frontend-product-builder
Skill0 starsChanged 7 months agoApache-2.0View on GitHub
Guardrail for building frontend product surfaces from real workflows, state, and browser-verified interaction instead of generic landing-page scaffolds.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- markoblogo/abvx-agent-skillstheir own version, first seen Jun 14, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- markoblogo/abvx-agent-skills★ 16same name
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 repository57 other files it gives its agents.
- ai-app-integrationSkill
- anti-llm-frontend-designSkill
- aspnet-core-web-developmentSkill
- async-python-patternsSkill
- browser-game-foundationsSkill
- browser-local-qaSkill
- build-mcp-server-sdk-v2Skill
- canva-design-opsSkill
- check-completionSkill
- cli-tool-creatorSkill
- cloudflare-agents-mcpSkill
- cloudflare-durable-objectsSkill
- cloudflare-workers-platformSkill
- deployment-preview-workflowsSkill
- docx-document-artifactsSkill
- durable-workflow-orchestrationSkill
- dynamic-og-imagesSkill
- eval-auditSkill
- evaluate-ragSkill
- figma-design-to-code-rulesSkill
- fine-tuningSkill
- game-asset-pipeline-expansionSkill
- game-ui-playtestSkill
- generate-synthetic-dataSkill
- github-pr-ci-opsSkill
- gmail-inbox-opsSkill
- golden-datasetSkill
- huggingface-llm-trainerSkill
- javascript-monorepo-buildsSkill
- linear-issue-managementSkill
- media-generation-transcriptionSkill
- millrace-rs-contract-paritySkill
- minecraft-mod-qa-automationSkill
- notion-workspace-flowsSkill
- openai-docsSkill
- optimize-agentic-cliSkill
- pdf-artifact-workflowSkill
- phaser-2d-game-developmentSkill
- postgres-query-performanceSkill
- product-ui-polish-reviewSkill
- pydantic-v2-patternsSkill
- python-repo-refactoring-hygieneSkill
- rag-corpus-hygieneSkill
- react-next-performance-reviewSkill
- rust-best-practicesSkill
- shadcn-ui-compositionSkill
- skill-evaluation-harnessSkill
- tauri-desktopSkill
- tauri-mcp-cliSkill
- tauri-ptySkill
- tile-pixel-art-transitionsSkill
- train-sentence-transformersSkill
- typer-cli-patternsSkill
- using-dbt-for-analytics-engineeringSkill
- validate-evaluatorSkill
- visual-asset-pipelineSkill
- watchdog-file-watcher-patternsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
18 rules. About 0 are common, 17 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈17
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 40
If the prompt is a one-shot build or design request with no follow-up available, infer reasonable defaults and keep moving to a complete …
- Distinctive: line 43
Keep labels, numbers, and controls in code.
- Distinctive: line 44
Verify the real surface in a browser on desktop and mobile before handoff.
- Distinctive: line 49
Ask a clarifying question only when the request is genuinely ambiguous or unsafe.
- Distinctive: line 53
Do not turn a dashboard, tool, or app request into a marketing shell.
- Distinctive: line 54
Keep text, labels, metrics, and controls in code.
- Very specific: line 55
Use browser-local-qa for the smallest reliable verification surface.
- Distinctive: line 65
Start from the product category and actual job to be done.
- Distinctive: line 68
If context is missing, surface the assumption and continue rather than asking a narrowing question unless the request is genuinely …
- Distinctive: line 78
Write down the core objects, states, and actions the user expects.
- Distinctive: line 79
Start from those objects, not from a generic hero, feature grid, or card stack.
- Distinctive: line 80
If the surface is operational, map prompt nouns to named regions first, then use the domain's native UI forms: tables, lists, filters, …
- Distinctive: line 81
Use real sample data and states instead of fake metrics and social proof.
- Distinctive: line 83
Check the screen for vague labels, weak alignment, overflow, missing controls, or "looks polished but does nothing" behavior.
- Distinctive: line 98
Check that the first screen shows the real task, not a generic promo page.
- Distinctive: line 99
Check that the controls, states, and copy are specific to the product.
- Distinctive: line 100
Check that any visual flourish helps the task instead of hiding missing substance.
- Distinctive: line 104
If the result still feels generic, re-check whether it accidentally became a landing page or reused default component-library tropes.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Frontend Product Builder
Purpose
Help agents build frontend product surfaces from the real workflow, state model, and browser-verified interaction instead of generic landing-page scaffolds. This is a guardrail, not a frontend course or a browser QA manual.
Use When
- the task is a new frontend app, tool, dashboard, game, site, or redesign
- the first screen should be the real product, not a marketing wrapper
- the surface needs real state, controls, or responsive browser checks
Do Not Use When
- the request is only a small style tweak inside a fixed design system
- the work is backend-only, copy-only, or already owned by a more specific skill
- you only need generic frontend advice or a browser-selection guide
Quick Start
- Classify the surface first: app, tool, dashboard, game, site, or other product UI.
- Name the real job, primary objects, states, and actions before choosing layout or visuals. If the prompt is a one-shot build or design request with no follow-up available, infer reasonable defaults and keep moving to a complete first-pass answer.
- Decide whether concepting or imagegen is actually needed. Use it only when the surface needs concrete visual direction or non-textual product art.
- Build the working first screen and core workflow before polish.
- Keep labels, numbers, and controls in code; use existing assets or imagegen only for visuals code cannot convincingly supply.
- Verify the real surface in a browser on desktop and mobile before handoff.
Operating Constraints
- Operational surfaces should read as usable product, not a promo page or hero section.
- One-shot build and design prompts should be answered directly in one response; do not default to clarification when a reasonable assumption can resolve the gap.
- Ask a clarifying question only when the request is genuinely ambiguous or unsafe.
- Preserve expressive categories such as games, portfolios, editorial work, and art-directed product surfaces; do not flatten them into generic SaaS cards.
- Make at least one concrete interaction or state change explicit: select, edit, filter, toggle, inspect, or step through a workflow.
- Reject at least one generic trope and name the better alternative, such as replacing a hero/card stack with a table, sidebar, or inspector that shows the actual workflow.
- Do not turn a dashboard, tool, or app request into a marketing shell.
- Keep text, labels, metrics, and controls in code; use assets or imagegen for visuals that code cannot convincingly supply.
- Use
browser-local-qafor the smallest reliable verification surface; this skill only requires that the real page gets checked on desktop and mobile.
Inputs This Skill Expects
- The product category and the user's real goal.
- Any existing UI, screenshot, brand system, or design system.
- The key entities, states, filters, and actions the surface must support.
- Any hard constraints on layout, tone, density, responsiveness, or art direction.
- Missing optional context is acceptable; turn it into stated assumptions instead of blocking on a narrowing question unless the request is genuinely ambiguous or unsafe.
Output Contract
- Start from the product category and actual job to be done.
- For apps, tools, dashboards, and games, build the real workflow first, not a promo wrapper.
- For one-shot operational-surface prompts, answer in one response with the requested plan, named layout regions, at least one concrete interaction or state path, one rejected generic trope, and browser verification steps.
- If context is missing, surface the assumption and continue rather than asking a narrowing question unless the request is genuinely ambiguous or unsafe.
- For operational surfaces, translate at least three nouns from the prompt into named UI regions, controls, or state panels.
- For operational surfaces, show one concrete inspect-or-edit path for a selected object, not just a comparison table or summary strip.
- Choose domain-specific hierarchy, density, controls, and content.
- Make at least one interaction, mode, or state explicit on the screen.
- Explain at least one generic trope you rejected and the better product-specific alternative.
- Preserve intentional expressive design when the category calls for it, but keep the surface usable and legible.
Procedure
- Identify whether the request is a landing page or a product surface, and whether it is a one-shot prompt with no follow-up available.
- Write down the core objects, states, and actions the user expects. If optional context is missing, state the assumption and continue unless the request is genuinely ambiguous or unsafe.
- Start from those objects, not from a generic hero, feature grid, or card stack.
- If the surface is operational, map prompt nouns to named regions first, then use the domain's native UI forms: tables, lists, filters, sidebars, drawers, timelines, or inspectors.
- Use real sample data and states instead of fake metrics and social proof.
- Include at least one inspect-or-edit path for a selected object.
- Check the screen for vague labels, weak alignment, overflow, missing controls, or "looks polished but does nothing" behavior.
- Tune density and whitespace to the product instead of defaulting to the same spacious demo layout every time.
Pitfalls And Gotchas
- Turning every request into a SaaS dashboard.
- Using gradients, blobs, glassmorphism, glow, or orbs as default decoration.
- Inventing fake dashboards, fake charts, or fake testimonials to fill space.
- Making every UI rounded, airy, and shallow until it no longer matches the product.
- Fixing style while leaving the main workflow vague or inert.
- Banning all visual ambition and breaking games, portfolios, editorial work, or art tools.
Progressive Disclosure
Start with the smallest useful reading of the request, then widen only as needed to support the actual workflow. If the surface is operational, favor clarity and task completion; if it is expressive, favor the art direction the category deserves. Keep the skill short enough that it steers decisions instead of becoming a generic design manifesto. When in doubt, preserve the product skeleton and make the design more specific, not more generic.
Verification Pattern
- Check that the first screen shows the real task, not a generic promo page.
- Check that the controls, states, and copy are specific to the product.
- Check that any visual flourish helps the task instead of hiding missing substance.
- For operational surfaces, verify at least one interaction path such as filter, select, toggle, edit, or inspect.
- For expressive surfaces, verify that the chosen style is intentional and category-appropriate, not the default AI-generated look.
- Confirm the browser check covered the real page on desktop and mobile before handoff.
- If the result still feels generic, re-check whether it accidentally became a landing page or reused default component-library tropes.
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.

