Skill UI

Context Guardian preserves critical context before Claude Code’s automatic compression, collecting verified snapshots, detecting integrity issues, and briefing transitions so heavy-technical sessions keep every essential decision and dependency intact.

Index of 37 advanced engineering agent skills for Claude Code, Codex, Gemini CLI and Cursor, covering agent design, RAG, MCP servers, CI/CD, database design, observability, security auditing, release automation and platform reliability operations.

This bundle indexes 32 production-ready engineering skills for various AI coding tools like Claude Code and Codex. It covers core engineering, security, AI/ML, data engineering, and specialized tools such as AWS and Playwright. Users should load only the specific specialist SKILL.md needed rather than bulk-loading. Includes stdlib-only Python tools for analysis and scaffolding.

This comprehensive tool validates Claude Code plugins against official Anthropic specifications and internal enterprise standards. It performs two main types of checks: structural validation (checking `plugin.json` fields, file references, and permissions) and content validation (conducting deep grading using `SKILL.md`). Use this when building, auditing, or preparing plugins for marketplace submission to ensure compliance and quality.

A comprehensive, multi-stage workflow for enhancing and structuring raw footage using advanced AI tools. It covers the entire pipeline—from initial recording (Screen Studio) through AI planning (Claude/Codex), deterministic cutting (FFmpeg), compositing (Remotion), asset generation (ElevenLabs/fal.ai), and final human polish (Descript/CapCut). Designed for users creating vlogs, tutorials, or polished corporate videos.

This skill orchestrates deep critical reviews of research work using external AI models like Codex, Gemini, or Claude. It gathers project context, identifies logical gaps, and provides adversarial feedback on methodologies and results. Suitable for academic papers, experimental validation, and refining research ideas through multi-round reasoning.

Assistant for venture fund administrators: ingests capital calls, investments, and cash flows to compute KPIs (TVPI, DPI, IRR, MOIC), model carry/fees, and draft LP quarterly updates via Claude Code + Python.

Guides users through a structured 23-step interview to design, generate, and deploy Claude plugins across claude.ai and Claude Code, handling activation prompts, platform quirks, and GitHub pushes.

A lightweight CLI tool for systematically comparing various coding AI agents (such as Claude Code, Aider, and Codex) head-to-head. It measures crucial metrics—pass rate, API cost, execution time, and consistency—on reproducible tasks defined via YAML manifests. Use this to objectively select the best agent for your codebase or to validate model updates before production deployment.

This tool audits the token consumption across all components (agents, skills, rules, MCP servers) within a Claude Code session. It analyzes token overhead, identifies bloat (e.g., overly long descriptions, redundant components), and generates a detailed context budget report. Use it to maintain optimal context window usage, improve performance, and prevent context saturation.

Guides users through saving their Discord bot token, checking access policies, and locking down channel reach by managing pairing codes, allowlists, and policy transitions so the Claude assistant can reliably respond via Discord.

Applies two-axis scoring, mandatory devil’s advocate reasoning, and persistent history to keep post-task self-reviews honest, resistant to inflation, and suitable for Claude Code sessions.