Claude Skills meta-skill: extract domain material (docs/APIs/code/specs) into a reusable Skill (SKILL.md + references/scripts/assets), and refactor existing Skills for clarity, activation reliability, and quality gates.
Draft user-facing release notes from a git log range. Trigger when the user asks for "release notes", "changelog entry", or "what shipped this week" with a git ref range. Output is markdown sections grouped by Features / Fixes / Breaking with PR links.
Prepare safe, compact new-chat handoffs when a user wants a fresh chat, resume pack, context reset, recovery, or agent handoff. Before creating a new conversation, preserve durable project knowledge and protect dirty Git work with a verified local snapshot branch and commit; optionally push that branch when explicitly…
A lightweight workflow for coding agents that breaks work into checkpoints and records evidence of progress. It is aimed at experienced users and assumes the task has already been reduced to a workable unit.
A structured software-development workflow based on the SDD-RIPER method, with stages for clarifying goals, mapping code, writing specifications, and tracking work.
Generate structured A-share market commentary for three fixed trading sessions using supplied market data: within 30 minutes after market open, after midday close, and after market close. Use this skill when the user wants factual market observation, intraday commentary, or end-of-day review content based on real…
A workflow for creating an interactive prototype before building a medium-sized or larger project with a user interface. It uses the prototype to confirm what the product should look and do like.
A documentation process for recording project progress, architecture decisions, development handovers, and user-visible releases. It organises these records into navigation, dated details, architecture notes, and a changelog.
A configuration format for a project's run panel. It defines buttons that start or stop commands such as development servers, builds, tests, packaging tasks, and deployments, including their working directories and local URLs.
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code…
Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.
Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate external services.