Loading...
Loading...
Found 12 Skills
Generate or update PROJECT_MAP.md for user-specified folders. Applicable to scenarios where users request directory maps/project maps/repository overviews/folder-level descriptions/updating existing PROJECT_MAP.md. Must first ask for the folder scope to scan, default full-repository scanning is prohibited; supports single directory or multiple directories (combined or generated separately).
Analyze source code and produce an enterprise-quality, domain-organized Wiki under `.nium-wiki/`. Trigger on: "generate wiki", "create docs", "update wiki", "rebuild wiki", or any documentation generation request. Capabilities: - Semantic code analysis — understands logic, not just structure - Auto-generated Mermaid diagrams (architecture, data flow, class, dependency) - Bidirectional cross-linking across all documents - SHA256-based change detection for incremental rebuilds - Every section traces back to source via relative path links - Multi-language output (zh/en/ja/ko/fr/de and more)
You are a dependency management expert specializing in safe, incremental upgrades of project dependencies. Plan and execute dependency updates with minimal risk, proper testing, and clear migration pa
Expert documentation generator for coding projects. Analyzes codebases to create thorough, comprehensive documentation for developers and users. Supports incremental updates, multi-audience documentation, architecture decision records, and documentation health tracking. Works with any project type (APIs, CLIs, web apps, libraries). Use when you need to document a new project, update docs after adding features, or create comprehensive documentation for open source releases.
Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.
When the user says phrases like "update the index", "add this to the index", "added a new file", "added a new book/note/document", "need to update the material library index", the **Incremental Maintenance Mode** of this skill should be used. When the user says phrases like "index health check", "index体检", "check the index", "sync the index", "fill in missing index entries", the **Health Check Mode** of this skill should be used to scan all libraries ↔ INDEX to find missing/invalid entries and batch fill them in. Applicable to all libraries with INDEX.md: Reading Notes Library, Core Concepts Library, Viral Script Library, 04-Methodology Precipitation, and any newly created libraries in the future. The value of an index depends on content accuracy—you must fully read the original text before writing; inferring based on file names or impressions will render the index useless for reference. Even if the user only says "I added a file" or "put this in", as long as it involves the index, this skill should be triggered. Do NOT trigger for: Only viewing the index (directly Read), deepening topics (use li-topic), generating scripts (use li-writer). Use when the user adds new content to any indexed library, OR runs a global index health-check to find missing/stale entries.
This skill should be used when building data processing pipelines with CocoIndex v1, a Python library for incremental data transformation. Use when the task involves processing files/data into databases, creating vector embeddings, building knowledge graphs, ETL workflows, or any data pipeline requiring automatic change detection and incremental updates. CocoIndex v1 is Python-native (supports any Python types), has no DSL, and is currently under pre-release (version 1.0.0a1 or later).
Orchestrates parallel KB generation using spatial analysis and a map-reduce architecture with incremental update support.
Build native UIs in the style of Raph Levien, architect of Druid, Xilem, and Vello. Emphasizes declarative reactive architecture, synchronized tree transformations, GPU-accelerated rendering, and idiomatic Rust patterns. Use when designing responsive, beautiful native UIs or 2D graphics systems.
Use when user asks to "create repo map", "generate repo map", "update repo map", "repo map status", or "map symbols/imports". Builds and validates an AST-based repo map using ast-grep.
Analyze codebases from the bottom up and generate a hierarchical README.md document tree. Start analysis from leaf directories, generate README.md files for each directory containing one-sentence descriptions of files, classes, and functions, and summarize layer by layer upwards to form a complete codebase documentation system. Supports state persistence and resumable analysis, suitable for scenarios such as understanding new projects, generating technical documentation, and analyzing code structures. Use this skill when you need to understand codebase structures, analyze function implementations, or generate code documentation.
Douyin Video Batch Download Tool - Implements efficient, incremental video download functionality based on the F2 framework. Supports single/batch creator download, automatic Cookie management, and differential update mechanism. This skill should be used when users need to batch download videos from specific creators, deploy automated downloads on servers, or regularly update video libraries.