技術寫作

Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

CellChat cell-cell communication analysis toolkit - complete documentation with precise file name-based categorization

Foundational knowledge for writing Stan 2.37 models including program structure, type system, distributions, and best practices. Use when creating or reviewing Stan models.

Automated documentation generation specialist for technical specs, API docs, user guides, and knowledge bases with multi-format output

TypeScript development best practices, code quality tools, and documentation templates. Activated when working with .ts, .tsx files or TypeScript projects.

Write effective tests with proper structure and coverage. Use when writing unit tests, integration tests, or improving test quality.

Use after writing-plans to decompose monolithic plan into individual task files and identify tasks that can run in parallel (up to 2 subagents simultaneously)

Expert guidance for reliable bash script directory navigation and path handling. Use when writing new bash scripts, reviewing existing scripts, debugging directory-related failures, or when mentioned 'directory handling', 'bash paths', 'cd errors', 'script location', or 'git root'. Provides deterministic patterns to eliminate silent failures from unhandled cd, missing set -e, and path resolution issues.

JavaScript and TypeScript coding standards, conventions, and best practices. Use when writing, reviewing, or testing JS/TS code.

Applies Fabric AI prompt patterns for summarization, analysis, extraction, code review, and content creation. Use when asked to summarize content, analyze documents, extract insights, review code, create documentation, or transform text. Patterns are in data/patterns/.

Homeostatic sensor detecting requirements without implementation or test coverage. Scans for REQ-* keys in requirements docs and checks if they have corresponding code and tests. Use to find coverage gaps.

Provides web search capability for finding current information, documentation, and resources from external sources when local knowledge is insufficient

Complete Godot Engine knowledge base combining official documentation and source code analysis

Convert docstrings to NumPy/Sphinx style with proper Parameters, Returns, and Examples sections. This skill should be used when improving documentation quality across Python modules.

Use this skill when contributing code to open source projects. The skill covers proper pull request creation, avoiding common mistakes that annoy maintainers, cleaning up personal development artifacts before submission, writing effective PR descriptions, following project conventions, and communicating professionally with maintainers. It prevents 16 common contribution mistakes including working on main branch, not testing before PR submission, including unrelated changes, submitting planning documents, session notes, temporary test files, screenshots, and other personal artifacts. Includes 3 Critical Workflow Rules that must NEVER be skipped: (1) Always work on feature branches, (2) Test thoroughly with evidence before PR, (3) Keep PRs focused on single feature. The skill includes automation scripts to validate PRs before submission, templates for PR descriptions and commit messages, and comprehensive checklists. This skill should be used whenever creating pull requests for public repositories, contributing

Specialized codebase understanding agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search.

Code review best practices including review checklists (functionality, tests, documentation, security, performance), providing constructive feedback, automated checks integration, and handling review comments. Use when reviewing pull requests, providing code feedback, responding to review comments, or setting up review processes.

Advanced Git operations including rebasing, conflict resolution, history rewriting, worktrees, bisect, submodules, hooks, and complex workflows. Use for sophisticated Git challenges beyond basic add/commit/push, including fixing repository states, optimizing history, and managing complex branching strategies.

Expert knowledge for Application Layer modeling in Documentation Robotics

Research latest library documentation, industry best practices, and technical knowledge to automatically generate project-level skills. Use when asked to: (1) Research and create a skill for a library/framework, (2) Build a skill based on architectural patterns, (3) Generate skills from technical research, (4) Create domain-specific technical skills from web research, or (5) Any request combining research with skill creation.