ux-flow-auditor
Skill0 starsChanged 3 months agoMITView on GitHub
Traces user task flows with Playwright: click depth, step success, friction: and writes reports to .heyeddi/docs/ux-flows/. Use when measuring ease of use, clicks to complete a task, or onboarding friction. Not for static visual critique (use heyeddi-design critique) or layout screenshots (use visual-auditor).
In this repository51 other files it gives its agents.
- .cursor/rules/skill-authoring.mdcCursor rule
- backend-type-bridgerSkill
- composable-patternsSkill
- dart-type-bridgerSkill
- design-handoff-flutterSkill
- design-system-generalizerSkill
- engineering-excellenceSkill
- flutter-engineeringSkill
- flutter-patternsSkill
- heyeddi-designSkill
- heyeddi-handoffSkill
- heyeddi-intakeSkill
- heyeddi-orchestratorSkill
- heyeddi-productSkill
- heyeddi-pr-respondSkill
- heyeddi-pr-reviewSkill
- no-duplicate-uiSkill
- pre-merge-gateSkill
- primevue-openprops-architectSkill
- project-engineeringSkill
- ux-flow-auditorSkill
- verify-buildSkill
- visual-auditorSkill
- backend-type-bridgerSkill
- composable-patternsSkill
- dart-type-bridgerSkill
- design-handoff-flutterSkill
- design-system-generalizerSkill
- engineering-excellenceSkill
- flutter-engineeringSkill
- flutter-patternsSkill
- heyeddi-ci-configSkill
- heyeddi-ci-failsSkill
- heyeddi-ci-guideSkill
- heyeddi-ci-runnersSkill
- heyeddi-designSkill
- heyeddi-handoffSkill
- heyeddi-intakeSkill
- heyeddi-orchestratorSkill
- heyeddi-productSkill
- heyeddi-pr-respondSkill
- heyeddi-pr-reviewSkill
- heyeddi-setupSkill
- heyeddiSkill
- no-duplicate-uiSkill
- pre-merge-gateSkill
- primevue-openprops-architectSkill
- project-engineeringSkill
- taste-penpotSkill
- verify-buildSkill
- visual-auditorSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Read reference/cross-pillar-handoff.md.
- Very specific: line 50
Ensure .heyeddi/product.md defines user tasks (optional context).
- Very specific: line 52
Add or edit .heyeddi/docs/ux-flows/<task-id>.flow.json with steps (expect, fill, click).
- Very specific: line 53
Start dev server; set DEV_SERVER_URL if not http://localhost:5173.
- Very specific: line 85
After @heyeddi-handoff / @heyeddi-design: verify tasks are completable
≈ “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
UX Flow Auditor
Task-oriented UX: how many clicks to achieve a goal, where users get stuck.
All artifacts go under .heyeddi/docs/ and .heyeddi/audits/: never repo root.
Cross-pillar sync (mandatory)
Read reference/cross-pillar-handoff.md. Bookend every flow trace:
@heyeddi load_workflow_context --route /path
trace_flow …
update ux-flows report + friction notes
@heyeddi append_pillar_opinion --pillar ux …
→ @heyeddi-product updates AC if needed; @heyeddi-design notes layout frictionWhen to use
- "How many clicks to update settings?"
- Post-ship ease-of-use check
- Compare desktop vs mobile flow (separate flow JSON or viewport)
- Product acceptance: task completes within click budget
Subagents (default)
See reference/subagents.md. Run trace_flow.py via Task shell (needs dev server + Playwright).
Pipeline
init_ux_flows → ux-flows.md index + example .flow.json
define steps in ux-flows/<task>.flow.json
trace_flow --task-id → ux-flows/<task>.md + audit screenshot
agent adds friction notes to reportInstructions
- Ensure
.heyeddi/product.mddefines user tasks (optional context). python scripts/init_ux_flows.py --project-root <root>once per project.- Add or edit
.heyeddi/docs/ux-flows/<task-id>.flow.jsonwith steps (expect,fill,click). - Start dev server; set
DEV_SERVER_URLif nothttp://localhost:5173. python scripts/trace_flow.py --task-id <id> --project-root <root> --check- Append Friction notes to the generated markdown report.
Flow JSON schema
{
"task_id": "update-profile",
"goal": "User saves profile",
"start_route": "/settings",
"max_clicks": 4,
"viewport_width": 1440,
"steps": [
{ "action": "expect", "selector": ".settings .p-inputtext", "label": "Form visible" },
{ "action": "fill", "selector": ".settings input >> nth=0", "value": "Alex", "label": "Name" },
{ "action": "click", "selector": "button:has-text('Save')", "label": "Save" }
]
}.heyeddi/ outputs
| Path | Purpose |
.heyeddi/docs/ux-flows.md | Index of tasks, budgets, last run |
.heyeddi/docs/ux-flows/<task>.flow.json | Machine-readable steps |
.heyeddi/docs/ux-flows/<task>.md | Human report + friction notes |
.heyeddi/audits/ux-flow/ | Step screenshots |
Chain
- After
@heyeddi-handoff/@heyeddi-design: verify tasks are completable @visual-auditor: layout proof; this skill: interaction proof@engineering-excellence: separate concern (code structure)
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.

