figma-code-connect-components

Tier-2 Review: figma-code-connect-components

What we attempted

We attempted to validate the skill figma-code-connect-components against its documented workflow. The skill promises to connect Figma design components to code implementations using Figma's Code Connect feature, with a structured two-step workflow: first calling get_code_connect_suggestions to identify unmapped components, then send_code_connect_mappings to establish the links. Our test harness attempted to install any required dependencies and run a smoke-invocation to confirm the skill could execute its core function.

What failed

Both tests failed cleanly. The install test failed because the skill is not a Python package—it is a workflow guide that describes how to interact with external MCP servers. There is no setup.py, requirements.txt, or install command documented in the SKILL.md. The smoke-invocation test failed because the skill requires an active Figma MCP server (either figma-mcp or figma-desktop-mcp) and published Figma components in a team library. Our test environment had neither the MCP server running nor access to a Figma design file with published components. Without these, the skill could not be invoked in any meaningful way.

What we observed

The SKILL.md is well-structured and provides clear, step-by-step instructions. It correctly identifies prerequisites (Figma MCP server, published components, Organization/Enterprise plan) and handles edge cases like missing node IDs or already-mapped components. The skill also properly delineates boundaries with related skills (figma-use, figma-generate-design, figma-implement-design). However, the skill is entirely dependent on external infrastructure that was not available in our test harness. The failure mode is not a bug in the skill's logic but a fundamental environmental dependency: without Figma MCP and a suitable Figma workspace, the skill cannot be tested or executed.

Rating is theoretical until re-run

Given the composite score of 4.8/5.0, we acknowledge that the skill appears well-designed on paper. The dimensions—trigger clarity, output specificity, scope precision, self-containment, and reusability—are all rated highly based on the SKILL.md content alone. However, this rating is theoretical until the skill can be physically re-run in an environment that includes a configured Figma MCP server, a Figma design file with published components, and access to a codebase for component scanning. The 4.0 on reusability likely reflects the narrow dependency on Figma's Code Connect feature, which is only available on specific plans.

Is the skill still valuable in principle?

Yes. Despite the test failures, the skill addresses a real and painful problem: maintaining design-code consistency across Figma components and their implementations. The workflow is logical and matches how Figma's Code Connect actually works. For teams on Organization or Enterprise plans who already use Figma and have a codebase with component implementations, this skill could save significant manual effort. The fact that it failed in our harness is a reflection of infrastructure limitations, not skill quality. If you have the required Figma setup and MCP server, this skill is likely a strong addition to your workflow. Just be prepared to configure the environment first—the skill itself does not provide any installation automation.

Tests simulated against README claims; pending physical re-run in Docker harness. Ran 2026-05-21.

Overall: broken. 0 tests passed, 0 partial, 2 failed; key blocker: missing Figma MCP server and no installable package.

Inferred dependencies: figma-mcp-server, figma-desktop-mcp, codebase-access.

Test	Status	Notes
install	fail	No install command documented in SKILL.md; skill is a workflow guide, not a Python package.
smoke-invocation	fail	Requires Figma MCP server and published components; no MCP server available in test environment.