Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add CHENyiru3/AI-Skills-Collections --skill scientific-figure-polishgit clone --depth 1 https://github.com/CHENyiru3/AI-Skills-CollectionsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chenyiru3/ai-skills-collections/scientific-figure-polish)<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/scientific-figure-polish"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/scientific-figure-polish/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/scientific-figure-polish"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/scientific-figure-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.01500 |
| Opus 5.5 | $0.00027 | $0.00600 |
| Sonnet 5.5 | $0.00014 | $0.00300 |
| Haiku 4.5 | $0.00007 | $0.00150 |
Grade A, and why
scientific-figure-polish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scientific Figure Polish
Apply the user's FEAST-derived figure style: compact, organized, readable, and scientifically faithful. Current user instructions override these defaults. Read style-reference.md for visual conventions and examples. For direct PDF edits, also read pdf-editing.md and use the available PDF skill for its format-specific requirements.
Priorities
- Preserve scientific meaning and the author's current edits.
- Retain the original figure's compact density and organize the content on a clear grid.
- Match the size and alignment of comparable units.
- Make equivalent text levels consistent and readable.
Tighten internal gaps before extending the artwork; cropping outside margins alone does not fix a loose composition. Preserve compactness jointly with readability.
Compactness and readability are joint constraints. If larger text does not fit, first share repeated annotations, repair wrapping, reduce gaps, or rebalance groups. Do not force the old footprint with unreadable text or overlaps. Use the smallest necessary geometry adjustment and explain a material expansion; changing scientific content requires separate justification.
Establish the current baseline
- Inspect the actual current artwork before editing. The author also modifies files manually. When replacing shared or manually edited artwork, retain a recoverable baseline and check for intervening author edits; hashes can help identify the exact source. A read-only review does not need a backup workflow.
- Treat the latest author-approved artwork as authoritative. Plotting sources or retained component figures may predate manual changes. Rebuild only when their scientific content and author adjustments can be preserved.
- For density comparisons, “original” defaults to the current supplied figure before this edit. If the author identifies an earlier version as the compactness reference, use that version's organization while preserving the current scientific content and manual edits.
- Review every unit in the requested scope. An all-figure scan includes main and supplementary figures; a named-figure request stays within that scope.
- Render the whole figure and inspect dense details. Identify panel roles, comparable families, annotation levels, and the original density before changing geometry.
- Optionally use scripts/figure_inventory.py for a read-only PDF inventory and review previews. Its measurements support inspection; they do not prove correct alignment or scientific fidelity.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 68 lines · 68 tokens per session scan A 5d253eaa659e
scientific-figure-polish is a skill published in the GitHub repository CHENyiru3/AI-Skills-Collections (2 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 1,500 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-11.
scientific-figure-polish compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| scientific-figure-polishCHENyiru3/AI-Skills-Collections | Skill | 2 | 3d ago | MIT | A | 68 | Claude Code, Codex |
| scientific-schematicsK-Dense-AI/scientific-agent-skills | Skill | 57k | 5d ago | MIT | A | 68 | Claude Code |
| paper-poster-htmlwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | today | MIT | A | 107 | Claude Code |
| latex-postersforyourhealth111-pixel/Vibe-Skills | Skill | 3.8k | 5d ago | Apache-2.0 | A | 53 | Claude Code |
| figure-composercompanion-inc/feynman | Skill | 10k | 7d ago | MIT | A | 42 | Claude Code, Codex |
| paperFigWUBING2023/PaperSpine | Skill | 6.3k | today | MIT | A | 126 | Claude Code, Codex |
| schematicssynthetic-sciences/openscience | Skill | 4.4k | yesterday | Apache-2.0 | A | 134 | Claude Code |