end-user-xp-improver
Skill1 starsChanged 5 months agoMITView on GitHub
Use when planning, implementing, or reviewing a user-facing UI, CLI, API, onboarding, error, or documentation change that needs explicit audience, workflow, low-friction defaults, accessibility, and recovery-path decisions.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-skills-archive-orchestratorSkill
- call-r-lib-in-pythonSkill
- code-commenterSkill
- code-reviewerSkill
- fp-developerSkill
- lesson-documenterSkill
- plan-designerSkill
- preferred-workflowSkill
- release-preparerSkill
- scientific-prose-editorSkill
- simple-code-writerSkill
- spec-driven-developerSkill
- wayback-link-fallbackSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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 12
Read product documentation, existing interfaces, examples, tests, and support signals to identify the target users and their job to be done.
- Distinctive: line 19
Verify the revised path with representative success, invalid input, empty state, permission failure, retry/recovery, and accessibility …
- Distinctive: line 25
Use familiar project conventions and stable, predictable behavior.
- Distinctive: line 28
Keep advanced configuration optional and progressively disclosed.
- Distinctive: line 29
Use clear labels, keyboard/focus behavior, contrast, and assistive semantics for UI work.
- Distinctive: line 30
Do not require users to understand implementation details.
- Distinctive: line 32
Document target users or assumptions in an existing appropriate location only when the task authorizes documentation changes or the …
- Very specific: line 38
Stop when audience or product intent has multiple high-impact interpretations, a proposed default changes security/privacy/data behavior, …
≈ “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
End-User Experience Improver
Optimize the common user journey without inventing unsupported product requirements.
Workflow
- Read product documentation, existing interfaces, examples, tests, and support signals to identify the target users and their job to be done.
- Map the current path from entry to success, including setup, decisions, waiting, errors, recovery, and repeated use.
- Identify concrete friction supported by evidence or label it as an assumption.
- Choose defaults that serve the common case while keeping advanced controls discoverable.
- Preserve established workflows and compatibility unless change is intentional.
- Verify the revised path with representative success, invalid input, empty state, permission failure, retry/recovery, and accessibility scenarios where applicable.
Design rules
- Minimize setup and required decisions before first value.
- Use familiar project conventions and stable, predictable behavior.
- Make errors specific, actionable, and safe; preserve user input when recovery permits.
- Show progress, success, empty, loading, disabled, and failure states when relevant.
- Keep advanced configuration optional and progressively disclosed.
- Use clear labels, keyboard/focus behavior, contrast, and assistive semantics for UI work.
- Do not require users to understand implementation details.
Document target users or assumptions in an existing appropriate location only when the task authorizes documentation changes or the implementation already requires that doc to change. Do not create a new documentation system.
Stop conditions
Stop when audience or product intent has multiple high-impact interpretations, a proposed default changes security/privacy/data behavior, accessibility cannot be evaluated with available context, or reducing friction would break an established contract.
Expected output
Report the target user and task, friction addressed, defaults and recovery paths chosen, scenarios verified, assumptions, and deliberately deferred experience improvements.
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.

