conext-supplementary
Use when deciding what goes in the ACM CoNEXT main body versus the appendix budget versus the artifact — splitting content by decision-criticality so nothing a reviewer needs to accept the paper hides in an appendix or repository, within the acmart limits (long ≤4 appendix pages, short ≤2).
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill conext-supplementary --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.
# CoNEXT Supplementary Decide where each piece of content lives: the **reviewed body**, the **appendix budget**, or the **artifact**. The governing rule at CoNEXT is **decision-criticality** — anything a reviewer must read to be convinced the paper should be accepted belongs in the body, not in an appendix a reviewer may skip or an artifact they may not open. CoNEXT's appendix budget is small (long papers ≤4 pages, short papers ≤2), so this is a real allocation problem, not a dumping ground. ## The three tiers | Tier | Belongs in | Test | |---|---|---| | **Decision-critical** | Main body (≤16 / ≤10 pages) | Would a reviewer's accept/reject flip without it? -> body | | **Supporting** | Appendix (≤4 / ≤2 pages) | Strengthens or reassures but does not decide -> appendix | | **Reproducibility / bulk** | Artifact | Needed to *reproduce* but not to *judge* -> artifact | ## What must stay in the body - The **central claims and the measurements that back them** — a headline result relegated to an appendix reads as hidden weakness. - The **key baseline comparison** and how baselines were tuned. - The **central limitation** and how you bound it (argue it where the result lives). - The **eval
- The three tiers
- What must stay in the body
- What the appendix is for
- What the artifact is for
- Common misallocations
- Double-anonymity across tiers
- Output format
What does the conext-supplementary skill do?
Use when deciding what goes in the ACM CoNEXT main body versus the appendix budget versus the artifact — splitting content by decision-criticality so nothing a reviewer needs to accept the paper hides in an appendix or repository, within the acmart limits (long ≤4 appendix pages, short ≤2).
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill conext-supplementary --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.