Aamas Submission logo

Aamas Submission

CommunityPopular
brycewang-stanford
aamas-submission

Use when auditing an AAMAS main-track submission for OpenReview readiness, the 8-page-plus-references limit, the full-paper versus 2-page extended-abstract choice, double-blind anonymity, the supplementary zip cap, track fit across the AAAI/JAAMAS/Blue Sky tracks, dual-submission rules, and desk-reject triggers before upload.

Overview

Publisherbrycewang-stanford
RepositoryAwesome-Journal-Skills
Skill nameaamas-submission
Stars
1.2K
Forks
159
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by brycewang-stanford on GitHub. Read the source before you install it.

Installation

Install the Aamas Submission AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/AAMAS-Skills/skills/aamas-submission
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git /tmp/Awesome-Journal-Skills
mkdir -p .claude/skills
cp -r /tmp/Awesome-Journal-Skills/AAMAS-Skills/skills/aamas-submission .claude/skills/aamas-submission
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Aamas Submission in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Aamas Submission on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Aamas Submission is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

AAMAS Submission

Use this for an AAMAS submission audit. Reopen the current-edition Call for Papers, submission instructions, important-dates page, and OpenReview group before giving deadline-ready advice; AAMAS rotates hosts yearly and the host page may block automated fetches.

Pick the track first

AAMAS is a multi-track conference, and choosing the wrong one is a silent rejection.

  • Main Technical Track: original agents/multiagent research, submitted as a full paper or a 2-page extended abstract.
  • AAAI Track: a strong AAAI submission redirected to AAMAS, in main-track format plus a short response to the AAAI reviews with changes highlighted; the extended-abstract option does not apply.
  • JAAMAS Track: a 2-page extended abstract of a JAAMAS journal article accepted or published in the window before the notification date.
  • Blue Sky Ideas, Demo, Competitions: visionary positions, live systems, and contests, each with its own page rule and deadline.

Submission audit

  • Confirm the target is the intended AAMAS track, not a workshop, tutorial, or a neighbor conference sharing the deadline season.
  • Verify OpenReview profiles, coauthor list, conflicts, subject-area keywords, title, and the short plain-text abstract that is due before the paper deadline.
  • Apply the current style file with no margin, spacing, or font hacks. AAMAS 2026 main-track papers were at most 8 pages plus any number of reference pages, and typesetting tricks to cram content into 8 pages were disallowed.
  • Decide full paper versus extended abstract deliberately: an extended abstract is archival presence, not a compressed full paper, and cannot carry a full evaluation.
  • Package supplementary material as one zip within the current cap (25 MB in 2026).
  • Enforce double-blind anonymity: replace author names and affiliations on page one with the paper tracking number, remove acknowledgements, and strip identifying metadata, paths, and repository owners from the PDF, code, and supplement.
  • Check the dual-submission and prior-publication rules for the chosen track before upload.

Blocking risks

  • Late abstract or paper upload against an AoE deadline.
  • Overlength main text, or an extended abstract mistaken for a full-paper slot.
  • Identity leak in the PDF, supplement, code paths, or metadata.
  • Supplement zip over the size cap or in a rejected format.
  • Wrong track, or a concurrent archival submission the track forbids.
  • An interaction claim with no multiagent evidence, or weak opponent/baseline coverage.

Desk-reject and triage table

TriggerSeverity at AAMASRepair window
Overlength 8-page bodyDesk rejectNone after the deadline
Style-file tamperingDesk reject or chair flagNone
Author identity leak in PDF or codeDesk rejectNone
Wrong track (e.g. AAAI-Track rules unmet)Return without reviewOnly before that track's deadline
Interaction claim without multiagent experimentReview-stage damageFixable only before the deadline

Final-week sequence for a MARL-plus-theory paper

  1. Freeze the game definition, agent objectives, and any equilibrium claims; reviewers cross-reference them.
  2. Regenerate every learning curve and payoff table from seeded scripts so PDF and supplement cannot diverge.
  3. Confirm the opponent/population set and evaluation protocol are stated in the body, not buried in the appendix.
  4. Strip PDF metadata, notebook authorship, and repository owner strings from the supplement.
  5. Confirm the OpenReview abstract matches the PDF abstract exactly, and the track is correct.

Format anchors

  • AAMAS uses a two-column proceedings layout; wide algorithm blocks, extensive-form game figures, and multi-panel learning curves that fit a one-column draft routinely overflow, so compress early rather than on deadline night.
  • The page and supplement numbers above describe the 2026 cycle; treat every value as provisional and recheck the current CFP before relying on it.

Output format

text
[AAMAS readiness] Ready / Needs fixes / Not ready
[Track] main-full / main-extended-abstract / AAAI / JAAMAS / Blue Sky / Demo / Competitions
[Blocking checks] <OpenReview/page/anonymity/supplement/track/dual-submission>
[Interaction-evidence risk] <one issue about the multiagent claim>
[Desk-reject risk] <one issue>
[Fix order] <ordered fixes before submission>

Frequently asked questions

What does the Aamas Submission AI skill do?

Use when auditing an AAMAS main-track submission for OpenReview readiness, the 8-page-plus-references limit, the full-paper versus 2-page extended-abstract choice, double-blind anonymity, the supplementary zip cap, track fit across the AAAI/JAAMAS/Blue Sky tracks, dual-submission rules, and desk-reject triggers before upload.

Why use Aamas Submission on TypingMind?

Because you install it once and use it with any model. Aamas Submission is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Aamas Submission in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/AAMAS-Skills/skills/aamas-submission. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Aamas Submission?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Aamas Submission?

As many as you like. As long as a model supports skills, you can use Aamas Submission with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Aamas Submission AI skill free?

Yes. It is published on GitHub by brycewang-stanford under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇