技術寫作

Expert documentation generation for golden layers. Detects SCD types, documents business rules, metric definitions, aggregation logic, and data quality scoring. Use when documenting golden layer tables.

Comprehensive TypeScript engineering guidelines based on Google's TypeScript Style Guide. This skill should be used when writing TypeScript code, performing TypeScript code reviews, or answering questions about TypeScript best practices. Applies to .ts and .tsx files, and TypeScript configuration.

Reference terminal documentation for TTY/PTY, streams, signals, and cross-platform patterns

LLM-powered documentation generation for narrative architecture docs, tutorials, and developer guides. Uses AI consultation to create contextual, human-readable documentation from code analysis and spec data.

Repair malformed markdown code fence closings. Use when markdown files have closing fences with language identifiers (```text instead of ```) or when generating markdown with code blocks to ensure proper fence closure.

Comprehensive assistance with latex-wikibook

Use when writing Jest tests - covers testing patterns for interpreters, parsers, and async code

This skill should be used when performing systematic scans of research paper text to identify and fix typos, grammar errors, inappropriate words, and awkward expressions. Use for thorough proofreading and error correction in academic writing for computer science conferences.

Modern PHP development best practices including PHP 8.x features, OOP patterns, error handling, security, testing, and performance optimization. Use when writing PHP code, reviewing PHP projects, debugging PHP issues, or implementing PHP features outside of WordPress/Laravel specific contexts.

Write clear technical documentation for themes, plugins, and web products including installation guides, configuration docs, API references, tutorials, and changelogs. Use when creating user guides, developer docs, or help articles.

Guide for writing clear, descriptive commit messages

Bitwarden Passwordless.dev documentation, SDKs, and React examples

Professional copywriter for compelling headlines, sales copy, and persuasive writing techniques

Use when working with examples, tutorials, or skill documentation. Invoke when the user asks about skill configuration, manifest structure, or creating new skills.

論文草稿的撰寫、讀取、引用管理。LOAD THIS SKILL WHEN: 寫草稿、draft、撰寫、Introduction、Methods、Results、Discussion、引用、citation、字數CAPABILITIES: write_draft, draft_section, read_draft, list_drafts, insert_citation, sync_references, count_words, get_section_template

MANDATORY at session start. REQUIRED when user topic shifts (from debugging to docs, from frontend to backend, etc). Updates terminal title with emoji + project + topic. SessionStart hook auto-invokes. Claude must also invoke on all topic changes.

Technical tutorial writing in modified DigitalOcean style. Use when (1) writing step-by-step technical tutorials, (2) creating documentation for code/applications, (3) explaining technical concepts procedurally, (4) working with Temporal applications/tutorials, or (5) the user asks to write, create, or help with a tutorial. Follows specific style constraints: friendly but formal tone, comprehensive explanations, code sandwich approach, assumes English is reader's second language, and never generates new code (only references provided code).

MANDATORY implementation wrapper. ALWAYS invoke when moving from design→code. Present 3 options: (1) Cookoff - 2-5 parallel agents compete, each creates own plan, pick best, (2) Single subagent, (3) Local. Triggers: "let's build", "implement", "looks good", user picks implementation option, ANY signal to start coding after design. This skill MUST run before writing-plans/executing-plans at design boundaries. For exploring DIFFERENT designs, use omakase-off.

Central authority for Claude Code subagents (sub-agents). Covers agent file format, YAML frontmatter, tool access configuration, model selection (inherit, sonnet, haiku, opus), automatic delegation, agent lifecycle, resumption, command-line usage (/agents), Agent SDK programmatic agents, priority resolution, and built-in agents (Plan subagent). Assists with creating agents, configuring agent tools, understanding agent behavior, and troubleshooting agent issues. Delegates 100% to docs-management skill for official documentation.

Git 提交前文檔同步。觸發：docs、文檔、sync docs、發布。