realraelrr/docling-skill
Agent-first document ingestion layer on Docling with Markdown, image sidecars, manifests, OCR, and quality gating.
Agent-first document ingestion layer on Docling with Markdown, image sidecars, manifests, OCR, and quality gating.
npx add-skill realraelrr/docling-skillAgent-first document ingestion layer on Docling with Markdown, image sidecars, manifests, OCR, and quality gating.
Agent-friendly generator for Feishu-style card images and visual posts.
An OpenClaw skill that turns a receipt image (optionally with a caption) into a structured row in a Google Sheet, with automatic HKD conversion. Intended to be invoked manually inside OpenClaw today, and wired up to a Telegram webhook later.
🧃 Token weight loss. Lean output compaction for terminal-heavy agent workflows. Works as a native CLI tool or as an extension to popular coding and agent frameworks.
Harness for DeepSeek V4-Pro / V4-Flash. Python lib (pip install deepseek-harness) + dsh CLI + MCP server (npx @deepseek-harness/mcp) + Anthropic SKILL.md. 16 documented protocol quirks, 12 probes, 270+ trials.
Extract, structure, and apply visual design identity as machine-readable Design DNA across tokens, style, and effects
Build a minimal Python executive AI agent with fully commented code for learning, teaching, and junior developers