Preprocess Document For Llm
技能 活跃Convert a document to markdown and classify it with an LLM in a single pipeline.
To automate the process of preparing documents for LLM analysis by converting them into markdown and then classifying them, saving teams time on manual data normalization.
功能
- Convert various document types to markdown
- Classify documents using an LLM
- Single pipeline for document preprocessing and classification
- Examples in multiple programming languages (Bash, TS, Python, Go)
使用场景
- Automating the processing of incoming documents for backend teams
- Normalizing documents before routing or further analysis
- Classifying documents into categories like invoices, contracts, or reports
非目标
- Performing complex document editing beyond conversion
- Developing custom LLM models for classification
- Providing a GUI for document processing
Security
- warning:Secret ManagementAPI keys are referenced as placeholders ('YOUR_API_KEY', '$ANTHROPIC_API_KEY') in code examples, but their handling and security are not detailed in the documentation, suggesting a potential for insecure practices if not managed carefully by the user.
Versioning
- info:Release ManagementWhile there's a commit date, there's no explicit versioning information (like semver) in the SKILL.md or manifests, and installation instructions point to 'main'.
Code Execution
- info:ValidationThe examples show how to construct API requests, but explicit validation schemas for inputs or outputs are not detailed within the skill's documentation or code snippets.
- info:Error HandlingThe examples show basic API calls, but do not detail specific error handling mechanisms or structured error reporting for failures during document conversion or LLM classification.
Compliance
- info:GDPRThe skill processes document content, which may include personal data, and sends it to external LLM APIs. No specific sanitization for personal data is mentioned.
Errors
- info:Actionable error messagesThe documentation mentions API keys and integration guides, implying error handling is managed by the Iteration Layer and Anthropic APIs, but specific error messages and remediation steps for this skill are not detailed.
Execution
- info:Pinned dependenciesThe SKILL.md includes example scripts with shebangs and references specific interpreter versions in comments or examples (e.g., 'claude-sonnet-4-20250514'), but explicit pinning and lockfiles for dependencies are not evident for the skill's internal components.
Protocol
- info:Idempotent retry & timeoutsThe skill relies on external API calls, and while the APIs themselves likely have timeouts and retry mechanisms, these are not explicitly configured or documented within the skill's scope.
Practical Utility
- info:Edge casesWhile the documentation references an integration guide for error handling, specific edge cases for document conversion (e.g., malformed PDFs) or classification (e.g., ambiguous text) and their recovery steps are not explicitly detailed within the SKILL.md.
安装
请先添加 Marketplace
/plugin marketplace add iterationlayer/skills/plugin install skills@iterationlayer-skills质量评分
类似扩展
Manus
100Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing.
Extract Fleet Vehicle Registration
100Extract vehicle identification, owner details, registration dates, and technical specifications from vehicle registration documents.
Iterationlayer
98Integrate Iteration Layer APIs for document, website, image, and sheet processing. Composable APIs — Document Extraction, Website Extraction, Document to Markdown, Image Transformation, Image Generation, Document Generation, and Sheet Generation — share one credit pool and chain together into workflows.
Extract Rental Application
98Extract applicant details, employment history, income, and references from a rental application form into structured JSON for tenant screening.
Google Drive Skill
100Interact with Google Drive - search files, find folders, list contents, download files, upload files, create folders, move, copy, rename, and trash files. Use when user asks to: search Google Drive, find a file/folder, list Drive contents, download or upload files, create folders, move files, or organize Drive content. Lightweight integration with standalone OAuth authentication supporting full read/write access.
Generate Epub Book
100Generate a complete EPUB e-book with chapters, table of contents, and rich text formatting.