Analytics & Monitoring Agent Skills for Claude Desktop

Measures interactive zsh latency with zsh-bench.

Revise English AI/ML research-paper prose in the distilled writing style of four AAAI papers from Peng Cui's research group: Stable…

This skill calculates key financial ratios and metrics from financial statement data for investment analysis

Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing.

Audit, plan, add, improve, or review production logging and observability for a selected class, package, migrated operation, module…

Claude Agent SDK build harness with a Planner/Builder/Evaluator loop.

Analyzes and improves AI agent collaboration environments based on the 12 principles of Agent Harness maturity.

Builds self-verifying experiment laboratories and measurement feedback loops for optimization, debugging, visual fidelity, quality, cost…

Finds and recalls past AI agent sessions across Cursor, Codex, Claude Code, and other hosts using activity keywords, projects, or session…

Agent 会话可视化 / session timeline: execution maps for Cursor, Codex, Claude Code, Workbuddy, kimi-code threads (ID or name)…

Make NVIDIA OO agent types render beautiful documentation for the LLM — doc(), spec(), hidden, Annotated field descriptions, and…

Patterns and techniques for evaluating and improving AI agent outputs.

Safely read, edit, and execute notebooks on a standalone or remote Jupyter Server through HTTP Sessions and WebSocket kernel channels.

Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and…

See, Understand, Act on video and audio.

Design, implement, review, evaluate, or improve AI agents and agentic workflows in English.

Designs, implements, evaluates, and optimizes reliable AI agents and multi-agent workflows in Simplified Chinese.

Advanced prompt optimization and composition system for all prompt types (system prompts, task-specific, creative, technical, agentic).

Create or rewrite a complete Markdown report for a concrete AI accelerator architecture, covering hardware, execution, GPU differences and…

Evaluates and benchmarks LLM prompt variations using three-column comparison across weak prompts, portable templates, and live skill…

Architects and governs robust AI agent runtimes, multi-agent orchestration, context compression, memory strategies, and domain-enhanced…