Keeps UI work consistent with an app's DESIGN.md design system and decision log. Use when building or modifying UI in a repo with a DESIGN.md (or one that keeps drifting without it), when new screens must match existing ones, when buttons or patterns come out different every session, or when design decisions get lost between sessions.
EnglishReverse-engineers a DESIGN.md (Google Labs format) from an already-built project and measures its design drift. Use whenever an existing codebase should adopt DESIGN.md, when UI values have multiplied (several grays, mixed radii, inconsistent buttons), when the owner says the UI looks inconsistent or "quedó desprolijo", or to re-audit drift after a migration batch — even if nobody says the word DESIGN.md.
EnglishAdversarial review of plans, specs, and proposals before execution — verifies references, extracts and rates assumptions, runs a pre-mortem, hunts what's missing, then pressure-tests its own findings for confidence and real-world severity. Use before executing an implementation plan, when asked to review a spec or proposal, or as the quality gate after writing-plans.
EnglishDisciplined causal analysis for explaining observed outcomes — competing hypotheses, evidence ranked by strength, active disconfirmation, and a discriminating next probe. Use when investigating why something happened (intermittent failures, regressions, production incidents, surprising benchmark results) BEFORE proposing fixes, especially when a "obvious culprit" is tempting.
English
AGENT SKILLS ATLASIncludes Designing Consistently, Extracting Design Markdown, Reviewing Plans, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Designing Consistently
Keeps UI work consistent with an app's DESIGN.md design system and decision log. Use when building or modifying UI in a repo with a DESIGN.md (or one that keeps drifting without it), when new screens must match existing ones, when buttons or patterns come out different every session, or when design decisions get lost between sessions.
Extracting Design Markdown
Reverse-engineers a DESIGN.md (Google Labs format) from an already-built project and measures its design drift. Use whenever an existing codebase should adopt DESIGN.md, when UI values have multiplied (several grays, mixed radii, inconsistent buttons), when the owner says the UI looks inconsistent or "quedó desprolijo", or to re-audit drift after a migration batch — even if nobody says the word DESIGN.md.
Reviewing Plans
Adversarial review of plans, specs, and proposals before execution — verifies references, extracts and rates assumptions, runs a pre-mortem, hunts what's missing, then pressure-tests its own findings for confidence and real-world severity. Use before executing an implementation plan, when asked to review a spec or proposal, or as the quality gate after writing-plans.
Tracing Root Causes
Disciplined causal analysis for explaining observed outcomes — competing hypotheses, evidence ranked by strength, active disconfirmation, and a discriminating next probe. Use when investigating why something happened (intermittent failures, regressions, production incidents, surprising benchmark results) BEFORE proposing fixes, especially when a "obvious culprit" is tempting.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Designing Consistently skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.