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.

55

Quality

63%

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/figma-use-figjam/SKILL.md
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 overview skill: lean, high-signal, packed with FigJam-specific gotchas and exact error messages Claude cannot infer, with a clean one-level reference architecture. The only real weaknesses are minor — key recipes (text mutation, upload_assets payload) are delegated to the companion skill's references, and batch-modify workflows lack an inline validation checkpoint.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious facts Claude cannot know — exact error strings ("TypeError: figma.createPage no such property", "Cannot write to node with unloaded font"), tool failure modes ("get_metadata does NOT work on FigJam files"), and defaults ("sticky → Inter Medium"). Nearly every token earns its place, fitting anchor 5 rather than anchor 4.

5 / 5

Actionability

Concrete, executable guidance dominates: a copy-paste-ready "ToolSearch query=\"select:use_figma,get_figjam,…\"" snippet, specific instructions ("load from node.text.fontName rather than hardcoding"), and exact tool behaviors for upload_assets. Minor gaps keep it below anchor 5 — the canonical text-mutation recipe and the upload_assets request/response shape are delegated to the figma-use references rather than shown.

4 / 5

Workflow Clarity

A coherent sequence is laid out — inspect with get_figjam upfront to get IDs, batch-load schemas and references, then mutate following load font → await → mutate → return IDs — with explicit error-recovery guidance ("If you forgot to return an ID… call get_figjam"). It stops short of anchor 5 because there is no explicit validation checkpoint around batch/destructive mutations (batch-modify is delegated to a reference).

4 / 5

Progressive Disclosure

The Reference Docs section lists all 13 bundle files (all verified to exist) with one-line scope descriptions, plan-board-content is clearly positioned as the delegating entry point, and cross-links to ../figma-use stay one level deep with no nested reference chains. This matches anchor 5: clear overview with well-signaled one-level-deep references and easy navigation.

5 / 5

Total

18

/

20

Passed

Description

40%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 identifies a clear niche (FigJam usage of the use_figma MCP tool) and distinguishes it from its companion skill, but it never states what the skill concretely enables or when it should be triggered. It reads as a relationship note between two skills rather than a self-describing capability statement.

Suggestions

Add an explicit 'Use when…' trigger clause (e.g., 'Use when working with FigJam files, boards, whiteboards, or figma.com/board URLs, or when the user mentions stickies, sections, or FigJam diagrams') — its absence currently caps completeness.

Enumerate 2-3 concrete capabilities (e.g., 'Create and configure FigJam sections, stickies, connectors, tables, and text nodes; position nodes; batch-modify existing nodes').

Include natural user vocabulary and variations such as 'whiteboard', 'board', 'sticky notes', 'retro/brainstorm boards' to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ("Figma's use_figma MCP tool in the FigJam context") but lists no concrete actions such as creating sections, stickies, connectors, or tables — it only says "helps agents use" the tool. This matches anchor 2 (domain named, actions minimal/generic) rather than anchor 3, which requires 1-2 explicitly named actions.

2 / 5

Completeness

The "what" is vague ("helps agents use… in the FigJam context" — no enumerated capabilities) and there is no "when"/"Use when…" clause anywhere; "Can be used alongside figma-use" is pairing guidance, not a trigger. This matches anchor 2 (vague what, no when) — anchor 3 would require a clear, action-enumerating "what".

2 / 5

Trigger Term Quality

"FigJam" and "Figma" are natural terms users would say, but common variations and synonyms are missing (whiteboard, board, sticky notes, brainstorm/retro, file extensions). This matches anchor 3 (some relevant keywords, missing common variations) rather than anchor 4's broader coverage.

3 / 5

Distinctiveness Conflict Risk

The description carves out a clear FigJam niche and explicitly distinguishes the companion "figma-use" skill ("Can be used alongside figma-use which has foundational context"), but both skills trigger on the same use_figma tool domain, leaving minor overlap risk — anchor 4 rather than 5.

4 / 5

Total

11

/

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.