Skill Creator
majiayu000
6838 published skills · 19,665 GitHub stars across the catalog. View on GitHub ↗
enhancing-progressively
CSS-first approach - use CSS before JavaScript. Triggers: レイアウト, スタイル, 位置, アニメーション, 表示/非表示, トグル, レスポンシブ, CSS Grid, Flexbox, transforms, transitions, CSSのみ, JavaScript不要, シンプル
oracle-codex
This skill should be used when the user asks to "use Codex", "ask Codex", "consult Codex", "Codex review", "use GPT for planning", "ask GPT to review", "get GPT's opinion", "what does GPT think", "second opinion on code", "consult the oracle", "ask the oracle", or mentions using an AI oracle for planning or code review. NOT for implementation tasks.
ultrathink
First-principles deep thinking for significant problems. Use when you need to question assumptions, craft elegant solutions, and challenge beliefs.
writing-typescript
Idiomatic TypeScript development. Use when writing TypeScript code, Node.js services, React apps, or discussing TS patterns. Emphasizes strict typing, composition, and modern tooling (bun/vite).
writing-python
Idiomatic Python 3.14+ development. Use when writing Python code, CLI tools, scripts, or services. Emphasizes stdlib, type hints, uv/ruff toolchain, and minimal dependencies.
dry-refactor
This skill should be used when the user asks to "refactor duplicate code", "apply DRY principles", "eliminate code repetition", "extract common functionality", or mentions code duplication, similar patterns, repeated logic, or reusable abstractions.
signal-capture
Detect and capture technical preferences, naming conventions, and architectural practices from user messages into Packmind standards. Trigger when user prescribes HOW to code rather than WHAT to build (e.g., "Use snake_case for columns", "Always use async/await", "Prefix interfaces with I"). Does NOT trigger for feature requests, bug reports, or general implementation tasks without coding preferences.
release-skill
Bump version, update changelog, commit, tag, push, and build release installer
feature-docs
Use when the user asks to generate comprehensive feature documentation with verified test cases, create feature README with code evidence, or document a complete feature with test verification. Triggers on keywords like "feature documentation", "document feature", "comprehensive docs", "feature README", "test verification", "verified documentation".
code-validator
驗證 maihouses 專案的 TypeScript/React 代碼品質,確保符合 CLAUDE.md 的最高規格標準。當修改或審查代碼時自動使用。
documenting-architecture
Generate architecture overview documentation from codebase analysis. Uses tree-sitter-analyzer for precise code structure extraction. Generates Mermaid diagrams for visual representation. Triggers: architecture overview, project structure, module diagram, dependency graph, code structure, directory structure.
formatting-audits
Design document review format definition with 100-point scoring system. Provides quality evaluation criteria, scoring items, and pass/fail logic for SOW/Spec documents. Combined with confidence markers (✓/→/?) to clarify evaluation evidence. Triggers: SOW review, Spec review, document review, design review, ドキュメントレビュー, 設計レビュー, 90 points, scoring, grading, 品質評価, スコアリング, 合否判定.
writing-go
Idiomatic Go 1.25+ development. Use when writing Go code, designing APIs, discussing Go patterns, or reviewing Go implementations. Emphasizes stdlib, concrete types, simple error handling, and minimal dependencies.
type-checker
執行 TypeScript 類型檢查並修復類型錯誤。當遇到類型錯誤、需要類型定義、或用戶提到「type」、「類型」時使用。
loki-mode
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.
automating-browser
Interactive browser automation using claude-in-chrome MCP tools. Best for: demos, documentation GIFs, manual testing, live browser control. For automated E2E testing in CI/CD, use webapp-testing skill instead. Triggers: browser automation, ブラウザ自動化, screenshot, スクリーンショット, form fill, フォーム入力, click, navigate, GIF recording, GIF録画, ブラウザ操作, Chrome, demo, デモ, live browser.
skill-linter
Validate skills against agentskills.io specification. Use when adding new skills to the marketplace, reviewing skill PRs, checking skill compliance, or running quality gates on skills. Validates frontmatter fields (name, description, license, compatibility, metadata, allowed-tools), directory naming, line limits, and structure.
tabz-guide
Progressive disclosure guide to TabzChrome capabilities. This skill should be used when users ask about profiles, terminal management, browser automation, MCP tools, audio/TTS notifications, integration, debugging, API, or setup. Provides on-demand help organized by topic with references to detailed documentation.
parallel-agents
Native multi-agent orchestration using Claude Code's Agent Tool. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.
output-style-audit
Validates output-style persona definitions, behavior specifications, and keep-coding-instructions decisions. Use when auditing, reviewing, or improving output-styles, checking persona clarity, validating behavior concreteness, or verifying scope alignment (user vs project). Triggers when user asks about output-style best practices or needs help with persona definition.
validate
Check decisions against beliefs, wisdom, and intentions. Use before significant actions to ensure coherence with accumulated knowledge.
tabz-mcp
Control Chrome browser: take screenshots, click buttons, fill forms, download images, inspect pages, capture network requests. Use when user says: 'screenshot this', 'click the button', 'fill the form', 'download that image', 'what page am I on', 'check the browser', 'look at my screen', 'interact with the website', 'capture the page', 'get the HTML', 'inspect element'. Provides MCP tool discovery for tabz_* browser automation tools.
behavioral-modes
Defines different operational modes for AI behavior. Each mode optimizes for specific scenarios like brainstorming, implementation, or debugging.
applying-code-principles
Fundamental software principles - SOLID, DRY, Occam's Razor, Miller's Law, YAGNI. Triggers: 原則, シンプル, 複雑, アーキテクチャ, リファクタリング, 保守性, コード品質, design pattern, best practice, clean code