agentleFS
JustineDevsJustineDevs/meta-architect/skills/vibe/SKILL.md

vibe

Skill5 starsChanged 7 months agoMITView on GitHub

Use when the user wants a DX and UX review of the planned workflow before implementation proceeds.

19 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 4

    Distinctive

    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
  1. Distinctive:

    Use this skill inside Codex to review whether the system will feel coherent for both operators and end users.

    line 8
  2. Distinctive:

    Prefer fewer surfaces, fewer steps, and clearer operator outcomes.

    line 25
  3. Distinctive:

    Check terminology, feedback, loading states, keyboard access, responsive behavior, and documentation continuity.

    line 32
  4. Distinctive:

    Every friction point explains who is affected and where it occurs.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Vibe

Use this skill inside Codex to review whether the system will feel coherent for both operators and end users.

Output

Produce:

  • decision, status, evidence, blockers, next_allowed_triggers
  • developer workflow risks
  • user workflow risks
  • operator friction and user friction
  • complexity hotspots
  • onboarding or operability friction
  • simplifications that improve clarity
  • exact next trigger, usually $build

Rules

  • Focus on concrete friction, not aesthetics-only feedback.
  • Prefer fewer surfaces, fewer steps, and clearer operator outcomes.
  • Preserve the architecture and security constraints established earlier in the flow.

Procedure

  1. Walk the complete user journey from discovery through setup, first success, failure, and recovery.
  2. Identify ambiguity, waiting, duplicated input, hidden state, and unsafe defaults.
  3. Check terminology, feedback, loading states, keyboard access, responsive behavior, and documentation continuity.
  4. Recommend the fewest changes that materially improve completion and confidence.
  5. Hand a prioritized, testable implementation slice to $build.

Default evidence dossier

Use docs/reference/accessibility-and-usability.md for user-facing web, documentation, plugin, and CLI-adjacent surfaces. Map material barriers to WCAG 2.2 criteria and name the automated, keyboard, assistive-technology, and human checks that verify the result. WCAG is an accessibility baseline, not a complete usability verdict.

Quality bar

  • Every friction point explains who is affected and where it occurs.
  • Visual polish never hides missing behavior, validation, or recovery.
  • Recommendations preserve accessibility and the safety boundaries from $vet.

Example

For a plugin setup flow, verify that users can understand the MCP URL, scan state, skill import status, policy requirements, and next action without relying on stale or ambiguous status text.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.