Agents & automation skills

Discover and install skills from skills.sh directly inside an agent session

Full browser automation: navigate, click, fill forms, extract data, and screenshot

Compress conversations into handoff docs so another agent can seamlessly continue your work

Move issues and PRs through triage states, categorize work, and generate agent-ready briefs

Build interactive prototypes to validate UI designs or state logic before full implementation

Systematically stress-test plans and decisions by mapping dependencies and asking frontier questions

This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use…

Complete agent development lifecycle: scaffold, build, evaluate, deploy, and monitor ADK agents on Google Cloud

Create, test, and publish new skills from within your agent

Structured ideation and problem decomposition frameworks

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any…

When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or…

Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…

Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator…

Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family,…

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

Search, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage,…

Execute implementation plans task-by-task in your current session with test-driven gates

Execute implementation plans by spawning focused subagents per task with integrated review cycles

Dispatch independent tasks to specialized agents working in parallel with isolated context

A catalog of 2,658+ installable SKILL.md playbooks plus a local MCP control plane that lets your agent discover, pick and validate the skills it needs.