develata/math-extractor
My-Skills/math-extractor/SKILL.md
Extracts strictly mathematical terms (Definitions, Theorems, Lemmas, Propositions, Proofs) from documents (PDF, MD, TEX, TXT), handling PDF conversion and AI-based cleaning. Use when the user wants to extract math content from a file.
documentation
Updated Apr 30, 2026
$ install --global
skillsauthnpx skillsauth add develata/deve-skills math-extractorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 30, 2026, 3:17 AM12.5s3 files scanned
SKILL.md
- name:
- math-extractor
- description:
- Extracts strictly mathematical terms (Definitions, Theorems, Lemmas, Propositions, Proofs) from documents (PDF, MD, TEX, TXT), handling PDF conversion and AI-based cleaning. Use when the user wants to extract math content from a file.
Math Extractor
This skill extracts mathematical definitions, theorems, lemmas, propositions, and proofs from documents.
Input Schema
<input_schema>
<file_path>Path to the source file (pdf/md/tex/txt)</file_path>
</input_schema>
Logic & Workflow
The Agent must follow this Chain of Thought (CoT):
- Env Check: First, verify that
scripts/processor.pycan access the necessary API keys (MinerU & LLM) from the environment. If missing, return a configuration error. - Validation: Check file extension. If not .pdf/.md/.tex/.txt, return "不支持当前文件格式".
- Conversion:
- If PDF: Call
convert_pdf. The script internally uses the pre-configured MinerU key. - If conversion fails (or key missing), return "未设定好pdf转化为md的工具".
- If PDF: Call
- Preprocessing:
- Call
clean_and_chunk(implemented inclean_content). - Aggressively remove images, TOCs, and References to save tokens.
- Call
- Extraction (Batch AI):
- Call
batch_extract_math(implemented inbatch_extract). - The script uses the pre-configured LLM credentials to process chunks in parallel.
- Call
- Merge & Output:
- Save to
{filename}_extracted.mdand return the path.
- Save to
Usage
To use this skill, execute the python script with the file path.
Required Environment Variables:
EXTRACTION_API_KEY: API Key for LLM (e.g., OpenAI, DeepSeek).EXTRACTION_BASE_URL: Base URL for LLM API (default:https://api.openai.com/v1).
Optional Environment Variables:
MINERU_API_KEY: Required only for PDF conversion.MINERU_BASE_URL: Base URL for MinerU API (default:https://api.mineru.com/v1).LLM_MODEL: Model name to use (default:gpt-4o).
python scripts/processor.py <file_path> <output_directory>
Features
- Robust PDF Conversion: Uses MinerU for high-quality PDF to Markdown conversion.
- Smart Chunking: Splits text by paragraphs to avoid breaking math formulas.
- Cost Optimization: Heuristically filters out non-math chunks to save tokens.
- Math Protection: Whitelists safe HTML tags to prevent accidental deletion of math inequalities (e.g.,
a < b). - Encoding Fallback: Automatically tries UTF-8, GBK, and Latin-1 encodings.
- Retry Logic: Built-in retries for API calls to handle network instability.
Related Skills
develata/codex-tokens
tools
VerifiedTrustedCommunity
Collect and audit Codex token usage with a bundled Python CLI and optional Windows batch launchers. Use this skill when the user asks to check Codex token usage, generate daily token audit logs, calculate monthly CostUSD totals, review Codex spending, or run Codex token usage scripts on Windows, Bash, WSL, or Linux.
SKILL.mdUpdated May 30, 2026
develata/user-explanation-5step
tools
VerifiedTrustedCommunity
Use when giving the user an INLINE reply that carries a trade-off, a decision, a verdict, or a non-trivial finding (decision brief / round verdict / failure root-cause). NOT for "done"/status confirmations, one-line answers, or pure data dumps. Forces a compact decision-brief shape and blocks internal tool-name / file-path bleed into user-facing text.
SKILL.mdUpdated May 30, 2026
develata/terminology-audit
development
VerifiedTrustedCommunity
Use for cross-file or cross-chapter terminology audits and corpus-wide term unification in thesis/paper sources — extract candidate term drift, build a decision queue, classify each occurrence, apply accepted replacements safely, and verify counts/build. Trigger on "术语审计", "术语统一", "术语一致性", "逐词审", "这个词全文怎么用", "把 X 全文改成 Y", "terminology audit", or "unify term X". Do NOT use for ordinary prose drafting or a single known-location edit; use academic-writing for prose quality and claim-boundary judgment.
SKILL.mdUpdated May 30, 2026
develata/codex-dispatch-watchdog
tools
VerifiedTrustedCommunity
Use for ANY codex CLI dispatch via dispatch wrapper (no time threshold; presence-of-risk triggers, not estimated wall — stdin-EOF stalls occur at <60s). Combines internal log-inactivity watchdog wrapper + external Claude-session cron probe + sentinel hook enforcement. Detects stalls in ≤60-270s vs hours-without-detection failure mode.
SKILL.mdUpdated May 30, 2026