the paper. The navigation map exposes the gap: a disputed claim points to a file a skimming reviewer will miss. The fix moves the ablation summary into the main paper, keeps full per-class numbers in the technical appendix, and scrubs the ZIP's metadata so nothing deanonymizes the immutable supplement.
Output format
[Supplement plan] technical appendix / multimedia appendix / code-data ZIP / none [Main-paper dependencies] <material that must not be hidden in supplement> [Navigation map] <claim -> supplement file/section> [Anonymity risks] <paths, metadata, links, ownership> [Submission risk] <missing/corrupt/too large/not allowed>
Stanford REAP × CoPaper.AI · 由斯坦福实证方法论团队精选与维护 访问 copaper.ai 微信:CoPaper.AI 按 11 个主流学科板块覆盖 经管与商科 社会科学 人文学科 数学与物理科学 生命科学 医学与健康 工程与技术 计算机科学与 AI 体育科学 点击任一学科名可跳转到对应说明;每类下的代表子领域在正文总览中完整列出。下方封面墙按 venue 导航,完整分类见覆盖一览。 🧭 布局指南 · 📚 Skill Pack 一览 · ⚡ 如何使用 · 🧪 自动实证
Other skills on awesome-journal-skills.
- /aaai-artifact-evaluation
Use when packaging AAAI code, data, multimedia appendices, technical appendices, reproducibility evidence, and post-acceptance artifact releases without violating double-blind or immutable-supplement rules.
Open skill - /aaai-author-response
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
Open skill - /aaai-camera-ready
Use when preparing an accepted AAAI paper for camera-ready source submission to AAAI Press, including proceedings page limits, two-column template compliance, copyright transfer, purchased extra technical pages, deanonymization, registration, oral or poster presentation, and
Open skill - /aaai-experiments
Use when designing or auditing AAAI experiments for the broad-AI program committee, including baselines, ablations, statistical significance, robustness, human evaluation, AI-for-Social-Impact and alignment/safety evidence, compute and cost reporting, and
Open skill - /aaai-related-work
Use when positioning an AAAI paper's novelty against archival work, contemporaneous arXiv or workshop papers, and AAAI/IJCAI/NeurIPS/ICML/ICLR neighbors across the broad AI scope, while staying inside AAAI's dual-submission and AI-as-source policy constraints and writing a
Open skill - /aaai-reproducibility
Use when strengthening an AAAI paper's reproducibility checklist (placed after references), experimental traceability, seed and hyperparameter reporting, compute and cost disclosure, dataset access and licensing, code/data ZIP readiness, and the claim-to-evidence map that
Open skill

