Loading...
Loading...
Found 44 Skills
Document codebase as-is with thoughts directory for historical context
Full-Process Web Novel/Story World Builder, suitable for users' overall novel writing needs such as saying "I want to write a novel", "Write a web novel", "Create a novel from scratch", "Help me write a novel of XX genre", "I want to write a novel", "Give me the entire novel creation process", "Auto-write a novel", "One-stop novel creation service", "Help me finish a novel", "How to write a novel with only an idea", etc. It automatically coordinates the full process of topic selection, outline design, writing, review, and polishing. Even if you only have a rough idea, it can help you complete a full work from 0 to 1 and build a unified story world. **All chapter-level operations are processed in parallel by sub-Agents, with each Agent responsible for a maximum of 3 chapters**
Use when reviewing React documentation for structure, components, and style compliance
Guide for making code reviews. Use this when asked to make code reviews, or ask to use it before committing changes.
Simulate a tough but constructive peer review of an AI research artifact. Use when the user asks for a review, critique, feedback on a paper or draft, or wants to identify weaknesses before submission.
Research-aligned self-consistency for debugging. Spawns independent solver agents that each explore and debug the problem from scratch. Uses majority voting. Based on "Self-Consistency Improves Chain of Thought Reasoning" (Wang et al., 2022). Use for critical bugs, algorithms, or when other approaches have failed.
Code refactoring workflow - analyze → plan → implement → review → validate
Research how production Rails apps solve architectural problems using the Real World Rails repository. Use when the user wants to know how other apps handle something, find patterns, or compare approaches. Triggers on "rails patterns", "how do other apps", "real world rails", "research how apps do".
MantaBase T3 Hardware Audit System (Chinese Version). Objectively classify hardware products based on design theories through Brand Blinding, three Auditor (Tool/Toy/Trash) special scoring and Peer Review. Triggers: product link, T3 audit, Tool/Toy/Trash classification, hardware evaluation, VC investment advice
Adversarial Quarto vs Beamer QA. Critic finds issues, fixer applies fixes, loops until APPROVED (max 5 rounds).
Run a comprehensive pull request review using multiple specialized agents. Each agent focuses on a different aspect of code quality, such as comments, tests, error handling, type design, and general code review. The skill aggregates results and provides a clear action plan for improvements. Triggers include "review PR", "analyze pull request", "code review", and "PR quality check".
This skill should be used when performing a code review on local changes on the current branch compared to the main branch. It uses multiple parallel agents to check for bugs, CLAUDE.md compliance, git history context, previous PR comments, and code comment adherence, then scores and filters findings by confidence level.