revylai/revyl-cli · Archived

revyl-mcp-create

Create and maintain Revyl tests through MCP tools using create/update operations and execution feedback loops.

First seen May 15, 2026

Installation

$ npx skills add revylai/revyl-cli --skill revyl-mcp-create

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from revylai/revyl-cli · top by installs.

npx skills add revylai/revyl-cli

Browse all from revylai/revyl-cli

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 510
License MIT
Default branch main
Open issues 1
Status Archived

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,791 B
  • docs SUMMARY.md 134 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 3 installs

SKILL.md

Revyl MCP Create Skill

Use this skill when tests should be authored and managed through MCP tools.

Core MCP Flow

  1. Build YAML from ordered instructions and validations.
  2. Create or update:

- createtest(name="...", platform="ios", yamlcontent="...") - updatetest(testnameorid="...", yaml_content="...", force=true)

  1. Execute and inspect:

- runtest(testname="...") - getteststatus(task_id="...")

Authoring Rules

  1. One action per instruction step.
  2. Keep validations separate from instructions.
  3. Validate user-visible outcomes.
  4. Use variables for sensitive or dynamic values.

Canonical YAML

Use the backend YAML contract returned by get_schema().

- type: instructions
  step_description: "Tap Log in."

- type: validation
  step_description: "The dashboard is visible."

- type: code_execution
  script: "seed-user"
  variable_name: seeded_user_id

- type: module_import
  module: "login-flow"

- type: if
  condition: "Is a cookie banner visible?"
  then:
    - type: instructions
      step_description: "Tap Accept."
  else:
    - type: instructions
      step_description: "Continue."

- type: while
  condition: "Is there a Load More button visible?"
  body:
    - type: instructions
      step_description: "Tap Load More."

For new authored YAML, use script for code execution and module for module imports. Legacy UUID forms may still parse for compatibility, but do not generate them.

Shared Setup Reuse

If shared steps appear in 3+ tests:

  1. list_modules()
  2. insertmoduleblock(modulenameor_id="...")
  3. update test YAML to import module.