Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/pantheon-org/tekhnenpx agentmods add skills/pantheon-org/tekhne/sci-data-extractorWrote 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/pantheon-org/tekhne/sci-data-extractor)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/sci-data-extractor"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/sci-data-extractor/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/pantheon-org/tekhne/sci-data-extractor"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/sci-data-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 106 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.
- medium Excessive Agency · line 130 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00096 | $0.01596 |
| Opus 5.5 | $0.00038 | $0.00638 |
| Sonnet 5.5 | $0.00019 | $0.00319 |
| Haiku 4.5 | $0.00010 | $0.00160 |
Grade A, and why
sci-data-extractor 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 1mo 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sci-Data-Extractor
AI-powered tool for extracting structured data from scientific literature PDFs. Converts tables, figures, and text from research papers into Markdown tables or CSV files using PyMuPDF (free) or Mathpix OCR (high-precision) plus an LLM extraction layer.
When to Use
- Extracting enzyme kinetics parameters (Km, Kcat, Kcat/Km) from biochemistry papers
- Converting experimental result tables from PDFs to structured CSV or Markdown
- Building a literature review dataset from multiple paper PDFs
- Batch-processing a folder of PDFs into a unified dataset
- Parsing complex tables or chart data points that require AI assistance
When Not to Use
- The paper is already in a machine-readable format (XML, JSON, HTML) — parse it directly
- You only need the abstract or title — use
semantic-scholar-searchinstead - The PDF is scanned at low resolution with no embedded text and Mathpix is unavailable — results will be unreliable
- You need real-time citation counts or DOI resolution — use
semantic-scholar-search
Mindset
Data extraction from PDFs is a pipeline with multiple failure points — always validate each stage.
- OCR first, extraction second: a gotcha is assuming PyMuPDF handles all PDFs equally. Scanned images, complex multi-column layouts, and formula-heavy pages are a known pitfall — switch to Mathpix for high-precision needs or pre-inspect output before running AI extraction.
- Prompts determine quality: the AI extraction layer is only as good as the extraction prompt. ALWAYS review the raw LLM output before saving; consider that ambiguous column headers or merged table cells can silently corrupt extracted values.
- Batch is not atomic: a production gotcha is treating batch runs as pass/fail. ALWAYS check the per-file success log; failed files are listed at the end and must optionally be re-run individually.
Workflow
1. Install dependencies (first run only)
What ships with it
27 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.
- .audits/2026-04-10/analysis.md 1.2 KB
- .audits/2026-04-10/audit.json 504 B
- .audits/2026-10-02/Analysis.md 497 B
- .audits/2026-10-02/audit.json 560 B
- .audits/2026-10-02/Remediation.md 1.2 KB
- .audits/latest 10 B
- evals/instructions.json 4.6 KB
- evals/scenario-1/capability.txt 50 B
- evals/scenario-1/criteria.json 2.3 KB
- evals/scenario-1/task.md 511 B
- evals/scenario-2/capability.txt 58 B
- evals/scenario-2/criteria.json 2.5 KB
- evals/scenario-2/task.md 577 B
- evals/scenario-3/capability.txt 60 B
- evals/scenario-3/criteria.json 2.6 KB
- evals/scenario-3/task.md 612 B
- evals/scenario-4/capability.txt 129 B
- evals/scenario-4/criteria.json 2.3 KB
- evals/scenario-4/task.md 574 B
- evals/scenario-5/capability.txt 117 B
- evals/scenario-5/criteria.json 2.2 KB
- evals/scenario-5/task.md 547 B
- evals/summary.json 1.1 KB
- references/setup-and-troubleshooting.md 2.9 KB
- requirements.txt 272 B
- scripts/batch_extract.py 4.9 KB runs code
- scripts/extractor.py 17 KB runs code
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.
- 1mo ago First seen · 142 lines · 96 tokens per session scan A ea35d1cd0244
sci-data-extractor is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 1,596 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
slides-as-code
Build research slides with text-first source (Slidev/Marp/Reveal/Quarto) and reproducible export (PDF). Includes structure, figure reuse rules, and quality checklist for top-tier scientific presentations.
arxiv-preflight
Pre-submission validation audit for arXiv papers across TeX source, PDF, figures, metadata, bibliography, file organization, and common-error scans. Produces pass/fail report with specific fixes per arXiv requirement. Triggers on: "check my arXiv submission", "validate for arXiv", "arXiv preflight", "ready for arXiv"…
paper2slides
Turn an academic paper PDF into a presentation deck (.pptx) end-to-end. Use this skill whenever the user wants to "make slides from a paper", "generate a deck from this PDF", "make a PPT from this paper", "generate slides from a PDF document", "make a deck from a research paper", or supplies a research paper PDF and…
LaTeX工具
A tool for creating, compiling, and checking mathematical modelling papers written in LaTeX, a document system often used for technical writing.
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…
glmocr-formula
Official skill for recognizing and extracting mathematical formulas from images and PDFs into LaTeX format using ZhiPu GLM-OCR API. Supports complex equations, inline formulas, and formula blocks. Use this skill when the user wants to extract formulas, convert formula images to LaTeX, or OCR mathematical expressions.