Skills your agents can run

Check OpenAI Codex CLI rate limit status (daily/weekly quotas) using local session logs. Portable Python script. Reads ~/.codex/sessions/ for quota data. When using --all --yes, it temporarily switches accounts by overwriting ~/.codex/auth.json (restored afterwards) to query each account. Uses the `codex` CLI for --fresh / --all.

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

Audit and improve CLAUDE.md files in repositories. Use when the user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs a quality report, then makes targeted updates. Also use when the user mentions “CLAUDE.md maintenance” or “project memory optimization.”

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR.

Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas.

百度 AI 搜索。支持网页搜索、百度百科、秒懂百科、AI 智能生成四种模式。自动包含当前日期上下文。当用户要求搜索信息、查询百科、获取最新资讯、搜索新闻、查找资料时使用。

RAG and semantic search via OpenViking Context Database MCP server. Query documents, search knowledge base, add files/URLs to vector memory. Use for document Q&A, knowledge management, AI agent memory, file search, semantic retrieval. Triggers on "openviking", "search documents", "semantic search", "knowledge base", "vector database", "RAG", "query pdf", "document query", "add resource".

When the user wants to design a sales compensation plan, set quotas, build accelerators, model plan costs, or create SPIFs. Also use when the user says 'design a comp plan,' 'set sales quotas,' 'build accelerators,' 'sales compensation,' 'OTE structure,' 'SPIF design.' For quota-setting inputs from forecast data, see forecast. For pipeline data that informs quota realism, see pipeline-review.

Monitor topics of interest and proactively alert when important developments occur. Use when the user wants automated monitoring of specific subjects (e.g., product releases, price changes, news topics, technology updates). Supports scheduled web searches, AI-powered importance scoring, smart alerts versus weekly digests, and memory-aware contextual summaries.

Generate professional PowerPoint pitch decks for startups and businesses. Use this skill when users request help creating investor pitch decks, sales presentations, or business pitch presentations. The skill follows standard 10-slide pitch deck structure and includes best practices for content and design.

Fix your entire life in 1 day. 10 psychological sessions based on Dan Koe's viral article.

Automatically summarizes conversation context and cleans up old messages to prevent context overflow and save tokens.

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

Use when building Go applications requiring concurrent programming, microservices architecture, or high-performance systems. Invoke for goroutines, channels, Go generics, gRPC integration.

Generate comprehensive, maintainable unit tests across languages with strong coverage and edge case focus.

Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and Pydantic v2. Master microservices, WebSockets, and modern Python async patterns.

Keep project documentation (.agents/project-index.md and sub-skills) in sync with codebase changes.

Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

Use this skill whenever writing, debugging, or reviewing Frida instrumentation scripts targeting iOS ARM64 or Android. Triggers include: any mention of 'Frida', 'dynamic instrumentation', 'hooking', 'Interceptor', 'Stalker', 'ObjC bridge', 'Java bridge', 'frida-server', 'frida-gadget', 'NativeFunction', or requests to hook/trace/patch native or managed functions at runtime. Also use when bypassing SSL pinning, root detection, anti-cheat systems, or Frida self-detection. Apply for both JavaScript and TypeScript agents targeting frida-tools 14+ and Frida 17.x. Do NOT use for static binary analysis (use radare2/Ghidra skills instead), build-time patching, or non-Frida instrumentation frameworks.

Feature-first project structure and separation of concerns for React Native. Use when structuring a React Native project or applying clean architecture patterns.