Instructions file CodexOpenCode
AGENTS.md instructions for SoMarkAI/skills, covering agents.md, project overview, repository structure, key architecture differences between skills and running the scripts.
Instructions file CodexOpenCode
AGENTS.md instructions for SoMarkAI/skills, covering agents.md, project overview, repository structure, key architecture differences between skills and running the scripts.
Instructions file
Claude Code instructions for SoMarkAI/skills, covering claude.md, project overview, repository structure, key architecture differences between skills and running the scripts.
Skill Claude CodeCodex
Review contracts and legal agreements (PDF, Word, images) for risks, unfair clauses, missing provisions, and key obligations using SoMark for accurate document parsing. Provides structured risk analysis with severity ratings. Requires SoMark API Key (SOMARKAPIKEY).
Skill Claude CodeCodex
Compare two documents (PDF, Word, images, PPT) and generate a structured diff report highlighting what changed, what was added, and what was removed. Uses SoMark to parse both documents first for accurate structure-aware comparison. Requires SoMark API Key (SOMARKAPIKEY).
Skill Claude CodeCodex
Analyze financial reports and research notes (PDF, Word, images) to extract key financial metrics, profitability trends, risk signals, and management commentary. Uses SoMark to accurately parse complex financial tables, multi-column layouts, and charts before AI analysis. Ideal for earnings analysis, equity research…
Skill Claude CodeCodex
Get a nested catalog tree from documents supported by SoMark or from SoMark JSON. Use for requests such as 文档目录、目录树、文档大纲、章节层级 or catalog tree; do not use for filesystem directory listings.
Skill Claude CodeCodex
Localize HTTP(S) images in SoMark Markdown into ZIP-like directory packages for one Markdown file or a batch of .md/.markdown files. Use when a user needs to persist SoMark object-storage image URLs, replace remote Markdown image links with local relative paths, produce images plus rewritten Markdown without creating…
Skill Claude CodeCodex
Parse text and coordinates from images with SoMark (character/word/line positions on original image). Ideal for OCR-first image understanding where location matters. Requires SoMark API Key (SOMARKAPIKEY).
Skill Claude CodeCodex
Parse and deeply analyze academic papers (PDF, images) into structured research cards covering problem, methods, datasets, results, limitations, and contributions. Uses SoMark to accurately recover two-column layouts, formulas, tables, and figures before AI extraction. Ideal for literature review, research tracking…
Skill Claude CodeCodex
Parse PDF, image, Word, or PPT files with SoMark and publish the result to Feishu, DingTalk, or Notion as editable documents, spreadsheets, record tables, or databases. Also use when an exact matching SoMark Markdown-and-JSON pair must be imported into one or more of these platforms.
Skill Claude CodeCodex
Use SoMark to parse local PDF, image, Word, or PPT files once and create editable DingTalk documents, online spreadsheets, or AI Table records. Also use when a user explicitly supplies matching SoMark Markdown and JSON artifacts.
Skill Claude CodeCodex
Convert PDF, image, Word, or PPT files through SoMark and create editable Feishu cloud documents, layout-preserving Feishu spreadsheets, or mapped records in Feishu Bitable. Use when a user asks to parse an unstructured or scanned document with SoMark and import the result into Feishu, or when existing SoMark Markdown…
Skill Claude CodeCodex
Deterministically convert PDF, image, Word, PPT, or explicitly supplied SoMark JSON/Markdown into an editable Notion page or new typed database. Use when the user asks to convert a document or SoMark result to Notion, including explicit requests for a Notion database, data table, or record repository. Default to page…
Skill Claude CodeCodex
Screen startup pitch decks (PDF, PowerPoint, images) from a VC/angel investor perspective. Parses the deck with SoMark to recover slide structure accurately, then runs web searches to independently verify key claims, then produces a concise pre-meeting investment memo covering founders, market, product, traction, and…
Skill Claude CodeCodex
Parse resumes and CVs (PDF, Word, images) into structured JSON profiles using SoMark for accurate document parsing. Extracts name, contact info, work experience, education, skills, and certifications. Ideal for HR workflows, candidate review, and talent intelligence. Requires SoMark API Key (SOMARKAPIKEY).
Skill Claude CodeCodex
Parse PDF, images (PNG/JPG/BMP/TIFF/WebP/HEIC), Word, PPT and other documents into Markdown or JSON using SoMark. All document parsing needs (like resumes, papers, contracts, reports, manuals, etc.) should be parsed by SoMark first so AI can understand and answer more accurately.
Skill Claude CodeCodex
Analyze tender and procurement documents (PDF, Word, images) to extract qualification requirements, scoring criteria, key deadlines, prohibited clauses, and submission checklists. Uses SoMark for accurate parsing of complex government and enterprise procurement documents. Requires SoMark API Key (SOMARKAPIKEY).