Claude Skills by seaworld008

Generating AI image-generation code using the Gemini API. Handles text-to-image generation, image editing, and prompt optimization. Use when image generation code is needed.

Generate, remix, inspect, download, or delete Sora videos through the bundled API CLI when the user requests a Sora video workflow.

Create text-to-speech narration, voiceovers, or batch audio with OpenAI''s Audio API and the bundled text_to_speech.py CLI.

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.

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.

Create, read, edit, or review Word documents (.docx), including styles, tables, headers, tracked changes, and comments. Use when Word is the input or required deliverable.

制作可横向翻页的单 HTML 网页 PPT，支持杂志风或瑞士风、讲稿、演讲者视图和观众屏同步；用于演讲、分享或发布会网页演示。

Convert PDF, DOCX, PPTX, and other documents to Markdown, preserving tables, images, and structure with the appropriate extraction tool.

Turn meeting transcripts into accurate minutes with decisions, actions, owners, and source evidence; also review or merge minutes and resolve speaker ambiguity.

Extract Mermaid diagrams from Markdown and render PNG images with the bundled tools when a diagram image or batch conversion is needed.

Converting document formats (Markdown/Word/Excel/PDF/HTML) and generating reusable conversion scripts. Use for distributable specs, accessibility-compliant PDFs, or Pandoc/LibreOffice pipelines.

Read, create, edit, merge, split, OCR, or fill PDF documents when PDF content or a PDF deliverable is the task.

Create, read, edit, or combine PowerPoint (.pptx) decks, including layouts, notes, comments, and templates. Use when PowerPoint is an input or deliverable.

Consultant for NotebookLM steering prompt design. Optimizes Audio/Video/Slide/Infographic output quality through source preparation, prompt engineering, and Custom Goals persona design.

演示文稿生成、叙事节奏设计和会议演讲优化。

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

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.

用户画像生成、角色注册、生命周期和跨智能体同步。

Configure and troubleshoot Honcho memory for Hermes.

Inspect untrusted external content for prompt injection when suspicious instructions or data-boundary risks need explicit analysis.

预演失败模式，识别计划风险并给出优先级。

Design or diagnose RAG ingestion, retrieval, permissions, reranking, citations, and evaluation when answers must be grounded in a specialized corpus.

Write or review operational runbooks for deployment, rollback, incidents, recovery, and maintenance using concrete commands and verification evidence.

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.

Apply Anthropic brand colors and typography when the user requests Anthropic visual identity or an Anthropic-branded artifact.

Building engineer self-branding by turning technical contributions into a professional brand. Use for GitHub/LinkedIn/blog/conference positioning or content strategy.

Propose one personal side-project idea scoped to a 1-3 day MVP when the user requests daily inspiration or weekend project ideation.

Consolidate overlapping documentation and remove repetition while preserving useful content, references, and ownership.

Verify factual claims against current authoritative sources and apply requested corrections with citations; use for accuracy checks or outdated documentation.

Generating and auditing personal dev environment configs (zsh/tmux/neovim/ghostty) and automating the macOS desktop via AppleScript/JXA (Finder, Mail, Safari). Use for dotfiles or Apple Events.

Design hiring interviews, competency matrices, question banks, scoring rubrics, and interviewer calibration for a specified role.

General-purpose LinkedIn automation – fetch profiles, search people and companies, send messages, manage connections, create posts, and more. Use when the user wants to interact with LinkedIn.

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."

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.

Manage product backlogs and sprints: user stories, acceptance criteria, epic breakdown, prioritization, estimates, and delivery tracking.

Create original static visual designs such as posters, artwork, and compositions as PNG or PDF artifacts.

Analyze competitors from product, pricing, reviews, SEO, and hiring evidence to produce feature comparisons, positioning, and actionable recommendations.

Build React/Next.js landing pages with Tailwind, focused copy, accessible sections, calls to action, metadata, and performance validation.

Prioritize features, synthesize customer research, and write PRDs or go-to-market plans using practical product management frameworks.

Strategic product leadership toolkit for Head of Product including OKR cascade generation, market analysis, vision setting, and team scaling. Use for strategic planning, goal alignment, competitive analysis, and organizational design.

User research specialist. Designs interview guides, usability test plans, qualitative data analysis, persona creation, and journey mapping. Complements Echo''s UI validation. Use when user research design or analysis is needed.

Build a SaaS application or vertical slice from a validated brief, covering authentication, tenancy, persistence, billing, deployment, and acceptance checks.

会话回放分析、行为模式提取和体验问题叙事。

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.

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

用户反馈收集、满意度调研、评论分析和洞察提炼。

红队场景、攻击路径、威胁建模和对抗演练设计。

隐私工程、敏感信息流、同意管理和数据治理。

用于通过 CodeQL 执行语义代码扫描、安全查询、自定义规则、SARIF 报告和 GitHub Code Scanning 集成。