Turn a research paper into a conference poster using its figures and findings. Produce one HTML/CSS file and a print-ready PDF, with measured layout checks and Gemini reviews of content accuracy and final appearance.
DEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-hue design-token system, and print-ready PDF via headless Chromium. Use when the user says "做海报", "poster", "conference poster", "paper poster", or asks to design/redo a research poster.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Override for Codex users who want Gemini, not a second Codex/Codex-MCP reviewer, to act as the reviewer. Install this package after
skills/skills-codex/*.
Gemini overlay assurance:
review_independence: cross-familyandacceptance_status: accepted.
One HTML file styled for an exact print canvas (@page { size: W H }), rendered to PDF
via Playwright print emulation. Iterate by measuring, not eyeballing — the screen
preview lies; only print emulation at the correct viewport tells the truth. Core gate
machinery is adapted from posterly (MIT, ©
2026 Ruishuo Chen — see NOTICE.md and LICENSES/posterly-MIT.txt in the mainline
skill directory); ARIS adds style discipline gates, figure-provenance gates, the
cross-model review loop, and the anti-patch-loop fix vocabulary.
This overlay is identical to skills/skills-codex/paper-poster-html/ except that the
two cross-model review calls go to Gemini through the local gemini-review MCP
bridge instead of a spawned GPT reviewer agent. Follow the base mirror for everything
not restated here (phases, gates, fix vocabulary, figure provenance, output contract).
gemini-review — Gemini invoked through the local
gemini-review MCP bridge.mcp__gemini-review__review_start; never reuse a prior review job across review
boundaries. Save the returned jobId, poll mcp__gemini-review__review_status with
a bounded waitSeconds until done=true, and treat the completed payload's
response as the reviewer output.imagePaths.gemini-review bridge is unavailable, stop and tell the user what to
configure. Do not silently degrade the cross-model reviews into self-review.mcp__gemini-review__review_start:
prompt: |
Audit a conference-poster content plan against its source paper.
## Poster content plan
[PASTE poster_html/POSTER_CONTENT_PLAN.md]
## Paper source (relevant sections)
[PASTE the paper sections backing the plan's claims — abstract, headline
results tables, method equations, theorem statements]
For EVERY claim, number, equation, and attribution in the plan, output one row:
| claim on poster | paper location | paper says (verbatim) | match? |
with match ∈ {OK, NUMERIC-MISMATCH, OVERCLAIM, MISSING-PRECONDITION,
NOT-IN-PAPER, SCOPE-NARROWED}. End with a count per category.
Poll review_status until done=true; save the response to
poster_html/CLAIM_EVIDENCE.md. Fix every non-OK row or record it as a
user-acknowledged tradeoff.
All hard gates PASS + polish warnings zero-or-waived + executor visual score ≥ 9 first. Then:
mcp__gemini-review__review_start:
imagePaths: ["poster_html/poster_preview.png"]
prompt: |
Final print-readiness audit of a conference poster (image attached).
## Final poster text content
[PASTE the text content extracted from poster_html/poster.html]
## Gate report summary
[PASTE the overall/hard_failures/warnings fields of poster_html/GATE_REPORT.json]
## Claim→evidence audit
[PASTE poster_html/CLAIM_EVIDENCE.md]
Check: (1) fidelity & overclaims RE-CHECKED on the final text (polish introduces
new claims), (2) residue (\ref{, TODO, raw < in math, missing images, remote
URLs), (3) visual rhetoric (headline numbers prominent, banner readable from
2 m, two-hue discipline, real paper figures central and inside their cards),
(4) gate-log coherence.
Verdict: PRINT-READY or NEEDS-FIX with a numbered, severity-ordered issue list.
Poll mcp__gemini-review__review_status with a bounded waitSeconds until done=true;
treat the completed payload's response as the reviewer verdict.
The reviewer recommends; it does not edit. Any fix → back through Phase 4/5 gates — never straight to re-review.
Save both review jobs' raw responses per ../../shared-references/review-tracing.md to
.aris/traces/paper-poster-html/<date>_run<NN>/.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Plan ablation studies, experiments that remove or replace parts of a machine learning method to test their contribution. Define reviewer questions, expected outcomes, priorities, execution order, and compute estimates, then implement experiments and record findings.
Plan and run ablation studies, experiments that remove or replace parts of a method to test their contribution. Organize reviewer questions, priorities, expected outcomes, and compute costs, then record results and findings.
Understand a single arXiv paper through an AlphaXiv summary, with full text and LaTeX source available when needed. Use it to identify key findings or ask specific questions about methods, experiments, and equations.
Compare machine learning experiment results from JSON or CSV files. Calculate improvements over a baseline, summarize variation across repeated runs, identify trends and unusual results, and suggest experiments to test possible explanations.
Search arXiv papers by topic or paper ID, review authors and abstracts, and summarize contributions stated in the abstracts. Download selected papers or all search results as PDFs to build a local paper library.
Improve a compiled LaTeX paper through two rounds of Claude review, edits, and recompilation. The workflow addresses inconsistent reasoning, unsupported claims, unclear writing, and visual presentation, while keeping a cumulative log of changes.