Loading...
Loading...
Found 3,323 Skills
Expert UX design assistance for user research, wireframing, prototyping, and design strategy. Use when: creating wireframes, conducting user research, building prototypes, designing user flows, writing UX copy, reviewing designs for usability, creating personas, planning usability tests, or when user mentions UX design, user experience, wireframes, prototypes, user research, information architecture, or design systems.
Document undocumented public APIs in PyTorch by removing functions from coverage_ignore_functions and coverage_ignore_classes in docs/source/conf.py, running Sphinx coverage, and adding the appropriate autodoc directives to the correct .md or .rst doc files. Use when a user asks to remove functions from conf.py ignore lists.
This skill should be used when the user asks to "break down tasks", "create a task list", "plan implementation", "decompose architecture", "create agent tasks", "plan MVP build", "break down feature", "create execution plan", or mentions task breakdown, agent development workflow, or implementation planning. Two-phase workflow for AI agent development with granular, testable tasks.
Full Caido SDK integration for Claude Code. Search HTTP history, replay/edit requests, manage scopes/filters/environments, create findings, export curl commands, and control intercept - all via the official @caido/sdk-client. PAT auth recommended.
When the user wants to design, optimize, or audit call-to-action (CTA) buttons. Also use when the user mentions "CTA," "call to action," "button design," "conversion button," "primary action," "CTA copy," "button text," "CTA placement," "conversion CTA," or "action button."
Post-implementation reality check. Run after tests pass, before declaring done. Use when completing a feature, bug fix, refactor, or integration — or when asked to verify, sanity check, or confirm something actually works.
TianQin SDK (tqsdk) - Python量化交易框架，用于期货/期权/股票交易策略开发、回测与实盘交易
Test and prototype code in a sandboxed environment. Use for debugging, verifying logic, or installing packages.
Improve test coverage in the OpenAI Agents Python repository: run `make coverage`, inspect coverage artifacts, identify low-coverage files, propose high-impact tests, and confirm with the user before writing tests.
Concurrency exploitation — race conditions, TOCTOU vulnerabilities, and parallel request abuse in web applications.
Build and deploy agentic finance applications on the Alva platform. Access 250+ financial data sources (crypto, equities, macro, on-chain, social), run cloud-side analytics, backtest trading strategies, and release interactive playbooks -- all from your AI agents.
Persistent browser interaction through a normal Node.js Playwright script for fast iterative web UI debugging.