product-design
Skill8 starsChanged 9 days agoMITView on GitHub
Use when shaping a new product, materially redesigning a user flow, choosing a web or app stack, or turning a product concept into an implementation-ready design.
26 other projects use a version of this.
Adopted by
Most recently taken up by
- lklimek/claudiustheir own version, first seen Nov 8, 2026
- thensls/nsls-builder-toolkittheir own version, first seen Nov 8, 2026
- fracazo/design-systemtheir own version, first seen Nov 8, 2026
- lobehub/lobehubtheir own version, first seen Nov 5, 2026
- Cure-Consulting-Group/ProductEngineeringSkillstheir own version, first seen Nov 4, 2026
- yoyothesheep/claude-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use ux-audit and i18n.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
shmehroSkillux-audit
Perform a heuristic UX audit on a UI screen, flow, or component description
Also in 3 projects that use this
lbednerSkilli18n
Use when a code or template change introduces a new translation message key, in either the framework CLI (aegis/i18n/locales/) or a generated project's CLI (the app/i18n/locales/ template tree). Covers adding the real English string, stubbing the same key into every other locale for parity, and the separate translation PR that later replaces placeholders with reviewed native text.
Also in 3 projects that use this
Other versions26 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 26
- lobehub/lobe-chat★ 84ksame name
- lobehub/lobehub★ 84ksame name
- alekspetrov/navigator★ 355same name
- qf-studio/navigator★ 355same name
- duyet/clickhouse-monitoring★ 303same name
- github/replica★ 230same name
- mblode/agent-skills★ 189same name
- chuhaiqu/skills★ 22same name
- vercel-labs/arcade★ 21same name
- yoyothesheep/claude-skills★ 16same name
16 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository17 other files it gives its agents.
- app-controlSkill
- artifactSkill
- clean-systemSkill
- contribution-checklistSkill
- debuggingSkill
- doc-styleSkill
- experiment-workflowSkill
- first-principlesSkill
- latex-authoringSkill
- logoSkill
- multi-agentSkill
- project-docsSkill
- reference-driven-productSkill
- specSkill
- tddSkill
- test-auditSkill
- word-farsi-docxSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 21 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
Use what is known; ask only what would change the architecture.
- Distinctive: line 31
Keep the first build small enough to test the core assumption.
“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Product design
Turn an early product idea into a user experience and an implementation boundary before code is written.
1. Users and flows first
Settle who it is for and what they must get done before any technology: the primary user, the platform, the problem removed, the two or three highest-value flows, and the minimum states (and screens, if visual) that complete them. Start from the job, not a feature list; invent no needs. Wireframes or exact flow maps set the implementation boundaries: an unresolved UX decision is an unresolved requirement, not a detail.
2. Stack from the product
Tie every choice to a product constraint: a server-rendered or hybrid framework for SEO-heavy public content; an SPA for an authenticated dashboard; a native or cross-platform stack for device-heavy mobile; the smallest runtime for a local developer tool. Among fitting stacks, prefer the one with a mature component ecosystem; do not rebuild standard UI primitives. Weigh build speed, maintenance, hosting, accessibility and ecosystem; scale only when scale is a real requirement.
3. Frontend first
Build screens and states with mocked data, run the main flows end to end, derive the data contracts the UI actually needs, then build backend, storage and auth against them and replace the mocks. The frontend exposes missing product decisions before the backend hardens around them. For a coupled product built with AI help, default to one monorepo (apps/, packages/, docs/product/); split only for real deployment, ownership or security boundaries.
Output
Use what is known; ask only what would change the architecture. For a full brief return, in order (for a narrow question, only the relevant part; for CLI, API or background products, commands, requests and failure paths instead of screens):
- Flows and screens: each flow as
entry → state → action → next state → completion/failure, then the minimum screen set and each screen's purpose. - Stack: the choice, each part justified by a product need, and one credible alternative with why it lost.
- Build order: from mocked interface to integrated product, marking where backend, persistence, auth, external APIs, tests and deployment first become necessary.
- Repository layout: the minimum useful structure.
Keep the first build small enough to test the core assumption; no roadmap before the core flows work.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.