Design with Intent skill
18 skills and 6 agents for UX strategy: from research and flows to accessibility, ethics and engineering handoff
- 246 ★ on the repository
- Last commit
- CC0-1.0
Minimal access
Why this level
- The skills and agents are Markdown instructions and run nothing themselves
- Some skills create diagram and deck files in your project
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/design-with-intentDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skills and agents are Markdown instructions and run nothing themselves
- Some skills create diagram and deck files in your project
This is third-party code. Review the repository files before installing.
What it does
Design with Intent is a system of skills for experience design that asks why a product exists before drawing how it looks. The `intent` skill is the entry point: it gathers project context, holds the UX principles and a catalog of over 72 named anti-patterns, and routes you to the right specialist. The other skills cover strategy and research (`strategize`, `investigate`, `blueprint`), design (`journey`, `organize`, `wireframe`, `articulate`), evaluation (`evaluate`, `fortify`, `include`), adaptation (`transpose`, `localize`), measurement (`measure`) and the cross-cutting `philosopher` and `storytelling`. Six agents group the skills by role: Noor greets and presents the result, Ember frames the problem, Wren designs the experience, Vigil checks quality and accessibility, Rune prepares the engineering handoff, and Sage helps think broadly. `specify` checks that a design is ready, runs an ethical review and assembles the project's artifacts around one entry page. `present` builds decks in Google Slides via .pptx, PowerPoint, Figma Slides or reveal.js and refuses to invent evidence.
Who it is for. Product designers and managers who take a project from hypothesis to engineering handoff with Claude Code, Cursor or Codex.
Good fit when
- A project is just starting and you need to frame the problem and check five foundational questions before the first mockups
- An interface is ready and has to be run through Nielsen's heuristics with severity-ranked findings
- A screen has to be checked for states and errors: nine states are described for each
- Before engineering handoff an ethical review against the catalog of manipulative patterns is needed
- Interviews and research are ready to be synthesized into findings with counts and quotes
Not a fit when
- You need pixel-level polish of a finished interface: the catalog has Impeccable for visual refinement
- You need design tokens and components in DTCG format: UX/UI Agent Skills covers that, while Intent works at the level of strategy and flows
- You need interface code: the skills produce research, diagrams, wireframes and specs rather than finished markup
Example request
/intent:evaluate Run a heuristic evaluation of the checkout screen and rank findings by severityLimitations
The materials are in English. Some skills return a visual result as rendered HTML diagrams, Pencil files or specs for your tool. The `present` skill first interviews you about audience, feeling, action and sources and does not start building without an approved story outline, so it will not give a quick throwaway deck. The CC0 license removes usage restrictions, and the repository's `intent` skill is version 1.7.4.
How to disable. In Claude Code remove the plugin through `/plugin`. If installed through `npx skills`, delete the skill folders and agent files from the agent's directory. Project artifacts the skills created live in your repository and are removed by hand.
FAQ
How do I call the skills in Claude Code?
After installing the plugin the skills are slash commands such as `/intent:strategize`, `/intent:journey`, `/intent:evaluate`, and the six agents are available as subagents via `@ember`, `@wren` and so on.
In what order should I chain the agents on a large project?
Ember frames the problem, Wren designs the experience, Vigil checks quality and accessibility, Rune packages the project for the build. Sage can be called at any step when the problem needs broader thinking.
What is in the anti-pattern catalog?
Over 72 named patterns in nine categories: deceptive patterns, default manipulation, fabricated urgency, addictive design, attention exploitation, AI-specific dark patterns and more. Each has a severity rating and regulatory context.
How does the philosopher skill work?
It is a mode of thinking with three strict phases: immersion in the problem, associative expansion and synthesis, which starts only when you invite it. Intensity levels and check-ins are set in the skill itself.
Which skill do I start with if I am not sure what I need?
The README gives a decision tree. "I do not know what problem we are solving" leads to `/strategize`, "I need to design the experience" to the set of `/journey`, `/organize`, `/wireframe` and `/articulate`, "does it work for everyone" to `/evaluate`, `/fortify` and `/include`, and "ready to build" to `/specify`.
Discussion
No questions or reviews yet.
Related
SkillsA skill that cross-examines a plan before work starts: numbered questions in rounds with a recommended answer and no changes until you confirm
Nine skills guide a product designer through seven layers, from observed behaviour to interface decisions.
A plugin of 17 skills for product teams: customer research, prioritisation, experiments and design from idea to prototype
Six focused skills for building self-contained HTML artifacts: wireframes, prototypes, mockups, plans and diagrams
cafe3310's personal skill collection: spec-driven project work, reviews, reports, browser, 3D and video in one repository
A set of business, marketing, UX and code skills based on well-known books, plus step-by-step metaskill journeys
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Design with Intent (this card) | no | 246 | |
| UX/UI Agent Skills | no | 3,109 | turns Claude into a design architect with DTCG tokens and checks, while Intent focuses on strategy, research and ethics |
| Impeccable | no | 104,096 | a frontend polish skill with commands and rules for spotting interface flaws, while Intent works before markup |
README in short
The README collects the six agents with a table of their skills, the skills grouped by task, three install routes and a decision tree for picking a skill by situation. A separate section covers the anti-pattern catalog. The license is CC0.
README badge
Original SKILL.md
--- name: intent description: > The entry point for Intent, a UX and design strategy system. Sets project context, routes to specialized skills, and loads foundational UX knowledge. Activate when starting any UX or product design work, setting project context, routing to other skills, evaluating an existing product's UX, or when the user asks about design intent, user experience strategy, ethical design, dark patterns, or design systems thinking. version: 1.7.4 user-invocable: true --- # Intent ## Invocation banner When `/intent` is invoked, the very first content in your response must be the invocation banner. Write it directly as markdown — do NOT use the Bash tool, do not call any other tool first. Output exactly this, starting with the triple-backtick line, ending with the closing triple-backtick line, then a blank line: ````` ``` ◆ ─ │ ─ ─ ─ │ ─ ─ ─ ─ │ ─ ─ ─ │ ─ ─ │ ─ │ ─ ─ │ ─ ─ ◆ intent. Make the reason behind every decision visible. What are you designing, and for whom? ◆ ─ │ ─ ─ ─ │ ─ ─ ─ ─ │ ─ ─ ─ │ ─ ─ │ ─ │ ─ ─ │ ─ ─ ◆ ``` ````` The triple-backtick code fence is essential — it preserves frame alignment in monospace. Do not modify the content, do not paraphrase, do not skip the banner. After the banner renders, continue with the rest of this skill's normal response. ## Overview Intent is a UX and design strategy system. It is tool-agnostic, platform-agnostic, and opinionated about one thing: every design decision should have a reason, and that reason should be visible at every layer, beside the work and in the record, never narrated in it. Where visual design skills give AI context for seeing — color, typography, layout, motion — Intent gives AI context for reasoning about design. For asking why before how. For framing problems before solving them. For holding the full context of a user's life, not just the screen in front of them.