Loading...
Loading...
Found 7,226 Skills
Use this skill when the user wants any MCP-capable agent or IDE assistant to interact with Google ADK agents through the adk-agent-extension MCP server. Trigger for requests like wiring ADK tools into Codex/Claude Code/Cursor/Cline/Gemini, registering a stdio MCP server, listing ADK servers/agents, creating sessions, and chatting with ADK agents.
Creates a QA planning subtask in the configured issue tracker tagged `qa-plan`, with test cases derived only from the ticket's functional and technical requirements.
Pushes the current branch, creates a PR linked to the configured tracker issue, comments the PR link on the issue, and moves the issue to In review.
Implement feature tasks using AI agents in logical batches, track completion status, identify blockers, and manage task handoffs. Use when you have an execution sequence and need AI agents to build tasks while maintaining progress tracking.
Generates custom Claude Code subagents with specialized expertise. Activates when user wants to create a subagent, specialized agent, or task-specific AI assistant. Creates properly formatted .md files with YAML frontmatter, suggests tool restrictions and model selection, generates effective system prompts. Use when user mentions "create subagent", "new agent", "specialized agent", "task-specific agent", or wants isolated context for domain-specific work.
Validate agent skills for correctness, readability, workflow clarity, and isolation, ensuring they can be installed independently without dependencies on other skills.
Reviews PR changes against issue technical details and acceptance criteria, posts concise outcomes to PR and issue tracker, and routes autonomous next steps.
Cross-tool compatibility workflow. Use when generating AGENTS.md files for compatibility with other AI coding tools, or creating tool-specific instruction files from CLAUDE.md.
No Polling for Background Agents
Check your agent's on-chain ERC-8004 identity, trust score, and KYA credentials. Use when you or the user want to see agent identity, check trust score, view KYA credentials, or check agent status. Covers phrases like "what's my agent ID", "check trust score", "show my identity", "agent status", "KYA credentials".
8-agent QA loop: browser exploration via Playwright MCP, then analyze, plan, test, audit, heal, expand, snapshot. Quality gate score >= 85 to pass.
Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates.