Name: figma-create-new-file
Rating: 70.39999999999999 (1 reviews)
Author: figma

figma-create-new-file

Always use this skill when the user wants to create a new Figma Design, FigJam, or Slides file. You MUST invoke this skill BEFORE every `create_new_file` tool call.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

93%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 an exemplary lean, actionable skill: a clear three-step workflow with explicit error branches for plan resolution, a complete tool-call specification with an executable example, and a valuable Slides-specific gotcha. The only minor gap is absence of guidance for handling a failed `create_new_file` call or validating its response.

Suggestions

Add one line on handling a failed or unexpected `create_new_file` response (e.g., report the error to the user and stop rather than proceeding) to close the workflow feedback loop.

Optionally note how to verify the returned `file_key` before using it in subsequent `use_figma` calls.

Dimension	Reasoning	Score
Conciseness	The ~35-line body is lean and assumes Claude's competence: every line instructs ("Use the `planKey` the user provided", "Call the `create_new_file` tool with all three required arguments") with no padding or explanation of concepts Claude already knows. Matches the anchor-5 'every token earns its place' exemplar.	5 / 5
Actionability	Fully executable guidance: concrete tool names (`whoami`, `create_new_file`, `figma.createSlide()`), every argument enumerated with required/optional status, a copy-paste-ready JSON example, and a specific empty-grid gotcha with the fix. Not 4 because no key details are missing for the common cases.	5 / 5
Workflow Clarity	A clear 3-step sequence with explicit checkpoints for plan resolution ("No plans: inform the user", "Multiple plans: show the available plans, ask the user to select one") and an empty-grid handling step for Slides. Not 5 because there is no feedback loop on the `create_new_file` result itself (e.g., what to do if the call fails or the response lacks `file_key`); not 3 because validation checkpoints for the risky resolution step are explicit.	4 / 5
Progressive Disclosure	A short, well-organized single-file skill (under 50 lines) with clear section headers and no external references needed; no references/scripts/assets bundle exists, and the body points only to MCP tools rather than files. Per the rubric's simple-skill guideline, well-organized sections alone warrant a 5.	5 / 5
	Total	19 / 20 Passed

Description

77%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 has explicit what/when structure with concrete, natural trigger phrases and low conflict risk. Its main weakness is thin capability coverage (a single action) and second-person phrasing ("You MUST invoke"), which costs it specificity points under the rubric's voice guideline.

Suggestions

Rewrite the second sentence in third person to avoid the second-person specificity penalty, e.g., "Invoked before every `create_new_file` tool call."

Broaden capability coverage with a few more concrete actions (e.g., resolving the plan key, choosing the editor type) to lift specificity beyond a single action.

Add common trigger synonyms such as "new Figma file" or "start a Figjam/presentation" to widen natural keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Figma Design, FigJam, or Slides file") and one concrete action ("create a new ... file" via the `create_new_file` tool), matching the 1-2-concrete-actions anchor (3), but the second sentence uses second-person voice ("You MUST invoke this skill"), which carries an explicit 1-point specificity penalty per the judging guidelines.	2 / 5
Completeness	Both what ("create a new Figma Design, FigJam, or Slides file") and when ("when the user wants to create a new ... file" and "BEFORE every `create_new_file` tool call") are explicitly answered with concrete trigger phrases, matching the anchor-5 example's structure. Not 4 because the 'when' clause is as explicit and specific as the anchor-5 exemplar.	5 / 5
Trigger Term Quality	"create a new Figma Design, FigJam, or Slides file" is the natural phrase a user would say, and the `create_new_file` tool-call trigger is captured, but common synonyms (e.g., "new Figma file", "start a presentation") and file extensions are missing. Not 5 because synonym/extension coverage is absent; not 3 because the core natural trigger phrase is present and idiomatic.	4 / 5
Distinctiveness Conflict Risk	Clear niche — creating new files in Figma products, tied to a specific tool call — with distinct triggers and minimal overlap risk with other skills. Not 4 because no closely related skill in the Figma domain would plausibly claim this exact trigger.	5 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: figma/mcp-server-guide
Path: skills/figma-create-new-file/SKILL.md
Commit: 38308b7

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.