Use when auditing an ACM CHI Papers submission for PCS readiness, covering the September full-paper deadline, the anonymized single-column template, word-count norms instead of page limits, subcommittee designation, supplementary and video upload, anonymization of external links, and CHI's desk-reject triage before upload.
SkillScore83Maintained
Automatic
◆Research pack
Last verified 8/15/2026
What it changes
Passed 19 of 23 test cases with the skill, and 10 of 23 without it.
Without skill43%
With skill83%
Checks it passed that the model alone missed
identifies consent forms as high-risk items for accidental identity leaks
uses texcount with the -inc flag to sum word counts across LaTeX source files
places subcommittee selection as the first step before freezing the manuscript
and 6 more in the full report
9 fixed10 passed either way4 still failing0 broke
Pass-rate lift
+39 pp
Tokens
+48%
Agent turns
0%
Response time
-28%
Model gemini-3.6-flashMeasured 8/15/2026v119 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 9
Prompt
When filling out the PCS submission form for CHI, how many subcommittee choices are authors permitted to designate, and when in the workflow should this decision be finalized?
What was checked, without and with the skill
Checked
Without skill
With skill
states that authors may designate up to two subcommittee choices
Passed
Passed
places subcommittee selection as the first step before freezing the manuscript
Missed
Passed
case-14 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md101 linessingle file
CHI Submission
Run this audit before uploading to PCS (Precision Conference Solutions) — CHI does not
use OpenReview or CMT. Every date and cap below was read from the CHI 2027 Papers pages
on 2026-07-08 through search-engine renderings (direct fetches of chi2027.acm.org
were blocked in the verification environment); reopen the live pages before acting on
any number.
What the CHI 2027 cycle posted
Full Papers deadline: Thursday, September 10, 2026, on PCS, including videos and
supplementary materials — CHI collects everything on one date, unlike venues with a
later supplement window. No separate abstract-registration deadline was found for
2027; confirm on the live page rather than assuming (待核实).
Review format: the single-column ACM submission template (CHI has used
single-column reviewing since 2021). The two-column look happens later, in TAPS.
Length is governed by words, not pages. The posted norm: roughly 5,000–8,000 words
for a typical paper (excluding references), submissions at or above 12,000 words
face extra scrutiny and desk rejection when the length is not justified, and papers of
about 5,000 words or fewer are welcomed as short papers reviewed with expectations
commensurate with their size. CHI's standing phrase is that a paper should be the
length appropriate to its contribution.
The submission form requires you to designate a reviewing subcommittee (up to two
choices) — a strategic decision, not paperwork; see chi-topic-selection.
Anonymization is mandatory and extends beyond the PDF: supplemental materials and
external links to datasets or code repositories that reveal identity are posted
desk-reject grounds.
The anonymization trap specific to CHI
CHI's policy is anonymized review of an HCI paper, which creates leak channels that ML
venues rarely have: consent-form headers naming the lab, screenshots of a deployed
system showing a university logo, video figures with a narrator saying "at our
institution," OSF or GitHub links registered to a named account, and app-store pages
for the studied prototype. Cite your own prior studies in the third person and keep
the citation; scrub everything else.
# Mechanical pre-upload sweep on the PCS package
pdfinfo paper.pdf | grep -Ei 'author|creator|producer' # PDF metadata identity