CtrlK
BlogDocsLog inGet started
Tessl Logo

figma-use-figjam

This skill helps agents use Figma's use_figma MCP tool in the FigJam context. Can be used alongside figma-use which has foundational context for using the use_figma tool.

58

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./skills-figquery/figma-use-figjam/SKILL.md

The canonical home for this skill is figma-use-figjam in figma/mcp-server-guide

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 FigJam companion skill: it leads with critical FigJam-vs-Design gotchas (no createPage, get_metadata unsupported), batches tool-schema and reference loading, and delegates per-node-type detail to 13 real, well-described reference files. The only notable gap is that no single end-to-end board-creation sequence or minimal inline code example anchors the workflow.

DimensionReasoningScore

Conciseness

The body is lean and dense with non-obvious, tool-specific facts (exact error strings, get_metadata incompatibility, sublayer font defaults, upload_assets semantics, batch-read patterns). Nothing explains concepts Claude already knows, so it matches 'Lean and efficient; every token earns its place'; the one-line rationale for ToolSearch batching is minor and useful, not a 4-level padding.

5 / 5

Actionability

Guidance is largely executable: a copy-paste ToolSearch query string, exact error messages to avoid triggering, the canonical font-load → await → mutate → return recipe, and concrete upload_assets instructions. It falls short of 5 because the core creation workflows (stickies, sections, tables) are delegated to references with no inline minimal example, leaving minor gaps for the most common first action.

4 / 5

Workflow Clarity

The inspect-then-mutate sequence is explicit ('Use get_figjam upfront before writing any use_figma code') and includes a genuine error-recovery loop (call get_figjam if you forgot to return an ID, rather than re-running an inspection script), plus exact error messages guiding fixes. It is not a 5 because the full board-creation workflow (plan content → create nodes → position) is never sequenced in one place, only implied across sections.

4 / 5

Progressive Disclosure

The body is a clear overview with a well-annotated reference list — all 13 referenced files exist in references/ — each with a one-line description of when to read it, and cross-links to the companion figma-use skill are one level deep and clearly signaled. This matches the 'clear overview with well-signaled one-level-deep references' anchor.

5 / 5

Total

18

/

20

Passed

Description

48%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 clearly identifies its niche (FigJam context for the use_figma MCP tool) and its relationship to the companion skill, but it names no concrete capabilities and provides no 'use when' trigger guidance. Users searching for whiteboard, sticky, or board keywords would not find it.

Suggestions

Add 2-4 concrete FigJam actions to the description (e.g., create sections, sticky notes, connectors, and tables on FigJam boards) to raise specificity.

Append a 'Use when...' clause with natural trigger terms such as whiteboard, FigJam board, sticky notes, retro, or brainstorm to fix completeness and trigger-term gaps.

Include the FigJam URL pattern (figma.com/board/...) as a trigger cue so agents load this skill rather than the design-file companion when handling board URLs.

DimensionReasoningScore

Specificity

The description names the domain ("Figma's use_figma MCP tool in the FigJam context") but lists zero concrete actions — no sticky notes, sections, connectors, boards, or text editing. It matches the anchor 'Names the domain but actions are minimal or generic'; a 3 would require 1-2 named actions, which are absent.

2 / 5

Completeness

The 'what' is present (helps agents use the use_figma MCP tool in the FigJam context) but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the what is clearly stated, not vague.

3 / 5

Trigger Term Quality

"FigJam" and "use_figma" are relevant keywords, but common natural phrases users would say — whiteboard, board, sticky notes, retro, brainstorm — are all missing. This fits 'Some relevant keywords but missing common variations or synonyms'; not a 4 since several obvious natural terms are absent, not just a few.

3 / 5

Distinctiveness Conflict Risk

FigJam (vs. Figma design files) is a clear niche, and the description explicitly distinguishes this skill from its sibling ("Can be used alongside figma-use"). Minor overlap risk remains with the figma-use companion skill itself, so not a 5.

4 / 5

Total

12

/

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: 4 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.