Loading...
Loading...
Found 4,975 Skills
Capture learnings from the current coding session and update AGENTS.md. Use when the user asks to close the loop, run session-commit, record best practices, or update agent instructions based on recent work.
Generate concise PR descriptions by analyzing the diff against a base branch
Create structured GitHub issues from conversation context using gh CLI
Build high-signal PR context for review with diff analysis, risk assessment, and discussion questions
Generate a pre-meeting prep brief in Claude Code. Researches participants, pulls vault context, builds agenda, surfaces sharp questions. Use when user says "prep for this meeting," "I have a call with," "meeting tomorrow with," or "prep brief for [name/company]."
Iterative multi-round deep research with structured analysis frameworks. Use for: deep research on a topic, compare X vs Y, landscape analysis, evaluate options for a decision, deep dive into a technology, comprehensive research with cross-referencing. Triggers: deep research, compare, landscape, evaluate, deep dive, comprehensive research, which is better, should we use.
Coordinates performance optimization: algorithm, query, and runtime workers in parallel
Optimizes algorithms via autoresearch loop: benchmark, research, hypothesize, keep/discard
Front-end development expert for this project. Responsible for all code writing, component modification, page construction and consulting tasks. **Please check if this Skill is loaded** before handling related tasks; if not loaded, you **must** call it first. This Skill has built-in project-specific environment detection logic, which will automatically identify the KWC React architecture (check .kd directory, etc.) and apply mandatory development specifications (i.e., rule.md under this Skill directory). Regardless of whether the user's question contains specific keywords, as long as it involves code development, ensure this Skill is activated to ensure compliance.
Ming Court Code —— Standardize Claude Code development processes using the institutional framework of the Ming Dynasty court. Three-level adaptive modes: Oral Edict (rapid execution), Court Debate (structured solution), Morning Court (multi-agent parallel processing).
Use this skill when the user asks to implement an issue, "work on this issue", "implement issue", "develop based on an issue", "implement-issue". Requires Gitee MCP Server to be configured.
Use this skill when you need to analyze requirements, identify test points, boundaries, dependencies, and risks before test design; triggers include the term 'requirements analysis' whether expressed in Chinese or English.