发现 Skills

Upload local images to a GitHub PR and embed them in the description or comments. Use when asked to "attach screenshots to PR", "add images to PR", "upload test results to PR", "embed screenshots in PR description", "add before/after images to PR", "attach UI screenshots", "show test results in PR", "add visual evidence to PR", or any request involving images and PRs. Always use this skill when the user wants to visually document changes in a pull request, even if they don't use the word "upload" — phrases like "put the screenshot in the PR" or "show the image in the PR" should trigger this skill. Supports Playwright MCP / Chrome DevTools MCP / agent-browser as browser automation backends.

Used to access and record a project's security architecture decisions and long-term memory.

Publish the @magnet-ai/magnet-mcp-server package to NPM with version bumping and git tagging. Use when user says "publish to npm", "npm publish", "deploy to npm", "release to npm", "publish package", "bump version and publish", or "release new version".

Applies current Go testing best practices. Use when writing or modifying Go test files or advising on Go testing strategies.

This skill should be used when managing Claude Code plugin marketplace operations including setup, validation, version syncing, and plugin scaffolding. Sets up marketplace repos to be self-sufficient with their own validation and sync scripts. Triggers on "setup marketplace repo", "install repo scripts", "scaffold plugin", "auto-fix marketplace", "reverse scan", "sync versions", "validate marketplace", "add to marketplace", "check marketplace", or "create plugin". Do NOT use for skill content improvements (use skillsmith), plugin component creation (use plugin-dev), or OmniFocus/Obsidian operations.

AddressSanitizer detects memory errors during fuzzing. Use when fuzzing C/C++ code to find buffer overflows and use-after-free bugs.

Support workflows, ticketing systems (Zendesk, Intercom), knowledge base design, chatbot design, and metrics (CSAT, NPS). Use when building support infrastructure, designing help centers, or optimizing customer experience.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) creating new documents, (2) modifying or editing content, (3) working with tracked changes, (4) adding comments, or any other document tasks.

Complete design system reference for React applications. Covers colors, typography, spacing, component patterns, glassmorphism effects, GPU-accelerated animations, and WCAG AA accessibility. Use when implementing UI, choosing colors, applying spacing, creating components, or ensuring brand consistency.

Guide feature development for React applications with architecture focus. Covers Zustand/Redux patterns, IndexedDB usage, component systems, lazy loading strategies, and seamless integration. Use when adding new features, refactoring existing code, or planning major changes.

HR and talent management expertise for talent acquisition, performance management, compensation strategy, organizational design, culture building, succession planning, and D&I programs. Use when hiring, managing performance, designing organizations, or building culture.

Structured comparison of competing options with weighted scoring matrices, trade-off analysis, decision frameworks, and recommendation templates. Use when evaluating alternatives, making purchase decisions, or comparing strategies.

Cross-platform mobile development with React Native and Expo. Use when building iOS/Android apps with JavaScript/TypeScript, implementing native features, or optimizing mobile performance.

Research-first UI/UX design workflow. Use BEFORE any frontend visual work to research modern patterns, gather inspiration from real products, and avoid generic AI-generated looks. Mandatory prerequisite for quality UI work.

Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.

Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.

Apple HIG guidance for presentation components including alerts, action sheets, popovers, sheets, and digit entry views.

Execute systematic privilege escalation assessments on Linux systems to identify and exploit misconfigurations, vulnerable services, and security weaknesses that allow elevation from low-privilege user access to root-level control.

IMPORTANT - Path Resolution: This skill can be installed in different locations (plugin system, manual installation, global, or project-specific). Before executing any commands, determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below.

Visually test web UIs using Chrome CDP — spot layout issues, interaction bugs, responsive breakage, and produce a structured report

Spotting founder blind spots and startup failure modes early, based on comparable patterns and second-order effects.

Push content to TRMNL e-ink displays via a webhook API. Use this when a user wants to display information on their TRMNL device, update an e-ink dashboard, or send status updates to TRMNL.

Use when the user wants to design Codex agent equivalents (specialized workers/profiles/prompt files), define triggering conditions, or build reusable agent prompts and validation tools.

Use when asked to detect silent failures/weak error handling or explicitly asked to run the silent-failure-hunter subagent.