parity-auditor
Skill0 starsChanged 5 months agoMITView on GitHub
Cross-platform parity auditor. Use when the user asks about feature parity between web and mobile, wants to compare platforms, find what's missing on mobile or web, audit platform gaps, or check web vs RN differences. Triggers on "parity", "web vs mobile", "web vs RN", "feature parity", "what's missing on mobile", "what's missing on web", "compare platforms", "platform gap", "audit parity".
In this repository18 other files it gives its agents.
- app-icon-gridSkill
- archive-manualSkill
- commitSkill
- component-consistencySkill
- component-locatorSkill
- debug-triageSkill
- gemini-iconSkill
- prd-writingSkill
- refactor-and-safety-passSkill
- release-helperSkill
- smellSkill
- streamdeck-aerospace-rewireSkill
- streamdeck-workspace-buttonSkill
- svg-icon-renderSkill
- test-conventionsSkill
- verification-gateSkill
- work-breakdownSkill
- yt-audioSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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 66
Use component-locator and component-consistency skills when checking component parity.
- Distinctive: line 70
Don't flag intentional platform differences (e.g., swipe-to-dismiss on mobile, hover states on web).
≈ “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
Parity Auditor
You are auditing feature parity between web and mobile (React Native) platforms. Produce a structured comparison with actionable gap analysis.
Discovery Process
- Identify platform roots — scan for app directories (e.g.,
apps/web,apps/mobile,apps/rn). If not a monorepo, ask the user for both project paths. - Inventory screens/flows — list routes/screens from each platform. Sources: route config files, navigation config, page directories, screen directories.
- Inventory shared code — check for shared packages (
packages/,shared/,common/). Note what's shared vs duplicated vs platform-only. - Map components — use component-locator to find UI components on each platform. Identify which exist on both, which are platform-only.
Parity Matrix
Produce a comparison table for each screen/flow:
## Parity Audit
**Web root**: `<path>`
**Mobile root**: `<path>`
**Shared**: `<path or "none">`
### Screen/Flow Parity
| Screen / Flow | Web | Mobile | Gap Notes |
|---|---|---|---|
| Login | done | done | — |
| Profile | done | partial | Missing edit profile |
| Feed | done | missing | Not started |
### State Coverage
| Screen | Loading | Empty | Error | Offline |
|---|---|---|---|---|
| Login | web+mobile | n/a | web only | neither |
| Profile | web+mobile | web only | web only | neither |
### Component Parity
| Component | Web | Mobile | Notes |
|---|---|---|---|
| VerifiedBadge | done | done | Shared logic, platform UI |
| UserCard | done | missing | — |
### Navigation Parity
| Flow | Web | Mobile | Notes |
|---|---|---|---|
| Deep linking | done | partial | Missing /cars/:username |
| Tab structure | done | done | — |
| Back behavior | n/a | done | — |
### Risk Flags
- **Performance**: <any concerns — large lists, heavy images, missing virtualization on mobile>
- **Accessibility**: <any a11y gaps between platforms — missing labels, roles, contrast>
- **Platform-specific**: <features that only make sense on one platform — not a gap>Rules
- Use component-locator and component-consistency skills when checking component parity.
- "partial" means the screen/feature exists but is missing states, sub-features, or has divergent behavior.
- "missing" means it doesn't exist at all on that platform.
- "done" means functionally equivalent (not pixel-identical — platforms should feel native).
- Don't flag intentional platform differences (e.g., swipe-to-dismiss on mobile, hover states on web).
- Flag when shared code exists but one platform isn't using it.
- Reference work-breakdown skill to turn gaps into actionable tickets.
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.

