ux-state-completeness-auditor
Skill0 starsChanged 19 days agoMITView on GitHub
Audit user flows for loading, empty, success, validation, partial, permission, offline, and error states. Use when async UI or data-driven workflows are added.
In this repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- completion-claims-auditorSkill
- existing-work-preservationSkill
- mcp-reliability-auditorSkill
- multi-agent-integration-reviewerSkill
- project-context-recoverySkill
- requirement-traceability-auditorSkill
- scope-drift-guardSkill
- architecture-complexity-auditorSkill
- dependency-cycle-auditorSkill
- database-schema-reviewerSkill
- data-consistency-auditorSkill
- migration-safety-reviewerSkill
- loop-breakerSkill
- reproduction-builderSkill
- root-cause-debuggerSkill
- dependency-grounding-auditorSkill
- ci-failure-investigatorSkill
- cross-platform-readiness-auditorSkill
- environment-config-auditorSkill
- environment-parity-auditorSkill
- production-readiness-auditorSkill
- documentation-accuracy-auditorSkill
- token-efficient-workflowSkill
- accessibility-auditorSkill
- dead-feature-detectorSkill
- responsive-design-auditorSkill
- release-verification-agentSkill
- agent-tool-trust-auditorSkill
- authentication-security-auditorSkill
- authorization-boundary-auditorSkill
- dependency-vulnerability-auditorSkill
- injection-risk-auditorSkill
- input-validation-auditorSkill
- secret-leakage-detectorSkill
- security-misconfiguration-auditorSkill
- api-contract-auditorSkill
- integration-reality-checkerSkill
- missing-test-detectorSkill
- regression-detectorSkill
- test-quality-auditorSkill
- ui-flow-verifierSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
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 8
Ensure the product remains understandable outside the happy path.
- Distinctive: line 20
Read applicable repository instructions before edits.
- Distinctive: line 32
Create a state matrix for each async/conditional step: initial, loading, success, empty, validation error, server/network error, …
- Distinctive: line 34
Check loading prevents duplicate/destructive actions without freezing unrelated navigation.
- Distinctive: line 35
Check empty state explains why there is no data and provides the next useful action when appropriate.
- Distinctive: line 36
Check errors preserve user input/state where safe, expose a recovery path, and avoid leaking internals.
- Distinctive: line 38
Verify transitions between states, not only isolated screenshots.
- Distinctive: line 46
Do not expose raw stack traces, tokens, or sensitive backend details in user-facing errors.
- Distinctive: line 50
Every relevant matrix state has an intentional rendering/behavior.
- Distinctive: line 63
If product copy or desired recovery behavior is unspecified, identify the design decision instead of inventing business messaging.
≈ “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
Purpose
Ensure the product remains understandable outside the happy path.
When to activate
A UI fetches/submits data, depends on permissions, or has zero/error conditions.
When not to activate
Static content has no asynchronous/conditional state.
Preconditions
- Read applicable repository instructions before edits.
- Preserve unrelated working-tree changes and establish a baseline when the workflow can modify code.
- Identify which tools and environments are actually available; do not claim unavailable checks ran.
Required inputs
- Flow and data sources
- Known API/error semantics
- Product copy/design conventions
Workflow
- Create a state matrix for each async/conditional step: initial, loading, success, empty, validation error, server/network error, permission/auth, retry/recovery, and partial/stale where relevant.
- Trace which application state produces each UI state and find impossible/unhandled branches.
- Check loading prevents duplicate/destructive actions without freezing unrelated navigation.
- Check empty state explains why there is no data and provides the next useful action when appropriate.
- Check errors preserve user input/state where safe, expose a recovery path, and avoid leaking internals.
- Exercise representative states with controlled fixtures or network stubs that model real contracts.
- Verify transitions between states, not only isolated screenshots.
Relevant tools
Component/integration tests, browser network controls, product design system.
Safety restrictions
Do not expose raw stack traces, tokens, or sensitive backend details in user-facing errors.
Validation
- Every relevant matrix state has an intentional rendering/behavior.
- Error and retry transitions preserve safe user state.
- Critical controls do not double-submit during pending operations.
Expected output
- State matrix
- Missing/ambiguous states
- Transition tests
- Copy/recovery observations
Failure handling
If product copy or desired recovery behavior is unspecified, identify the design decision instead of inventing business messaging.
Completion criteria
The skill is complete only when every applicable validation item above has observed evidence or is explicitly marked not executed with the concrete blocker. Do not replace missing evidence with confidence language.
Research mapping
This skill was selected from research problems: P038. See research/vibe-coding-problems.md and research/problem-evidence.csv in the Vibe Coding Skills repository.
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.

