agentleFS
BurakDBurakD/ai-engineering-harness/skills/cross-surface-consistency/SKILL.md

cross-surface-consistency

Skill1 starsChanged 2 months agoApache-2.0View on GitHub

Checks that equivalent capabilities behave consistently across multiple interfaces or channels such as web, mobile, desktop, CLI, APIs, admin tools, or partner integrations. Use when one change can create accidental behavioral drift between surfaces.

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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
  1. Distinctive:

    Check authentication, authorization, feature availability, data representation, analytics or event behavior, and compatibility expectations …

    line 16
  2. Distinctive:

    Prefer shared domain or service logic for shared rules when the project's architecture supports it, while allowing interface-specific …

    line 20
  3. Distinctive:

    Add targeted parity or contract tests, shared fixtures, schema checks, or deterministic comparisons when they can protect important …

    line 22
  4. Distinctive:

    Document intentional asymmetry when future maintainers could otherwise mistake it for a defect.

    line 24
  5. Distinctive:

    When a defect is isolated to the quality of one individual interface rather than inconsistency between interfaces, use the interface QA …

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.

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

Cross-surface consistency

  1. Identify every interface, client, channel, integration, or operational surface that exposes, controls, or depends on the affected capability.
  2. Determine the canonical behavior or contract that should be shared across those surfaces and identify where intentional differences are permitted.
  3. Compare relevant inputs, validation, defaults, permissions, state transitions, outputs, terminology, error semantics, availability rules, and side effects across surfaces.
  4. Check authentication, authorization, feature availability, data representation, analytics or event behavior, and compatibility expectations where they form part of the shared capability contract.
  5. Distinguish intentional platform- or audience-specific behavior from accidental drift. Do not force identical presentation where only semantic consistency is required.
  6. Prefer shared domain or service logic for shared rules when the project's architecture supports it, while allowing interface-specific adaptation at appropriate boundaries.
  7. Add targeted parity or contract tests, shared fixtures, schema checks, or deterministic comparisons when they can protect important cross-surface behavior.
  8. Document intentional asymmetry when future maintainers could otherwise mistake it for a defect.
  9. When a defect is isolated to the quality of one individual interface rather than inconsistency between interfaces, use the interface QA procedure instead of expanding this review unnecessarily.

Report the surfaces examined, shared behavior verified, intentional differences, accidental drift found, validation evidence, and deferred consistency risks.

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.