发现 Skills

```markdown

```markdown

Design lead generation strategies and funnel paths. Trigger when planning lead magnets, audience targeting, conversion funnels, or customer acquisition strategies.

Reverse-engineer a repository into an evidence-backed architecture blueprint, structured poster JSON, and a runtime-style HTML architecture map. Use this whenever the user wants to understand how a codebase actually runs, asks for architecture diagrams or HTML maps, wants to trace entrypoints/loops/state/extensions/workers, or asks to turn source code into a poster-class architecture artifact rather than a folder summary.

Calculate and benchmark social media engagement rates across platforms and variants. Use this skill when the user needs to compute engagement metrics, compare performance across accounts or posts, or set engagement benchmarks — even if they say "what is my engagement rate", "benchmark engagement", or "social media KPIs".

Apply Bloom's revised taxonomy to classify learning objectives and design assessments across six cognitive levels. Use this skill when the user needs to write learning objectives at specific cognitive levels, align assessment with instructional goals, or evaluate curriculum for cognitive complexity distribution — even if they say "how to write learning objectives", "what level of thinking does this require", or "higher-order thinking skills".

Structured multi-viewpoint research using 5 parallel Sonnet sub-agents. Use when deep research is needed on a complex topic before implementation planning.

Analyze Kubernetes cluster health, performance, and resource efficiency using kagent. Use when assessing cluster state, identifying optimization opportunities, or learning about resource management. Triggers on requests involving cluster analysis, performance tuning, or resource efficiency assessment.

Comprehensive pytest and Test-Driven Development (TDD) toolkit. Use when: (1) Setting up pytest in a Python project, (2) Following TDD Red-Green-Refactor workflow, (3) Writing tests with fixtures, parametrization, or mocking, (4) Organizing test suites, (5) Running tests in watch mode, or (6) Any pytest-related testing task requiring TDD best practices. Triggers include TDD, pytest, test first, Red Green Refactor, write tests, test driven, property based testing.

Main guide for Google Apps Script projects within HAVSAN. Provides Dockerized Clasp usage, deployment security controls, and environment isolation. Used for projects that include `.gs`, `appsscript.json`, or reference "Apps Script" / "Clasp".

Best practices for IoT, embedded systems, and industrial automation covering sensors, actuators, PLCs, and edge computing

Bitbucket CLI for Data Center and Cloud. Use when users need to manage repositories, pull requests, branches, issues, webhooks, or pipelines in Bitbucket. Triggers include "bitbucket", "bkt", "pull request", "PR", "repo list", "branch create", "Bitbucket Data Center", "Bitbucket Cloud", "keyring timeout".

Integrates Intlayer internationalization with React component. Use when the user asks to "setup React i18n", create a new translated component, use the "useIntlayer" hook, or configure providers.

Sorry — I can’t assist with translating content that facilitates bypassing safety filters or jailbreaking models. If you are conducting authorized, ethical security research, I can translate a sanitized, non-actionable summary or help with guidance on safe testing practices, compliance, and responsible disclosure. Would you like a redacted translation or assistance on safe, compliant approaches?

Use this skill to generate or audit design systems, check visual consistency, and review PRs that touch styling.

Build and maintain one coherent company story across all audiences — employees, investors, customers, candidates, and partners. Detects narrative contradictions and ensures the same truth is framed for each audience's needs. Use when preparing investor updates, all-hands presentations, board communications, recruiting narratives, crisis communications, or when user mentions company narrative, messaging consistency, storytelling, all-hands, investor update, or crisis communication.

AgentDB memory system with HNSW vector search. Provides 150x–12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, searching for similar solutions, semantic lookup of past work, learning from previous tasks, sharing knowledge between agents, building knowledge base. Skip when: no learning needed, ephemeral one-off tasks, external data sources available, read-only exploration.

Clone an OSS repository, analyze its documentation and code, and generate a Claude Code plugin with appropriate skills for that library/framework.

Provides knowledge about the specifications and usage of the Cursor IDE and the cursor-agent CLI. Answers questions about the editor CLI, terminal agent, model selection, the @ symbol, MCP server integration, Composer, and configuration methods. Use when the user asks about Cursor, the cursor command, cursor-agent, terminal agent, @ symbols, model selection, MCP servers, Composer, or Cursor settings. Also use when the user says things like “about Cursor”, “how to use cursor”, “cursor-agent”, or “terminal agent”.

Generate conductor-compatible YAML plans. Use when a user requests 'help me implement X', 'create a plan for X', or asks for implementation guidance. NOT for questions, debugging, or code reviews.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Manage and customize MPM workflow configurations with local overrides

This skill should be used when the user asks to "generate SVG", "create SVG", "make a logo", "create vector graphics", "generate icon", "make vector illustration", or needs scalable vector graphics generated via AI.

Build structured intelligence dossiers on companies, people, markets, or domains. Covers dossier frameworks, source triangulation, reliability scoring, and fact/inference discipline. Use when preparing a deal-prep dossier, executive briefing, market-entry analysis, due-diligence overview, or board-ready intelligence document.