eccv-artifact-evaluation
Use when packaging code, models, and data around an ECCV paper — the anonymous review-time archive under the trailing supplement deadline, the do-not-cite-your-own-repo rule, and the June-to-September post-acceptance runway for a public release aligned with the ECVA and Springer copies of the paper.
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill eccv-artifact-evaluation --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# ECCV Artifact Evaluation Use this for artifact strategy at ECCV, which has no badge-granting artifact track: artifacts live in two phases with opposite rules. Before decisions, code is a **sealed, anonymous supplement**; after the June decision, it becomes a **public release with a ten-week runway** before the September conference makes the paper visible to the whole field. ## Phase 1 — sealed archive (review time) - Upload with the supplement by the trailing deadline (March 12 in 2026, one week after the paper). - The submission text must not link to the authors' public repository even if it already exists — ECCV 2026 policy treated that as an anonymity break, while arXiv posting itself was fine. - Assume one reviewer opens the archive for ten minutes. Optimize for that reader: a README that maps each main-table row to a command, pinned dependencies, and one tiny demo input that runs on CPU. - Scrub the usual vision-stack leaks: wandb entity names in configs, dataset paths containing lab or cluster names, git history, notebook metadata, license headers with author names, model cards naming the group. ## What vision reviewers actually probe | Artifact | Probe | Failure they repor
- Phase 1 — sealed archive (review time)
- What vision reviewers actually probe
- Phase 2 — the ten-week release runway
- Dataset and benchmark releases
- Output format
minimal release self-check before announcing git clone <public-url> fresh && cd fresh pip install -r requirements.txt # pinned, resolvable python demo.py --input assets/demo.jpg # CPU-runnable smoke test python eval.py --split val --ckpt <hash> # reproduces one paper row
What does the eccv-artifact-evaluation skill do?
Use when packaging code, models, and data around an ECCV paper — the anonymous review-time archive under the trailing supplement deadline, the do-not-cite-your-own-repo rule, and the June-to-September post-acceptance runway for a public release aligned with the ECVA and Springer copies of the paper.
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill eccv-artifact-evaluation --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Awesome-Journal-Skills, a repository with 909 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.