paper-illustration
Generate publication-quality AI illustrations for academic papers using Gemini image generation.
Skill by wanshuiyin
Chalk Labs
Need help deploying paper-illustration?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code. Read the repository before you give any tool access to your data.
npx agentmarket install skill/wanshuiyin-paper-illustration
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/paper-illustration
Tools it pre-approves 9
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(*),Read,Write,Edit,Grep,Glob,mcp__codex__codex,mcp__codex__codex-reply,WebSearch
What's inside
- Skill name
paper-illustration- Description
- Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
- License
- MIT
- Allowed tools
- Bash(*),, Read,, Write,, Edit,, Grep,, Glob,, mcp__codex__codex,, mcp__codex__codex-reply,, WebSearch
- Instructions
- 731 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
- Instructions call the network
Agent Skills spec issues
- body: 731 lines (spec recommends under 500)
Files (1)
- SKILL.md
SKILL.md (first lines)
# Paper Illustration: Multi-Stage Claude-Supervised Figure Generation
Generate publication-quality illustrations using a **multi-stage workflow** with **Claude as the STRICT supervisor/reviewer**.
## Core Design Philosophy
```
┌──────────────────────────────────────────────────────────────────────────┐
│ MULTI-STAGE ITERATIVE WORKFLOW │
├──────────────────────────────────────────────────────────────────────────┤
│ │
│ User Request │
│ │ │
│ ▼ │
│ ┌─────────────┐ │
│ │ Claude │ ◄─── Step 1: Parse request, create initial prompt │
│ │ (Planner) │ │
│ └──────┬──────┘ │
│ │ │
│ ▼ │
│ ┌─────────────┐ │
│ │ Gemini │ ◄─── Step 2: Optimize layout description │
│ │ (gemini-3-pro)│ - Refine component positioning │
│ │ Layout │ - Optimize spacing and grouping │
│ └──────┬──────┘ │
│ │ │
│ ▼ │
│ ┌─────────────┐ │
│ │ Gemini │ ◄─── Step 3: CVPR/NeurIPS style verification │
│ │ (gemini-3-pro)│ - Check color palette compliance │
│ │ Style │ - Verify arrow and font standards │
│ └──────┬──────┘ │
│ │ │
│ ▼ │
│ ┌─────────────┐ │
│ │ Paperbanana │ ◄─── Step 4: Render final image │
│ │ (gemini-3- │ - High-quality image generation │
│ │ pro-image) │ - Internal codename: Nano Banana Pro │
│ └──────┬──────┘ │
│ │ │
│ ▼ │
│ ┌─────────────┐ │
│ │ Claude │ ◄─── Step 5: STRICT visual review + SCORE (1-10) │
│ │ (Reviewer) │ - Verify EVERY arrow direction │
│ │ STRICT! │ - Verify EVERY block content │
│ └──────┬──────┘ - Verify aesthetics & visual appeal │
│ │ │
│ ▼ │
│ Score ≥ 9? ──YES──► Accept & Output │
│ │ │
│ NO │
│ │ │
│ ▼ │
│ Generate SPECIFIC improvement feedback ──► Loop back to Step 2 │
│ │
└──────────────────────────────────────────────────────────────────────────┘
```
## Constants
- **IMAGE_MODEL = `gemini-3-pro-image-preview`** — Paperbanana (Nano Banana Pro) for image rendering
- **REASONING_MODEL = `gemini-3-pro-preview`** — Gemini for layout optimization and style checking
- **MAX_ITERATIONS = 5** — Maximum refinement rounds
- **TARGET_SCORE = 9** — Minimum acceptable score (1-10) — RAISED FOR QUALITY
- **OUTPUT_DIR = `figures/ai_generated/`** — Output directory
- **API_KEY_ENV = `GEMINI_API_KEY`** — Environment variable
## Optional: Style reference (`— style-ref: <source>`, opt-in)
Lets the user steer **structural** figure conventions (caption length, panel-count distribution, figure-to-table ratio in the parent paper) toward a reference paper. **Default OFF — when the user does not pass `— style-ref`, do nothing differently from before.**
Only when `— style-ref: <source>` appears in `$ARGUMENTS`, run the helper FIRST, before generating prompts:
```bash
# Resolve $STYLE_HELPER via the canonical strict-safe chain (see
# shared-references/integration-contract.md §2). Policy A — gate:
# unresolved helper means --style-ref cannot be satisfied, so abort.
cd "$(git rev-parse --show-toplevel 2>/dev/null || pwd)" || exit 1
if [ -z "${ARIS_REPO:-}" ] && [ -f .aris/installed-skills.txt ]; then
ARIS_REPO=$(awk -F'\t' '$1=="repo_root"{print $2; exit}' .aris/installed-skills.txt 2>/dev/null) || true
fi
if [ -z "${ARIS_REPO:-}" ] && [ -f "$HOME/.aris/repo" ]; then
ARIS_REPO=$(cat "$HOME/.aris/repo" 2>/dev/null) || true
fi
STYLE_HELPER=".aris/tools/extract_paper_style.py"
[ -f "$STYLE_HELPER" ] || STYLE_HELPER="tools/extract_paper_style.py"
[ -f "$STYLE_HELPER" ] || { [ -n "${ARIS_REPO:-}" ] && STYLE_HELPER="$ARIS_REPO/tools/extract_paper_style.py"; }
[ -f "$STYLE_HELPER" ] || {
echo "ERROR: extract_paper_style.py not resolved at .aris/tools/, tools/, \$ARIS_REPO/tools/, or via ~/.aris/repo." >&2
echo " Fix: rerun bash tools/install_aris.sh or smart_update.sh (refreshes ~/.aris/repo), export ARIS_REPO, or copy the helper to tools/." >&2
echo " --style-ref cannot be satisfied; aborting." >&2
exit 1
}
STYLE_STATUS=0
CACHE=$(python3 "$STYLE_HELPER" --source "<source>") || STYLE_STATUS=$?
case "$STYLE_STATUS" in
0) ;; # use $CACHE/style_profile.md as structural guidance
2) echo "warning: style-ref skipped (missing optional dep)" >&2 ;;
3) echo "error: --style-ref source failed; aborting illustration" >&2 ; exit 1 ;;
*) echo "error: helper failed unexpectedly; aborting illustration" >&2 ; exit 1 ;;
esac
```
Sources accepted: local TeX dir / file, local PDF, arXiv id, http(s) URL. Overleaf URLs/IDs are rejected — clone via `/overleaf-sync setup <id>` first and pass the local clone path.
**Strict rules** (full contract in `tools/extract_paper_style.py` docstring):
- Use `style_profile.md` to align caption length and figure density with the reference paper. The CVPR/ICLR/NeurIPS visual standards above still take precedence — `--style-ref` only refines length-and-density tendencies, never image content.
- **Never copy figure content, color palettes, or specific design elements** from anything reachable through the cache. The visual design comes from the user's prompt, not the reference.
- **Never pass `— style-ref` (or the cache contents) to the Claude vision-checker / Gemini reasoning-checker sub-agents** when they score the generated image — the image must be judged on its own merits.
## CVPR/ICLR/NeurIPS Top-Tier Conference Style Guide
**What "CVPR Style" Actually Means:**
### Visual Standards
- **Clean white background** — No decorative patterns or gradients (unless subtle)
- **Sans-serif fonts** — Arial, Helvetica, or Computer Modern; minimum 14pt
- **Subtle color palette** — Not rainbow colors; use 3-5 coordinated colorsFrom wanshuiyin/Auto-claude-code-research-in-sleep, MIT.
More from wanshuiyin/Auto-claude-code-research-in-sleep
- 0.699score
figure-spec
wanshuiyin
Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG.
SkillAFreshness: A★ 18KClaude Code +9 - 0.699score
paper-illustration-image2
wanshuiyin
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation.
SkillAFreshness: A★ 18KClaude Code - 0.699score
proof-orchestrator
wanshuiyin
Manage a stateful, run-directory-based proof project with Codex: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when…
SkillAFreshness: A★ 18KClaude Code +9 - 0.699score
render-html
wanshuiyin
Render an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed…
SkillAFreshness: A★ 18KClaude Code +9 - 0.699score
proof-orchestrator
wanshuiyin
Manage a stateful, run-directory-based proof project: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local…
SkillAFreshness: A★ 18KClaude Code - 0.699score
paper-poster-html
wanshuiyin
DEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real…
SkillAFreshness: A★ 18KClaude Code - 0.699score
lean-formalize
wanshuiyin
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement.
SkillAFreshness: A★ 18KClaude Code - 0.695score
experiment-queue
wanshuiyin
SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention.
SkillAFreshness: A★ 18KClaude Code - 0.694score
arxiv
wanshuiyin
Search, download, and summarize academic papers from arXiv.
SkillAFreshness: A★ 18KClaude Code +9 - 0.694score
claims-drafting
wanshuiyin
Draft patent claims for an invention.
SkillAFreshness: A★ 18KClaude Code - 0.694score
analyze-results
wanshuiyin
Analyze ML experiment results, compute statistics, generate comparison tables and insights.
SkillAFreshness: A★ 18KClaude Code +9 - 0.694score
alphaxiv
wanshuiyin
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback.
SkillAFreshness: A★ 18KClaude Code +9
Signals
- Stars
- 18,007
- Forks
- 1,488
- Open issues
- 58
- Last commit (this folder)
- Jul 14, 2026 (3 months ago)
- Last release
- Sep 28, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.353score
paper-illustration
yvesory
Generate publication-quality AI illustrations for academic papers using Gemini image generation.
SkillBFreshness: B★ 19Claude Code - 0.285score
paper-illustration
AI4Scientist
Generate publication-quality AI illustrations for academic papers using Gemini image generation.
SkillCFreshness: C★ 128Claude Code
More from wanshuiyin
- 0.699score
paper-poster-html
wanshuiyin
DEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real…
SkillAFreshness: A★ 18KClaude Code - 0.699score
paper-illustration-image2
wanshuiyin
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation.
SkillAFreshness: A★ 18KClaude Code - 0.699score
lean-formalize
wanshuiyin
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement.
SkillAFreshness: A★ 18KClaude Code - 0.699score
figure-spec
wanshuiyin
Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG.
SkillAFreshness: A★ 18KClaude Code +9 - 0.699score
proof-orchestrator
wanshuiyin
Manage a stateful, run-directory-based proof project: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local…
SkillAFreshness: A★ 18KClaude Code - 0.699score
render-html
wanshuiyin
Render an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed…
SkillAFreshness: A★ 18KClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get paper-illustration running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
paper-illustration skill. Agent Mart. https://agentmart.dev/skills/wanshuiyin-paper-illustration (last updated 2026-10-24)