Claude Skills by seaworld008

Product marketing skill for positioning, GTM strategy, competitive intelligence, and product launches. Covers April Dunford positioning, ICP definition, competitive battlecards, launch playbooks, and international market entry.

Build MCP servers that expose external APIs or services through well-scoped tools in Python or TypeScript.

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.

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.

Purpose: Zero-downtime migration planning, compatibility validation, and rollback strategy generation.

Inspect or improve Turborepo, Nx, pnpm, or Lerna monorepos: package boundaries, dependency graphs, selective tests, caching, and migrations.

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

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

Diagnose excessive Postgres or Neon network egress and database transfer costs by tracing query volume, payloads, polling, and connection behavior.

Build or troubleshoot Neon Postgres connections, branching, pooling, scaling, Auth, and platform integrations using current Neon documentation.

Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys.

Master Next.js 14+ App Router with Server Components, streaming, parallel routes, and advanced data fetching. Use when building Next.js applications, implementing SSR/SSG, or optimizing React Server Components.

多智能体任务分解、链路编排、执行协调和结果整合。

Audit SKILL.md, AGENTS.md, prompts, hooks, and plugin manifests for instruction conflicts, quality, broken references, and manifest-to-disk drift.

用于把对话、决策和笔记沉淀到 Notion。

用于基于 Notion 上下文准备会议材料。

用于整合 Notion 信息并生成研究文档。

用于把 Notion 规格转成计划、任务和进度跟踪。

Add or improve logs, metrics, traces, and alerts when services need diagnosable production behavior or operational acceptance evidence.

Design production observability with SLI/SLO definitions, actionable alerts, telemetry and dashboards.

Read, search, create, or edit notes in an authorized Obsidian vault while preserving frontmatter, wikilinks, and unrelated notes.

预演失败模式，识别计划风险并给出优先级。

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

Use when evaluating an options structure, checking expiry payoff checkpoints, comparing premium outlay versus downside protection, or preparing a short strategy note for a trade review.

人工智能应用设计、评估、检索增强和安全护栏规划。

用于通过 OSV-Scanner 检查锁文件、清单、SBOM、Git 历史和源码树中的开源依赖漏洞。

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

Investigate and improve measured frontend, backend, query, or database bottlenecks; use profiling and workload evidence to protect the gains.

Profile Node.js, Python, or Go CPU, memory, I/O, and query bottlenecks; use flamegraphs and representative load tests to verify improvements.

Designing GitHub Actions workflows in depth: trigger strategy, security hardening, performance optimization, PR automation, and Reusable Workflow design.

Turn clear requirements into ordered tasks, dependencies, and acceptance checks; preserve unfinished work when revising an existing plan.

Production-grade Playwright testing skill for E2E suites, flaky test diagnosis, browser automation, migration from Cypress/Selenium, CI integration, visual checks, and regression validation.

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.

Use when reviewing portfolio exposures, checking concentration and beta risk, summarizing sector or region tilts, or preparing a risk note before reallocating capital.

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

Review GitHub PRs or GitLab MRs for correctness, security, compatibility, and affected test coverage, with actionable evidence tied to the diff.

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

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.

Refine prompts or ambiguous requirements into testable specifications when the user asks to improve wording, scope, constraints, or acceptance criteria.

Configure and run Promptfoo evaluations, assertions, rubrics, and datasets when testing LLM prompts or comparing model behavior.

关键指标、埋点、漏斗、留存和仪表盘规格设计。

Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving application performance.

Design QA strategies, risk-based test cases, execution plans, and defect reports when establishing or improving software quality assurance.

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

多会话并行执行编排，协调多个智能体共同完成任务。

Build, debug, upgrade, or ship React Native and Expo apps, including navigation, native modules, iOS/Android differences, performance, and EAS delivery.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Review user corrections or session outcomes to propose durable workflow improvements. Persist memory or edit agent guidance only when requested.