Tooluck logoTooluck
SKILL.md

aaai-reproducibility

Agent skill frombrycewang-stanford/Awesome-Journal-Skills

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 Phase-1 reviewers use to judge rigor across AAAI's broad AI scope.

How to install aaai-reproducibility

install aaai-reproducibility
# install the Awesome-Journal-Skills pack with the skills CLI
npx skills add brycewang-stanford/Awesome-Journal-Skills

# or add only this skill to Claude Code: copy the folder

AAAI-Skills/skills/aaai-reproducibility/

# into

~/.claude/skills/aaai-reproducibility/ (all projects)

.claude/skills/aaai-reproducibility/ (one project)

AAAI-Skills/skills/aaai-reproducibility/SKILL.md

MITFull file
1# AAAI Reproducibility
2
3Use this when a draft needs to survive AAAI review on rigor, not just novelty. AAAI-27 requires the
4reproducibility checklist to be **uploaded separately** from the main PDF, in its own field on the
5submission form (AAAI-26 carried it inside the PDF after the references) — so it is a document a
6reviewer opens on its own, and it has to agree with the paper and supplement rather than read as an
7afterthought. AAAI-27 also states that reviewers assess reproducibility from what was actually
8submitted, and that material promised "after acceptance or publication" is not evidence it exists.
9
10## Reproducibility audit
11
12- Map each central claim to submitted evidence: theorem, table, figure, ablation, appendix item,
13 checklist answer, or code/data artifact.
14- Record seeds, splits, preprocessing, hyperparameters, model selection, early stopping, prompt
15 selection, and hardware.
16- Report variance or uncertainty when stochasticity affects conclusions.
17- Document dataset licenses, access constraints, sensitive data, human-subjects issues, and
18 annotation procedures.
19- Separate training compute, inference compute, and experiment search cost.
20- Check the reproducibility checklist for contradictions with the main text and supplement.
21
22## Common AAAI weaknesses
23
24- Checklist says code/data are available but supplement lacks runnable commands.
25- Main results rely on one seed, one benchmark, or one prompt family.
26…

Excerpt shown under the repository's MIT license.

More skills in Awesome-Journal-Skills

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

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

CCCXGHGM+135 skills

nexu-io /

open-design
107k

The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create motion, prototypes, websites, apps, dashboards, presentations, images, and videos with your team and AI agents. Share work, exchange feedback, and iterate together in one workspace.

40 skills

tt-a1i /

archify
95k

Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.

CCCXOC1 skill

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates