Skills for Real Engineers. Straight from my .agents directory.
constraint-driven-development
Agent skill fromaddyosmani/agent-skills
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or eslint-disable suppressions, skipped or deleted tests, assertions stripped out, unimplemented stubs, thresholds edited down. Use when no quality bar is written down, when the user says "set up constraints" or "define our standards", when the user wants dimensions they care about — accessibility, web performance, coverage — set up as enforced constraints, when an agent keeps silencing checks or skipping tests to get to green, when you need a coverage or performance threshold and don't know what number to pick, or when an agent writes more code than anyone will read.
How to install constraint-driven-development
npx skills add addyosmani/agent-skills# or add only this skill to Claude Code: copy the folder
skills/constraint-driven-development/
# into
~/.claude/skills/constraint-driven-development/ (all projects)
.claude/skills/constraint-driven-development/ (one project)
1# Constraint-Driven Development23## Overview45Other skills in this pack describe what good looks like. `code-review-and-quality` gives you five axes. `test-driven-development` gives you a cycle. `security-and-hardening` gives you a threat list. All of that lives in prose the agent reads and may or may not follow, and none of it survives the end of the session.67This skill produces something different: a written record of **this project's** bar, with numbers, that outlives the conversation and can be checked mechanically.89The reason matters. When you wrote the code, reading it told you whether it was any good. An agent writes more in an afternoon than you will read that week, so the judgement moves out of your head and into checks that run around the loop. Those checks need to exist, they need numbers you actually chose, and they need to fire close enough to the work that the agent fixes its own output.1011Spec-driven development says what to build. Test-driven development proves it works. Constraint-driven development defines what "good enough to ship" means, before anyone argues about it in a pull request.1213## When to Use1415Apply this skill when:1617- Starting a project or a significant feature and no quality bar is written down18- The user asks to "set up constraints", "add quality gates", "define our standards", or "stop the agent shipping junk"19- An agent is producing volume nobody is reading line by line20…
Excerpt shown under the repository's MIT license.
More skills in agent-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
