Claude Skills by seaworld008

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.

Identify technical debt, rank remediation by impact and effort, and track progress using code and maintenance evidence.

Use when designing Terraform IaC, reviewing modules, managing state, planning provider upgrades, or improving repeatable infrastructure deployment workflows.

Develop testable logic or fix behavioral bugs with focused regression tests and a red-green-refactor loop where it provides useful evidence.

Use when styling artifacts with reusable themes, applying preset color/font systems, or generating new visual themes for slides, documents, reports, HTML pages, and landing pages.

把仓库变更转化为学习文档、术语说明和设计记录。

Game audio generation agent. Produces code (Python/JS/TS/Shell) for SFX, BGM, Voice, Ambient, and UI sounds using ElevenLabs/Stable Audio/MusicGen/Suno/OpenAI TTS/JSFXR. Handles LUFS normalization and middleware integration.

会话回放分析、行为模式提取和体验问题叙事。

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

Correct speech-recognition errors, homophones, and mixed Chinese/English terminology in transcripts while preserving source meaning and speaker attribution.

事故首响、影响范围识别、恢复步骤和复盘整理。

用于通过 Trivy 扫描仓库、容器镜像、文件系统、rootfs、SBOM、Kubernetes、IaC、密钥、许可证和系统 CVE。

Use TweetClaw through OpenClaw to collect X/Twitter source context before drafting, monitoring, or campaign analysis.

Read Twitter/X posts and threads from supplied URLs, including author, text, timestamp, and available media, using the documented retrieval tools.

Use when writing or reviewing TypeScript for type safety, advanced types, API boundaries, strict-mode migrations, and common anti-pattern avoidance.

Create or maintain UI design tokens, component documentation, responsive rules, and designer-to-developer handoff artifacts.

Front-end UI/UX design intelligence for creating, reviewing, and hardening polished product interfaces across web, mobile, dashboards, SaaS, ecommerce, and content-heavy apps.

Find the most relevant engineering skill when task routing is unclear; load only the guidance needed for the current work.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Select relevant Superpowers workflow skills when the user requests that workflow or a concrete development task benefits from its process guidance.

Plan and synthesize UX research, personas, journey maps, and usability studies when validating product needs or design decisions.

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

Optimize React and Next.js rendering, data fetching, bundles, and runtime performance using Vercel''s engineering guidance.

Implement React ViewTransition animations, navigation transitions, transition types, and CSS pseudo-elements using the target React version''s API.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

用户反馈收集、满意度调研、评论分析和洞察提炼。

用于通过 Vuls 对 Linux、FreeBSD、容器、WordPress、库和网络设备执行 Agentless CVE 扫描。

Guardian of V.A.I.R.E. quality standards (Value/Agency/Identity/Resilience/Echo). Handles pre-release evaluation, scorecard assessment, and pass/fail determination. Use when UX quality gates are needed. Does not write code.

Build complex interactive HTML artifacts with React, Tailwind, and shadcn/ui when multiple components, routing, or state are needed.

Use when users need webpage scraping, structured data extraction, crawling strategy, anti-bot handling, selector design, or repeatable web data collection workflows.

Use when testing local web applications with Playwright, verifying frontend behavior, debugging UI issues, capturing screenshots, inspecting browser logs, or validating user flows.

Write a practical implementation plan when multi-step work needs task boundaries, dependencies, and acceptance checks.

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Use Xquik for X/Twitter research and connected-account actions; Radar and support workflows require a named request. Offline text analysis does not need this skill.

Create, read, edit, repair, or convert spreadsheet files (.xlsx, .xlsm, .csv, .tsv), including formulas, charts, and formatting. Use when a spreadsheet is the main input or deliverable.

Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).

Compare independent solutions with agent-hub when parallel competition is requested; isolate Git worktrees, evaluate variants, and integrate the selected result.

Specialist orchestrating codex exec / Antigravity CLI through dual paradigms — COMPETE (multi-variant comparison, select best) and COLLABORATE (decompose tasks across engines, integrate). Supports Solo/Team/Quick execution modes.

Build or debug ChatGPT Apps SDK projects with MCP tools and widget UIs, using current official guidance for resources, bridges, metadata, and CSP.

Build or iterate on HTML/JS web games with Playwright input bursts, gameplay screenshots, state inspection, and console checks.

Implement UI from Figma URLs or node IDs with visual fidelity, project conventions, and design assets. Requires an available Figma MCP connection.

Fetch Figma design context, variables, screenshots, and assets through MCP when working from Figma URLs or node IDs, or diagnosing its integration.

Use, configure, theme, extend, and orchestrate Hermes Agent.

Route a development task to the official Hermes Agent skill, Graphify Codex artifact set, Open GSD Core bundle, or optional GSD Pi bundle without duplicating their installers or state machines.

Use when a user explicitly needs terminal-based MCP discovery, schema inspection, authentication diagnostics, or scripted tool calls through mcporter; verify server trust, argument schemas, and mutation authority before execution.

Configure Hermes Agent''s built-in MCP client: server discovery, stdio/HTTP connections, tool registration, authentication, and reconnection diagnostics.

Find current official OpenAI guidance for Codex, APIs, models, prompting, or migrations. Preserve a named target model and cite fetched documentation.

人工智能应用设计、评估、检索增强和安全护栏规划。

Use when building or operating agents that should learn from prior runs, capture durable feedback, update behavior safely, and improve task performance across iterations.