Builder.io publishes agent skills for overseeing and coordinating other coding agents, including watching a Codex or Claude Code session and independently checking its work, comparing competing plans from multiple agents and choosing one, and running autonomous work that keeps going without routine check-ins. Their skills also cover recurring audits of feedback and errors, summarizing items that need human review across pull requests and issues, managing usage limits during long parallel runs, and shipping configured software delivery work.
Skills
25 skills · 4,649 stars · MIT
Adding A Skill Use in the BuilderIO/skills repo whenever adding, updating, publishing, documenting, validating,…
Agent Watchdog Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Code…
An Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, brow…
Efficient Fable Use when running Claude Fable on codebase-heavy or token-heavy work and the user wants Fable to o…
Efficient Frontier Apply the same orchestration as `/efficient-fable` to any high-cost frontier model: delegate rese…
Factory Experimental workflow for configuring an autonomous software delivery factory.
Factory Babysit Pr Experimental workflow for babysitting one explicitly authorized pull or merge request.
Factory Collect Experimental workflow for collecting and triaging product feedback, product telemetry, runtime er…
Factory Human Digest Experimental workflow for summarizing work that still needs human judgment across configured pull…
Factory Lookback Experimental workflow for auditing recurring feedback, telemetry, errors, and brittle delivery pa…
Factory Recover Experimental workflow for finding and resuming interrupted coding runs.
Factory Review Prs Experimental workflow for reviewing configured repositories' pull requests.
Factory Ship Experimental workflow for publishing and completing configured software delivery work.
Factory Watchdog Experimental workflow for monitoring explicitly authorized delivery tasks and reporting stalled w…
Plan Arbiter Use when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from…
Plow Ahead Use when the user explicitly wants autonomous progress without routine clarification stops: "plow…
Quick Recap Use when adding or following the red/yellow/green final status block convention for agent respons…
Read The Damn Docs Use when implementing, integrating, upgrading, debugging, or answering anything involving third-p…
Rewind Retrieve recent local Clips Rewind context when the user says "Look at Rewind," asks what just ha…
Stay Within Limits Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by check…
Turn Into App Turns a thread, skill, spreadsheet, or Claude/ChatGPT project into a polished, visual Agent-Nativ…
Visual Edit Open and collaboratively edit a running local app in Design, with shared fallback previews and so…
Visual Plan Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated c…
Visual Recap Turn a PR, branch, commit, or git diff into an interactive visual recap with diagrams, file maps,…
Webmcp Open a user-provided URL in the host's built-in browser and use the page's MCP or WebMCP tools be…