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)

66

Quality

80%

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.

A tight, highly actionable skill body: concrete tool contract, executable example, and a decision-tree workflow with a user-checkpoint for ambiguous plan selection. The only weaknesses are minor — a redundant restatement of argument defaults, repeated mandatory framing, and no error-path guidance for failed lookups.

DimensionReasoningScore

Conciseness

The body is efficient — a parameter table, a JSON example, and a short decision tree with no explanations of concepts Claude already knows. Not level 5 because the mandatory preamble repeats the frontmatter's enforcement language, and the paragraph 'Parse the arguments from the skill invocation. If editorType is not provided, default to design...' restates the defaults already given in the bullet list above it.

4 / 5

Actionability

Fully executable guidance: exact tool name, parameter table with required flags, a copy-paste-ready JSON call example, the tool's return fields (file_key, file_url), and the explicit next step ('Use the file_key for subsequent tool calls like use_figma'). Nothing is pseudocode or vague; not lower on any anchor.

5 / 5

Workflow Clarity

A clear three-step sequence with a planKey decision tree that handles the ambiguous multiple-plans case by asking the user — a real checkpoint. Not level 5 because there are no explicit validation or error-recovery steps (e.g. what to do if whoami returns an empty plans array or the tool call fails), and the anchor-5 example includes feedback loops.

4 / 5

Progressive Disclosure

Well-organized single-file skill: sections are clear, and the slides edge-case detail is appropriately deferred via a clearly signaled one-level reference ('See [figma-use-slides → slide-grid](../figma-use-slides/references/slide-grid.md)'). Not level 5 because the body is ~73 lines rather than under 50, and the sole reference points into a sibling skill's bundle rather than this skill's own, which is slightly unusual navigation though functional.

4 / 5

Total

17

/

20

Passed

Description

78%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.

A strong, trigger-rich description with explicit when-guidance, concrete editor types, and usage examples. Its main weaknesses are second-person voice, which the rubric penalizes, and a capability statement wrapped in mandatory rhetoric rather than stated plainly. Distinctiveness against sibling Figma skills is excellent.

Suggestions

Rewrite in third person to avoid the rubric's voice penalty and lead with the capability, e.g. 'Creates a new blank Figma file (design, FigJam, or Slides) in the user's drafts folder via the create_new_file tool. Use when the user wants a new/blank Figma, FigJam whiteboard, or Slides presentation file, or before calling use_figma.'

Add natural synonyms users would say — 'whiteboard' for FigJam and 'presentation/deck' for Slides — to broaden trigger coverage.

Trim the repeated MANDATORY/NEVER enforcement sentences to one clause; the emphasis consumes tokens without adding trigger specificity.

DimensionReasoningScore

Specificity

The description lists several concrete capabilities — creating a new blank Figma file in 'a new design, FigJam, or Slides file' variants, acting as prerequisite before 'use_figma', with usage syntax and two concrete invocation examples. It is not level 5 because the capability statement is thin relative to the mandatory framing, and the rubric's second-person voice penalty ('you MUST invoke', 'when you need a fresh file') reduces it from 5 to 4.

4 / 5

Completeness

Both 'what' (creating a new blank Figma file of the three editor types) and 'when' (explicit 'Trigger whenever the user wants a new blank Figma file... or when you need a fresh file before calling use_figma') are present. Not level 5 because the 'what' is embedded in trigger phrasing and mandatory rhetoric rather than stated as a leading, direct capability sentence as in the anchor-5 example.

4 / 5

Trigger Term Quality

Good natural keyword coverage: 'new blank Figma file', 'new design', 'FigJam', 'Slides file', 'fresh file', plus tool names create_new_file and use_figma. Not level 5 because common synonyms users would say — 'whiteboard', 'presentation', 'deck' — are absent except obliquely in the example 'Q3 Review'.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers — Figma file creation specifically, anchored to the create_new_file and use_figma tool names and the three editor types, which distinguishes it from other Figma skills like figma-use. Minimal conflict risk; not lower because no generic language remains that would overlap sibling skills.

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
openai/plugins
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.