virtus

Generate a rich, self-contained HTML artifact for specs, code reviews, designs, reports, or custom editors. Use when the user asks for an "HTML file/artifact/explainer/report/playground", wants a shareable visual deliverable instead of markdown, or asks to "make a canvas/dashboard/diagram-heavy doc". Trigger phrases include "make an HTML", "html artifact", "html canvas", "html report", "html explainer", "html playground", "visual spec", "html mockup".

Portable strategy knowledge base for this repository — bundled notebooks, local markdown notes, and code implementations grouped by topic under the skill's own `ref/` folder. Use when answering research questions about these strategies, locating implementation files, or searching topic summaries from a self-contained skill bundle.

Answer questions about Claude and Anthropic products using official claude.com/blog posts as a knowledge base, and refresh the local blog cache when current coverage matters. USE when: user asks how Claude Code works, asks about Claude features (MCP, skills, artifacts, prompt caching, tool use, web search, context windows), asks about Claude plans or pricing, asks about Claude integrations (Slack, Microsoft 365, Amazon Bedrock), asks for enterprise AI use cases or case studies, asks about agent skills or multi-agent systems, asks about best practices for prompting or building with Claude, asks for latest/newest/current Claude blog information, or asks to update/fetch/refresh the Claude blog index. NOT USE when: user is asking about a non-Claude AI product or provider, asking general programming questions unrelated to Claude, asking about Anthropic safety research or model internals not covered in blog posts, or the question can be answered from existing conversation context without needing blog references.

Help write, modify, review, and debug WalrasQuant trading strategy files. Use when Codex needs to create or edit strategy scripts under the strategy directory, subclass walrasquant.strategy.Strategy, wire Config and Engine, use subscriptions, event handlers, schedules, indicators, cache access, order APIs, precision helpers, execution algorithms, or wq process commands for WalrasQuant strategies.

Review git changes first, then create an appropriate commit, create or choose a release tag, and push the branch and tag. Use when the user asks to auto commit, tag, push, publish a release tag, or prepare a git-based release after local changes are ready.

Clean Chinese SRT subtitle files generated by speech recognition. Use this skill whenever the user has a .srt file with Chinese subtitles that need fixing — misrecognized words, wrong technical terms, brand names, or filler words like 啊/嗯/呢/这个. Trigger on requests like "修复字幕识别错误", "删除口语词", "清理字幕", "fix srt", or any mention of cleaning/fixing subtitle files.

Build a stunning personal website from a resume PDF. Use this skill whenever the user wants to create a personal website, portfolio site, or online resume from a PDF resume/CV. Also trigger when the user mentions converting a resume to a website, building a portfolio from their CV, or wants a personal landing page based on their professional background.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Build, debug, extend, or deploy Claude Agent SDK agents in Python or TypeScript. Use this skill whenever someone mentions the Claude Agent SDK, agent loops, query(), ClaudeAgentOptions, subagents, hooks, MCP servers in the context of the Agent SDK, structured output from agents, multi-turn sessions with resume/fork, deployment of SDK agents to production, or migrating from the old Claude Code SDK. Covers installation, quickstart, message streaming, sessions, custom tools, permissions, observability, and production deployment.