CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mobilebuildmcp-tool-contract-review

Use when reviewing MobileBuildMCP tool contract changes across implementation, manifests, workflow membership, output schema metadata, and next-step templates.

71

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

MobileBuildMCP Tool Contract Review

Review guardrails for tool contract changes across implementation, manifests, and workflow exposure.

Review scope

  • Review-only by default.
  • Do not edit product code unless the user explicitly requests implementation changes.

Files to inspect

  • src/mcp/tools/**
  • manifests/tools/*.yaml
  • manifests/workflows/*.yaml
  • src/core/manifest/schema.ts
  • src/runtime/tool-catalog.ts
  • src/runtime/types.ts
  • xcodebuildmcp.com/app/docs/_content/tool-authoring.mdx
  • xcodebuildmcp.com/app/docs/_content/architecture-manifest-visibility.mdx

Guardrails

  • Manifest id matches filename.
  • Manifest module points to implementation path without extension.
  • Tool module exports named schema and handler.
  • names.mcp remains globally unique.
  • names.cli stays workflow-local and consistent with CLI docs/fixtures.
  • Tool appears in at least one workflow unless intentionally hidden by availability.
  • outputSchema is present for tools that set ctx.structuredOutput.
  • nextSteps.toolId references existing manifest tool IDs.
  • Avoid parallel legacy paths or duplicate implementation paths.

Validation

  • npm run typecheck
  • npm test -- src/core/manifest/__tests__/schema.test.ts
  • npm test -- src/runtime/__tests__/tool-invoker.test.ts
  • npx skill-check .agents/skills/mobilebuildmcp-tool-contract-review
Repository

getsentry/XcodeBuildMCP

Path

.agents/skills/mobilebuildmcp-tool-contract-review/SKILL.md

Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.