Coding & Development

dating coach skill —— 读懂你和她、起草高张力不掉价的回复、给约会节奏与行动建议;有分寸、不 PUA、不舔。支持 Claude Code 与 OpenAI agent。

Local-first AI PC Agent Skill for private daily memory from configured notes, docs, schedules, DingTalk, Feishu, and Obsidian sources.

Open discovery, audit, and recommendation infrastructure for AI agent skills.

9 quality-canary skills for AI coding agents - code health, gold-standard rules, anti-hallucination grounding, supply chain, resilience, observability, testability, scaling, contract drift. Consent-gated, token-lean, one-button install, works across all major AI coding agents.

🛠️ Automate processes with Openclaw, a containerized solution for seamless AI integration using Docker for easy setup and management.

🤖 Explore and manage skills in the open agent ecosystem with this powerful CLI tool, supporting multiple agents including Opencode and Codex.

🤖 Connect DingTalk with OpenClaw Gateway for AI-driven chat responses and session management using a bot or DEAP Agent integration.

跨项目知识库整理 Skill：信息分层归位、权限白名单优化、历史对话提炼。Claude Code 全局整理工具。

Skills personales de Carlos Osuna para Claude Code: disciplina de PRs, manejo seguro de operaciones destructivas, espa\xC3\xB1ol venezolano neutro y otras pr\xC3\xA1cticas refinadas en varios proyectos.

Write documentation following Metabase's conversational, clear, and user-focused style. Use when creating or editing documentation files (markdown, MDX, etc.).

Machine learning development with JAX, functional programming patterns, and high-performance computing.

Bundle TypeScript and JavaScript libraries with blazing-fast speed powered by Rolldown. Use when building libraries, generating type declarations, bundling for multiple formats, or migrating from tsup.

Build and run evaluators for AI/LLM applications using Phoenix.

OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.

Adversarial code review using cross-model approach. Spawns reviewers on the opposing model (Claude uses Codex, Codex uses Claude) to challenge work from distinct critical lenses. Produces a synthesized verdict with findings and lead judgment. Triggers: "adversarial review".

Validate a business idea using the minimalist entrepreneur framework. Use when someone has a business idea and wants to test if it's worth pursuing before building anything.

Generate comprehensive trading plans with risk management, position sizing, entry/exit strategies, and performance tracking to trade with discipline and consistency.

自动分析B站视频内容，下载视频并拆解成帧图片，使用AI分析并生成详细的专题文档或实操教程。

Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.

Use when FastAPI async patterns for building high-performance APIs. Use when handling concurrent requests and async operations.

Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.

This skill should be used when generating comprehensive test cases from PRD documents or user requirements. Triggers when users request test case generation, QA planning, test scenario creation, or need structured test documentation. Produces detailed test cases covering functional, edge case, error handling, and state transition scenarios.

Set reminders using natural language. Automatically creates one-time cron jobs and logs to markdown.

Plan and break down user-story issues into ordered, traceable task issue drafts with explicit publish gates.