CtrlK
BlogDocsLog inGet started
Tessl Logo

figma-create-new-file

**MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `create_new_file` tool call. NEVER call `create_new_file` directly without loading this skill first. Trigger whenever the user wants a new blank Figma file — a new design, FigJam, or Slides file — or when you need a fresh file before calling `use_figma`. Usage — /figma-create-new-file [editorType] [fileName] (e.g. /figma-create-new-file figjam My Whiteboard, /figma-create-new-file slides Q3 Review)

72

Quality

88%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong, well-crafted description that clearly defines its scope (creating new Figma files), provides explicit trigger conditions (before create_new_file calls, when user wants new design/FigJam/Slides), and includes concrete usage examples. The mandatory prerequisite framing is unusual but effective for ensuring correct skill selection. Minor concern: the imperative/instructional tone ('you MUST invoke') is unconventional but doesn't use first or second person in a penalizable way since it's directing Claude's behavior.

DimensionReasoningScore

Specificity

Lists specific concrete actions: creating new blank Figma files, specifying editor types (design, FigJam, Slides), and provides concrete usage examples with parameters like 'figjam My Whiteboard' and 'slides Q3 Review'.

3 / 3

Completeness

Clearly answers both 'what' (creates new blank Figma files of various types) and 'when' (before every create_new_file tool call, when user wants a new design/FigJam/Slides file, or when needing a fresh file before use_figma). Explicit trigger guidance is provided.

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'new design', 'FigJam', 'Slides file', 'new blank Figma file', 'fresh file', 'create_new_file', and 'figma-create-new-file'. Good coverage of variations.

3 / 3

Distinctiveness Conflict Risk

Very distinct niche — specifically scoped to creating new Figma files (design, FigJam, Slides). The mention of 'create_new_file' tool call and Figma-specific editor types makes it clearly distinguishable from other skills.

3 / 3

Total

12

/

12

Passed

Implementation

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a solid, actionable skill with a well-structured workflow and clear decision tree for the planKey resolution. Its main weakness is moderate verbosity — some information is repeated (editor types, defaults) and the mandatory preamble duplicates the description. The Slides-specific edge case documentation is a valuable addition that demonstrates attention to real failure modes.

Suggestions

Remove the repeated 'MANDATORY' preamble paragraph since it duplicates the skill description, and consolidate the list of supported editor types to appear only once.

Tighten the 'Skill Arguments' section by removing the prose explanation of defaults and letting the examples speak for themselves.

DimensionReasoningScore

Conciseness

The content is mostly efficient but has some redundancy. The 'MANDATORY' note is repeated from the description, the skill arguments section re-explains defaults that could be more compact, and the 'Important Notes' section restates information already covered (e.g., supported editor types listed twice). However, it doesn't over-explain concepts Claude already knows.

2 / 3

Actionability

The skill provides fully concrete, executable guidance: a clear decision tree for resolving planKey, an exact JSON example for the tool call, specific parameter tables, and explicit handling for edge cases (single vs. multiple plans). The workflow is copy-paste actionable.

3 / 3

Workflow Clarity

The three-step workflow is clearly sequenced with a decision tree in Step 1 that handles branching cases (planKey available vs. not, single plan vs. multiple). The Slides-specific note about empty grids includes a guard/validation step. The handoff to the next skill (figma-use) is explicit.

3 / 3

Progressive Disclosure

The skill references one external file (figma-use-slides/references/slide-grid.md) which is appropriate, but there are no bundle files provided to support it. The content is somewhat monolithic — the editor-specific notes and important notes sections could potentially be split out for a cleaner overview, though the file is not excessively long. The single reference is well-signaled.

2 / 3

Total

10

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
figma/mcp-server-guide
Reviewed

Table of Contents

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.