build-things
Build software features end to end in an existing repository. Use when the user asks to build, implement, add, create, wire up, or ship code changes, including backend, frontend, APIs, and automation tasks.
Best use case
build-things is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Build software features end to end in an existing repository. Use when the user asks to build, implement, add, create, wire up, or ship code changes, including backend, frontend, APIs, and automation tasks.
Teams using build-things should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/build-things/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How build-things Compares
| Feature / Agent | build-things | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Build software features end to end in an existing repository. Use when the user asks to build, implement, add, create, wire up, or ship code changes, including backend, frontend, APIs, and automation tasks.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Build Things Execute implementation work from request to verified result. ## Workflow 1. Confirm scope from the user request. 2. Inspect the relevant code paths before editing. 3. Implement the smallest complete change that satisfies the request. 4. Prefer edits that match existing project patterns. 5. Run focused checks for the changed area (tests, lint, build, or app command). 6. Report what changed, what was validated, and any remaining risks. ## Implementation Rules - Keep diffs minimal and avoid unrelated refactors. - Reuse existing utilities and abstractions before adding new ones. - Preserve backwards compatibility unless the user requested a breaking change. - Add or update tests when behavior changes. - If validation cannot run, state exactly what could not be run and why. ## File Review Pattern - Read entrypoints and nearby modules first. - Trace call sites and side effects before changing interfaces. - Check config, environment assumptions, and platform-specific paths. ## Output Contract Return a concise summary that includes: - Changed files and intent. - Verification commands executed and key outcomes. - Open issues, follow-ups, or assumptions.
Related Skills
claude-agent-sdk-builder
Guide for building agents with the Claude Agent SDK (TypeScript/Node.js). Use when creating SDK-based agents, custom tools, in-code subagents, or production agent applications. Provides templates, patterns, and best practices for agent development.
chatgpt-app-builder
Build ChatGPT apps with interactive widgets using mcp-use and OpenAI Apps SDK. Use when creating ChatGPT apps, building MCP servers with widgets, defining React widgets, working with Apps SDK, or when user mentions ChatGPT widgets, mcp-use widgets, or Apps SDK development.
building-streamlit-custom-components-v2
Builds bidirectional Streamlit Custom Components v2 (CCv2) using `st.components.v2.component`. Use when authoring inline HTML/CSS/JS components or packaged components (manifest `asset_dir`, js/css globs), wiring state/trigger callbacks, theming via `--st-*` CSS variables, or bundling with Vite / `component-template` v2.
building-chatgpt-apps
Guides creation of ChatGPT Apps with interactive widgets using the Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Developer Mode configuration. NOT when building standard MCP servers without widgets (use building-mcp-servers skill instead).
Build Script-Execution Skill
Create a skill that orchestrates the write-execute-analyze loop to autonomously process data. Learn to implement error recovery, iterate toward robust solutions, and test your skill across diverse input scenarios. This is where specification-driven development meets real problem-solving.
build-app-step01
Use when users are building or scaling ChatGPT Apps / Apps SDK / MCP-based apps and want a preventive workflow to avoid common pitfalls before implementation, deployment, and growth. Trigger for requests about best practices, preflight checks, guardrails, checklists, workflow SOP, reliability, evals, and production readiness.
build-and-test
Build, test, lint, and validate the Phoenix Agentic Website Frontend. Use when user asks to build, compile, test, lint, run checks, fix test failures, or validate changes in the Website Frontend repo.
build-agent-python
Python build agent for scripts, backends, data pipelines, and ML projects. Extends build-agent with Python conventions. Use when building Python applications, APIs, data processing, or automation.
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
awesome:web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
app-builder
Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.