Loading...
Loading...
Found 6,492 Skills
Best practices for using agent-browser with Kernel cloud browsers. Use when automating websites with agent-browser -p kernel, dealing with bot detection, iframes, login persistence, or needing to find Kernel browser session IDs and live view URLs.
When a step fails during an agentic task, classify the error (transient, configuration, logic, or permanent), apply the right recovery strategy, and escalate to the user when all strategies are exhausted. Triggers on error messages, exceptions, tracebacks, "failed", "not working", "retry", or when 2 consecutive steps fail.
Design and refactor Agent Skills with concise, high-signal instructions and explicit trigger metadata. Use when creating a new skill, revising SKILL.md/README.md structure, or improving skill discoverability and portability.
Use when an existing agent already works without Prefactor and you need to add tracing for runs, llm calls, tool calls, and failures with minimal behavior changes.
Private browser testing rules for jb workflows. Prefer playwrighter_exec with careful tab selection, fall back to agent-browser, and avoid playwright-mcp.
Comprehensive Python engineering guidelines for writing production-quality Python code. This skill should be used when writing Python code, performing Python code reviews, working with Python tools (uv, ruff, mypy, pytest), or answering questions about Python best practices and patterns. Applies to CLI tools, AI agents (langgraph), and general Python development.
Query Light Protocol and related repositories via DeepWiki MCP. Use when answering questions about compressed accounts, Light SDK, Solana development, Claude Code features, or agent skills. Triggers on technical questions requiring repository context.
Manage Cursor Cloud Agents via the API. Launch agents, list running agents, check status, get conversation history, send follow-ups, stop or delete agents, and pull agent branch changes into the local repo. Use when the user mentions cloud agents, background agents, launching a task on a repo, checking agent status, or pulling agent changes.
Control OpenCode directly via the Agent Client Protocol (ACP). Start sessions, send prompts, resume conversations, and manage OpenCode updates.
Generate usage insight reports based on local Cursor Agent session records; only invoke when the user explicitly requests phrases like 'generate session analysis report' or 'create an Agent usage insight'.
Systematic documentation audit and maintenance. This skill should be used when documentation may be stale, missing, or misorganized — after feature work, refactors, dependency upgrades, or as a periodic health check. It prescribes folder structure for docs/ and manual/, dispatches haiku subagents for codebase/doc scanning, and routes doc creation to specialized agents (reference-builder, technical-writer, learning-guide) with docs-architect as quality gate.
Set up a complete book writing workspace with AI agents, instructions, prompts, and scripts. Use when users want to create a new book/technical writing project with Markdown + Re:VIEW + PDF output workflow. Triggers on "book writing workspace", "technical book project", "執筆ワークスペース", or similar project setup requests.