All Skills

Builds a full-scope product roadmap for an existing project by scanning PRDs in /docs, extracting legacy tasks, and creating a comprehensive plan to move from MVP/early release to the next major stage.

Skills for querying ontologies using the Ontology Access Kit (OAK). This should only be used for complex ontology operations, for basic external ontology searching use the OLS MCP

Extracts semantic memory from project analysis. Scans codebase, docs, and configs to understand tech stack, constraints, and goals.

Message queues, events, and async communication patterns

Guidance for setting up API reference documentation generators — TypeDoc, Sphinx, godoc, and rustdoc. Detects project language, recommends the right tool, and provides configuration templates. Use when a project needs automated API documentation from source code comments.

Builds a full-scope product roadmap for an existing project by scanning PRDs in /docs, extracting legacy tasks, and creating a comprehensive plan to move from MVP/early release to the next major stage.

Batch create professional certificates with customizable templates for courses, achievements, and awards. Supports CSV input and PDF export.

Production LLM application patterns, architectures, and best practices. Covers RAG pipelines, agent architectures, prompt engineering, LLMOps, and production deployment patterns.

Compare document similarity using TF-IDF, cosine similarity, and Jaccard index. Use for plagiarism detection, duplicate finding, or content matching.

Archaeological rescue skill for abandoned projects. Reconstructs lost context through git archaeology, timeline analysis, and mission extraction.

This skill should be used when the user asks to "create a P2P app", "build with Holepunch", "use Hypercore", "use Hyperswarm", "create a Pear application", "build peer-to-peer", "use Hyperdrive", "use Hyperbee", "debug P2P connectivity", "choose between Hypercore modules", or mentions Holepunch, Pear runtime, HyperDHT, Autobase, Corestore, or Bare runtime. Provides guidance for building zero-infrastructure P2P applications.

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

Extracts work items as Beads and bundles them into Convoys for Gastown multi-agent execution.

OpenHarmony/KaihongOS C/C++ 编程规范。当 Claude 需要为 OpenHarmony、KaihongOS 移植项目编写或审查 C/C++ 代码时使用。涵盖：(1) 代码格式化（clang-format 配置），(2) 命名规范，(3) GN 构建配置，(4) 文档注释规范，(5) 权限配置，(6) 线程同步。

Use this when the user asks about performance, slowness, optimization, or wants to make code more efficient. Focus on hot paths, unnecessary work, and algorithmic complexity.

Resume work from a previous session using a handoff document. Use when starting a new session and a handoff.md exists, when the user says "resume", "pick up where we left off", or "read handoff", or when continuing work started in a previous Claude Code session.

Generate a complete project index with per-module README files for efficient code navigation. Use when starting work on a new project or after major restructuring. Run once per project.

Visualize phase logs as HTML reports.

# OHOS Permission Skill ## 概述 OpenHarmony/KaihongOS 特有的权限配置技术。涵盖 DSoftBus Session 权限、AccessToken 处理、配置文件格式规范等关键知识点。 **适用场景**: - rmw_dsoftbus ROS2 中间件开发 - DSoftBus 分布式软总线应用 - Native 应用权限配置 - 跨设备通信调试 **验证状态**: ✅ 2026-01-19 rk3588s KaihongOS API 11 真机验证通过 --- ## 快速开始 (3 步配置) ```bash # 1. 准备配置文件

Use this to design a nice UI in single html as inspiration & UI exploration.

Monitor Nx Cloud CI pipeline status and handle self-healing fixes automatically. Use when user says "watch CI", "monitor pipeline", "check CI status", "fix CI failures", or "self-heal CI". Requires Nx Cloud connection. Do NOT use for local task execution (use nx-run-tasks) or general CI debugging outside Nx Cloud.

Analyze competitors with feature comparison matrices, positioning analysis, and strategic implications. Use when researching a competitor, comparing product capabilities, assessing competitive positioning, or preparing a competitive brief for product strategy.

Use this for SQL queries, database schema design, ETL pipelines, data transformations (pandas/Spark), and data validation.

Initialize prompt-vault logging environment for the current project.