awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
BuilderIO avatar

BuilderIO/skills

0
View on GitHub↗
www.agent-native.com↗

Skills

This is a curated collection of installable skills that extend AI coding agents with reusable workflows, instructions, and tool integrations. Skills can be added through an interactive command line installer or a plugin marketplace, at user or project level, with optional instruction blocks and a pull request recap action.

The collection centers on overseeing and steering agent work. Some skills audit another agent's output by reconstructing the original request from a transcript, pull request, or branch and reporting gaps. Others compare competing agent plans and produce a decision memo before any code is written. Workflow-control skills let agents proceed through routine ambiguity while recording assumptions, pause near usage limits, hand heavy tasks to cheaper models, resume interrupted work, check official documentation before building against external APIs, and close each response with a green, yellow, or red status block.

Planning and review skills turn text plans and branch or pull request diffs into interactive, commentable visuals with diagrams, annotated code, and open questions. Pull request skills shepherd changes through checks and review, and ship verified changes under configurable policies that set separate rules for fixing, replying, approving, merging, and closing, so agents act only where allowed.

The collection also covers working with live apps and signals. Agents can open and drive web or native apps inside the host's browser, edit running apps visually with changes applied to real source code, and convert workflows into visual apps. Further skills gather feedback, usage data, and errors to find recurring failure patterns, summarize items awaiting human judgment, detect stalled delivery work, and recover recent screen context from local transcripts and captured frames.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Features

  • Agent Skill Installers - Installs chosen skills into coding agents through an interactive command line or plugin marketplace at user or project level.
  • Agent Skill Collections - Offers a curated set of installable skills that extend AI coding agents with reusable workflows, instructions, and tool integrations.
  • Agent Work Auditing and Plan Comparison - Audits another agent's output against the original request and compares competing agent plans into a decision memo before any code is written.
  • Commentable Visual Plans - Turns text plans into scannable, commentable visual plans with diagrams, file maps, annotated code, and open questions for approval.
  • Competing Plan Comparisons - Compares plans from several agents and writes a decision memo naming the winner, rejected options, and checks needed before building.
  • Autonomy Controls - Lets agents proceed through routine ambiguity while recording assumptions, pausing near usage limits, and handing heavy tasks to cheaper models.
  • AI Agent Skills - Bundles reusable skills and instructions that give coding agents workflows for planning, review, automation, and app inspection.
  • Policy-Gated Agent Automation - Sets sources, prompts, schedules, and separate fix, reply, approve, merge, and close rules so agents act only where allowed.
  • Work Audit Agents - Provides skills that audit another agent's output by reconstructing the original request from a transcript, pull request, or branch and reporting gaps.
  • Pull Request Automation - Shepherds pull requests through checks and review, and ships verified changes under policies with separate rules for fixing, replying, approving, merging, and closing.
  • Autonomous Coding Workflows - Lets agents work through routine ambiguity on their own, record assumptions, pause near usage limits, resume interrupted work, and report clear status.
  • Visual Diff Recaps - Turns a branch, commit, or pull request diff into an interactive recap with annotated changes, diagrams, schema summaries, and review notes.
  • Visual Plan and Diff Reviews - Converts text plans and branch or pull request diffs into commentable visuals with diagrams, annotated code, and open questions for fast approval.
  • Agent Status Reporting - Closes every agent response with a green, yellow, or red status block showing done, pending, and blocked work.
  • Agent Change Reviews - Reviews what another coding agent actually changed against the original request and reports gaps, plus compares competing plans before any code is built.
  • Documentation-Grounded Agent Verification - Searches official documentation before building against external APIs or current product behavior so work avoids stale memory.
  • In-Conversation App Operation - Opens web or native apps in the host's built-in browser and drives them through tool calls with live screen state.
  • Agent-Assisted Pull Request Shipping - Publishes delivery work as pull requests under verification and merge policies and replies to or closes the source item when allowed.
  • Interactive Diff Visualizers - Produces interactive, commentable recaps of branch or pull request diffs with annotated changes, diagrams, schema summaries, and review notes.
  • Live App Instance Inspections - Opens running web or native apps inside the conversation to inspect screens and routes, with visual edits applied to real source code.
  • Conversation-Driven App Editing - Opens web or native apps in the host browser, drives them from the conversation, and applies visual edits that change real source code.
  • Review and Merge Queues - Follow an authorized pull request through checks and review, and work through a queue of them using separate criteria for replying, approving, and merging.
  • Running App Visual Editing - Opens a running local app as address-backed screens to inspect routes and layouts and applies visual edits to real source code.
4,650 stars·238 forks·JavaScript·MIT·4 views

Star history

Star history chart for builderio/skillsStar history chart for builderio/skills

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

Frequently asked questions

What does builderio/skills do?

This is a curated collection of installable skills that extend AI coding agents with reusable workflows, instructions, and tool integrations. Skills can be added through an interactive command line installer or a plugin marketplace, at user or project level, with optional instruction blocks and a pull request recap action.

What are the main features of builderio/skills?

The main features of builderio/skills are: Agent Skill Installers, Agent Skill Collections, Agent Work Auditing and Plan Comparison, Commentable Visual Plans, Competing Plan Comparisons, Autonomy Controls, AI Agent Skills, Policy-Gated Agent Automation.

Which projects share features with builderio/skills?

Projects with overlapping indexed features include: browserbase/skills — This repository is a collection of installable browser automation skills and plugins for AI coding agents such as… feitangyuan/onetake — Onetake is a skill for AI coding agents that produces product launch films, teasers, and feature demos as a single… vinvcn/mattpocock-skills-zh-cn — This repository is a Simplified Chinese localization of a coding-agent skills collection. The skills are plain… gordensun/gordenpptskill — GordenPPTSkill is a reusable AI agent skill that builds real, editable PowerPoint decks from a library of… michael-denyer/pstack-claude — pstack-claude is a plugin and skills pack for AI coding assistants. It bundles rigorous engineering workflows,… modem-dev/hunk — Hunk is an interactive terminal diff viewer for reviewing code changes across many files. It presents a changeset as…

Projects sharing features with Skills

These projects share indexed features with Skills. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • browserbase/skillsbrowserbase avatar

    browserbase/skills

    3,756View on GitHub↗

    This repository is a collection of installable browser automation skills and plugins for AI coding agents such as Claude Code. Once installed, whether through a plugin marketplace or a single command, each agent can drive real web browsers from the command line for navigation, testing, scraping, and research. Browsers can be remote cloud sessions with CAPTCHA solving, residential proxies, and a persistent identity, or local ones: either a clean isolated browser or an already running browser whose cookies and login state are reused. Beyond basic browsing, the skills cover several specialized w

    JavaScript
    View on GitHub↗3,756
  • vinvcn/mattpocock-skills-zh-cnvinvcn avatar

    vinvcn/mattpocock-skills-zh-CN

    5,600View on GitHub↗

    This repository is a Simplified Chinese localization of a coding-agent skills collection. The skills are plain Markdown instruction documents that guide coding agents through repeatable engineering tasks: planning, test-driven development, debugging, code review, and issue triage. Commands, code, and file paths stay unchanged in the translation, which tracks the English upstream through periodic merges, each checked by a person before it is accepted. The skills cover several stages of the development workflow. Planning and alignment skills interview the user until a plan or design is fully re

    JavaScriptai-agentchinesedeveloper-skills
    View on GitHub↗5,600
  • feitangyuan/onetakefeitangyuan avatar

    feitangyuan/onetake

    3,918View on GitHub↗

    Onetake is a skill for AI coding agents that produces product launch films, teasers, and feature demos as a single continuous take. It installs by cloning into an agent's skills folder, after which plain-language requests can trigger the whole workflow of planning, building, and rendering. Each beat in the film grows out of the previous element instead of replacing it, so scenes flow together rather than reading as slides. What sets it apart is how it plans and checks that continuity. It can break a reference film down into measurable data such as stillness, cut positions, and motion easing,

    Pythonagent-skillanimationcanvas
    View on GitHub↗3,918
  • gordensun/gordenpptskillGordenSun avatar

    GordenSun/GordenPPTSkill

    3,932View on GitHub↗

    GordenPPTSkill is a reusable AI agent skill that builds real, editable PowerPoint decks from a library of hand-polished Chinese-language slide templates. A language-model agent installs it from a repository link, and the user then describes the deck they want in plain language, pointing to local source files. The skill selects a template and produces a native .pptx file. Its approach is to leave the template's design alone. Text edits are supplied in a JSON file and applied only to the words inside existing shapes, so fonts, positions, and visual formatting stay as the template designer made

    Python
    View on GitHub↗3,932
Compare all 30 related projects→