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)

68

Quality

82%

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

Quality

Content

82%Weight 40%Scale 1-5

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

The body is actionable and well-sequenced with a clear parameter contract and a useful edge-case note for Slides. Minor redundancy in the mandatory-prerequisite wording and the absence of an explicit post-creation verification step are the only real gaps.

Suggestions

Dedupe the MANDATORY prerequisite statement (it appears both in the opening line and the frontmatter echo) and state editorType/fileName defaults once.

Add a brief verification step after create_new_file (e.g. confirm file_key is present and non-empty before handing off to use_figma) to lift workflow_clarity.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no 'what is Figma' padding), with a clean parameter table and JSON example. Not 5 because the MANDATORY prerequisite is stated twice (lines 9 and the frontmatter echo) and the default values for editorType/fileName are restated after the examples, which could be trimmed.

4 / 5

Actionability

Provides a concrete decision tree for planKey resolution, an explicit parameter table, a copy-paste JSON payload, and the exact return fields (file_key, file_url) with the next-step handoff. Not below 5 because the guidance is fully executable and covers the common single-plan and multi-plan cases.

5 / 5

Workflow Clarity

Steps are clearly sequenced (resolve planKey -> call create_new_file -> use result) with a branching decision tree and an 'ask the user' checkpoint for multiple plans. Not 5 because there is no explicit validation/verification of the created file before the handoff, even though the operation is non-destructive so the destructive-cap does not apply.

4 / 5

Progressive Disclosure

The body is compact and well-sectioned with a single clearly-signaled one-level-deep reference ('See figma-use-slides -> slide-grid'). Not 5 because most workflow detail is inlined in SKILL.md rather than split out, though for a skill this size that is defensible; the bundle directories are empty so there is nothing further to reference.

4 / 5

Total

17

/

20

Passed

Description

82%Weight 40%Scale 1-5

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

The description is specific, trigger-rich, and clearly answers both what and when with a distinct niche. Its main weakness is repeated second-person voice ('you MUST', 'you need'), which costs specificity under the rubric's voice rule.

Suggestions

Rewrite the description in third person (e.g. 'Creates a new blank Figma file; invoke before every create_new_file call') to avoid the second-person specificity penalty.

Add a couple of natural synonyms (e.g. 'presentation' for Slides, 'whiteboard' for FigJam) to round out trigger-term coverage.

DimensionReasoningScore

Specificity

Quotes 'create a new blank Figma file' and the 'design, FigJam, or Slides file' variants give several concrete actions, landing at anchor 4 base, but the description repeatedly uses second-person voice ('you MUST invoke', 'you need a fresh file'), which reduces the specificity score by 1 per the rubric. Not a 2 because the domain and concrete actions are clearly named rather than minimal/generic.

3 / 5

Completeness

It explicitly answers both what ('create a new blank Figma file') and when ('Trigger whenever the user wants a new blank Figma file... or when you need a fresh file before calling use_figma'), with concrete trigger phrases. The explicit 'Trigger whenever' clause satisfies the 'Use when...' requirement, so no cap applies; not below 5 because both halves are concrete and explicit.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'new blank Figma file', 'new design', 'FigJam', 'Slides file', and 'fresh file before calling use_figma' give good keyword coverage a user would actually say. Not 5 because a few natural synonyms (e.g. 'presentation', 'whiteboard', '.fig') are absent; not 3 because the terms present are clearly natural rather than generic.

4 / 5

Distinctiveness Conflict Risk

The skill targets a clear niche — creating a new blank Figma file — with distinct triggers (editor types, fresh-file-before-use_figma) and minimal overlap with sibling skills like figma-use. Not 4 because the create-new vs use-existing distinction is explicit and unambiguous.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

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.