Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

CIKM Submission · brycewang-stanford | DecimalAI

documentationby brycewang-stanford

CIKM Submission

brycewang-stanford/cikm-submission

Source brycewang-stanford/awesome-journal-skills ↗License MIT

Use when auditing a CIKM submission for EasyChair readiness across the five tracks, covering page budgets with appendices counted inside, the mandatory GenAI Usage Disclosure section, author-reviewer nomination, double-blind rules with arXiv declaration, the abstract-gate authorship freeze, and desk-reject triggers.

SkillScore81Maintained

Automatic

Research pack

Last verified 9/1/2026

What it changes

Passed 21 of 26 test cases with the skill, and 17 of 26 without it.

Without skill65%

With skill81%

Checks it passed that the model alone missed

Flags 11 pages of content as exceeding the 10-page budget.
States that the 10-page limit for Full Research includes appendices.
Notes that references sit outside the Demonstration track page limit.

and 8 more in the full report

6 fixed15 passed either way3 still failing2 broke

Pass-rate lift: +15 pp
Tokens: +40%
Agent turns: 0%
Response time: -19%

Model gemini-3.6-flashMeasured 9/1/2026v121 of 26 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-cikm-submission/SKILL.md https://app.decimal.ai/s/brycewang-stanford-cikm-submission/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-cikm-submission, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/brycewang-stanford-cikm-submission/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-cikm-submission

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-cikm-submission/SKILL.md https://app.decimal.ai/s/brycewang-stanford-cikm-submission/SKILL.md

Raw file: /s/brycewang-stanford-cikm-submission/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-cikm-submission.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

Our Full Research submission has exactly 8 pages of main body, 2 pages of appendix, 1.5 pages of references, and a 0.5 page GenAI disclosure placed between the appendix and references. EasyChair has reviewer nomination completed and no preprints exist. Evaluate using [Verdict], [Track + budget], [Form items], [Compliance], and [Ordered fixes].

What was checked, without and with the skill
Checked	Without skill	With skill
Confirms 10 pages of main text and appendix meets the Full Research track page budget.	Missed	Passed
Confirms correct placement of the GenAI disclosure section before references.	Missed	Passed

case-22 · gemini-3.6-flash · 9/1/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md118 linessingle file

CIKM Submission

A CIKM submission clears three gates that generic conference checklists miss: an EasyChair form with consequences (track selection, reviewer nomination, arXiv declaration), a page budget that counts appendices inside it, and a named GenAI Usage Disclosure section that must physically exist in the PDF. All specifics below are the verified CIKM 2026 rules (source map, 2026-07-08); reopen the current track call and policies page before certifying anything.

Per-track budget card (2026)

Track	Budget	Outside the budget
Full Research	10 pages incl. figures, tables, appendices	up to 2 pages of references + GenAI disclosure
Short Research	4 pages incl. appendix	references + GenAI disclosure
Applied Research	7 pages incl. appendix	references + GenAI disclosure
Resource	4 pages incl. appendices and acknowledgments	references + GenAI disclosure
Demonstration	4 pages incl. appendices and acknowledgments	references + GenAI disclosure

All tracks: ACM proceedings template (two-column), English, PDF. Applied Research additionally requires practical-application evidence — a system launch, data release, or equivalent — as part of the claim, not as decoration.

The EasyChair form is part of the submission

Track selection. Each track has a named EasyChair choice (e.g., "CIKM 2026 Full Research Track"); a paper filed under the wrong track competes under the wrong budget and criteria.
Author-reviewer nomination. Every submission must nominate at least one of its authors to review for the conference, set inside EasyChair at submission time. CIKM 2026 states plainly that failure to nominate leads to desk rejection — treat the nomination as a required field, assign the most senior eligible author, and record who was named.
arXiv declaration. If a non-anonymized version is online, or will go online before notification, that must be declared on the form. Not disclosing an existing public version is itself a desk-reject trigger — the risk is the silence, not the preprint.

GenAI Usage Disclosure section

Track record

Benchmark

21 / 26

test cases passed, vs 17 / 26 without

Adoption

Users: 1
Times used: 18

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

brycewang-stanford / awesome-journal-skills

CIKM-Skills/skills/cikm-submission/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

brycewang-stanford/cikm-review-processUse when reasoning about CIKM peer review — the EasyChair double-blind pipeline, the mixed IR/data-mining/knowledge-management reviewer pool, per-track evaluation criteria, the ACM Peer Review Policy including the no-AI-written-reviews rule, notification timing, and what actually moves borderline decisions.Close match+55 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

CIKM Submission

Per-track budget card (2026)

The EasyChair form is part of the submission

GenAI Usage Disclosure section

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills