Use when the user wants OCR on images, screenshots, scans, receipts, diagrams, or image files; extract text from a local image path, image URL, or base64 image; convert OCR output to plain text, markdown table, structured JSON, or code comments; or rename, summarize, or post-process files based on recognized text. Prefer this skill for image-to-text workflows backed by the local ocrtool-mcp binary.
- 📁 demos/
- 📁 evals/
- 📁 plans/
- 📄 .gitignore
- 📄 _config.yml
- 📄 check-doc-sync.py
生成HTML演示文稿/幻灯片 — 21 种风格模版，播放/演讲者模式。适用于路演、产品发布、技术分享、方案宣讲等场景。
This skill should be used when performing a structured, read-only code review of a file, module, diff, commit, or pull request, especially when the user asks to review a PR or diff, 审查一个模块或文件, 看看改动有没有问题, or coordinate multiple review perspectives from one manual entry point.
Guide for creating optimized Claude Code agents. Use to design a new specialized agent, a swarm sub-agent, or a multi-agent workflow. Follows the Skill → Agent (preloaded skills) → Skill orchestration pattern.
- 📄 LICENSE
- 📄 README.md
- 📄 SKILL.md
First open-source AI sanitizer with local semantic detection. 7 layers + code block awareness + LLM intent analysis. Catches prompt injection, reverse shells, memory tampering, encoding evasion, trust abuse. 85% fewer false positives in v2.1. Zero cloud — your prompts stay on your machine.
Convert an existing find-XXXX SKILL.md into a preprocessor Python script, updating config.yaml and removing the old SKILL.md. Covers xref-string-based and LLM_DECOMPILE-based discovery patterns.
Add a new journal to the MedSci Skills profile database. Extracts metadata from author guidelines, generates write-paper (detailed) and find-journal (compact) profiles in canonical format with quality gates.
- 📁 evals/
- 📁 references/
- 📄 SKILL.md
Use this skill whenever the user needs to manage VMs in VMware/vSphere/ESXi — it's the entry point for all VM operations.
Performs exploratory data analysis (EDA) on datasets from CKAN portals and CSV files. Use when analyzing datasets, checking data quality, exploring CSV files, or when the user asks to examine, analyze, or validate data.
- 📁 references/
- 📁 templates/
- 📄 SKILL.md
Interact with Channel Talk using extracted desktop app credentials - read chats, send messages, search messages, manage groups
Four sweep operations: (1) Model perf sweep — find optimal batch size / TGS for a model. Use for: sweep batch size, tune TGS, benchmark throughput, find optimal config. (2) Node perf sweep — compare per-node GPU performance to find outliers. Use for: check nodes, node performance, find slow node, compare nodes. (3) Node network health sweep — detect inter-node network issues via multi-node bisection. Use for: network health, IB issues, RCCL problems, node pair testing, isolate network problem. (4) Model sweep — run all model configs on one or two commits. Use for: regression test, validate commit, test all models, smoke test, CI, compare branches.
百度地图 JSAPI WebGL (BMapGL)完整开发指南，覆盖地图初始化、覆盖物、图层、事件、样式、性能优化的任务，一站式开发高性能 3D 地图应用。当用户提及 BMapGL、百度地图、jsapi-gl或相关地图开发需求时自动触发。
