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 Azhi-ss/academic-figure-skills --skill academic-figure-draft-analyzergit clone --depth 1 https://github.com/Azhi-ss/academic-figure-skillsWrote 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/azhi-ss/academic-figure-skills/academic-figure-draft-analyzer)<a href="https://agentmods.dev/skills/azhi-ss/academic-figure-skills/academic-figure-draft-analyzer"><img src="https://agentmods.dev/badge/skills/azhi-ss/academic-figure-skills/academic-figure-draft-analyzer/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/azhi-ss/academic-figure-skills/academic-figure-draft-analyzer"><img src="https://agentmods.dev/badge/skills/azhi-ss/academic-figure-skills/academic-figure-draft-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 22 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00052 | $0.01784 |
| Opus 5 | $0.00026 | $0.00892 |
| Sonnet 5 | $0.00010 | $0.00357 |
| Haiku 4.5 | $0.00005 | $0.00178 |
Grade A, and why
academic-figure-draft-analyzer 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 12d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Academic Draft and Paper Analyzer (Figure Planner)
Produce a human-readable figure strategy and a machine-readable Figure Plan v1. Plan figures around the paper's claims and reader questions, not around a fixed count or a generic pipeline template.
Read references/missing-info-policy.md when the paper is incomplete. If a repository handoff or extracted reference-style profile exists, carry it forward without renaming fields.
Dual-Track Planning Workflow
The analyzer operates in one of two modes depending on the input:
- Draft-to-Figure Fast-Track (草稿敏捷直出):
- Trigger: Input is notes, an outline, or an early draft (Markdown, text, or draft sections) without complete experimental/analysis results.
- Target: Focus exclusively on Figure 1: Overall Framework / Methodology Overview.
- Policy: Do NOT force a multi-figure plan (ablation/data behavior). Do NOT warn about missing experimental/analysis sections.
- Camera-Ready Multi-Figure Plan (完整定稿多图规划):
- Trigger: Input is a complete manuscript with experimental results (Markdown, LaTeX, PDF, or full text).
- Target: Systematically plan the multi-figure suite with claim verification and publication constraints.
Input contract
- Prefer: manuscript text or source, abstract, method, experiments, target venue/page limit, semantic architecture handoff, and any reference figures.
- Accept: Markdown (
.md) draft or notes, outline, title plus abstract, local PDF, paper URL/HTML, Word/LaTeX. - A URL is a paper source only after its content is inspected; do not classify every URL as a code repository.
- If a PDF or webpage cannot be read in the current environment, report that limitation rather than inventing paper structure.
Output contract
Include:
- Paper overview: question, contribution, evidence, and intended venue constraints.
- Completeness statement: sections and artifacts actually inspected.
- Per-figure recommendation with a controlled type and
must,strong, ornicepriority (in Draft mode, emit exactly one primary Figure 1). - A one-sentence communication goal: what the reader should understand after viewing the figure.
- Required nodes, edges, authority boundaries, and forbidden implications.
- Aspect ratio and final publication width hint.
Figure Plan v1JSON.
What ships with it
2 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.
- 12d ago First seen · 152 lines · 52 tokens per session scan A cbc0ba823af3
academic-figure-draft-analyzer is a skill published in the GitHub repository Azhi-ss/academic-figure-skills (103 stars, last pushed 9d ago), licensed MIT. It adds 52 tokens to every session and 1,784 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
ml-paper-writing
Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification…
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, conducting literature reviews, finding related work, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, citation verification workflows, and paper…
paper-read
Read, analyze, and extract knowledge from academic papers. Handles PDFs and arXiv links. Produces structured summaries, identifies core contributions, evaluates methodology, and enables cross-paper comparison.