CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

figma-use-slides

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

Quality

72%

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 ./examples/plugin-packages/figma/skills/figma-use-slides/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 a strong, dense skill document: it leads with critical Slides-specific pitfalls and exact failure signatures, gives a well-sequenced two-phase build workflow with batch validation feedback loops, and pushes detail into six real, clearly-signaled reference files. The only notable weaknesses are moderately padded prose in the Design Thinking and speaker-notes sections and build helpers living entirely in references rather than inline.

DimensionReasoningScore

Conciseness

Nearly all content is non-obvious, Slides-specific knowledge Claude could not know (the (240,240) appendChild offset bug, opaque SLIDE_GRID/SLIDE_ROW nodes, the exact createPage TypeError text), so most tokens earn their place. The Design Thinking and speaker-notes sections run somewhat discursive ('decide what it should *feel* like', extended prose on what good notes look like) and could be trimmed, keeping this below the lean anchor of 5.

4 / 5

Actionability

The body provides copy-paste-ready JS (the getSlideGrid listing script, the font-loading text-extraction script, the SLIDE_ROW rename snippet) and concrete numbers (3-5 slides per use_figma call, ~3s validation). It stops short of anchor 5 because the core build machinery — the color-constant preamble, addFrame/addText/addRect helpers, and the batch validation script — is only pointed to in slide-gotchas.md rather than shown inline, and design guidance is necessarily qualitative.

4 / 5

Workflow Clarity

The two-phase deck-building workflow is explicitly sequenced (plan with slide-by-slide layout descriptions, shared constants, layout-variety check; then batch builds of 3-5 slides) with explicit validation checkpoints and feedback loops: 'Validate every batch... If the check passes, proceed without a screenshot. If it fails, screenshot the affected slides and fix before continuing.' Batch operations carry validation, so the workflow cap does not apply; the gear-selection guidance (edits vs. structural additions vs. new decks) adds an upfront decision checkpoint.

5 / 5

Progressive Disclosure

The SKILL.md body is a well-organized overview that keeps detail in six one-level-deep reference files — all verified to exist, with the inline anchors (slide-gotchas.md#position-after-appendchild-critical, slide-gotchas.md#batch-validation-script, slide-properties.md#supported-formatting) resolving to real headings. A 'Reference Docs' section gives a one-line description of each file and instructs 'Load only the references your task needs', making navigation easy.

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 correctly identifies a niche (Figma Slides via the use_figma MCP tool) and distinguishes itself from the companion figma-use skill, but it reads as a structural label rather than a capability description. It lists no concrete actions, no natural user trigger terms like 'deck' or 'presentation', and no 'use when' guidance, leaving it below the quality bar the body content actually deserves.

Suggestions

Add a 'Use when...' clause stating when to invoke this skill, e.g. 'Use when creating or editing Figma Slides decks/presentations, adding speaker notes, or organizing slide sections' — this addresses completeness (currently capped at 3) and adds the missing trigger terms.

Replace the generic 'helps agents use... tool' with 2-3 concrete actions the skill enables, e.g. 'Create, edit, and restyle Figma Slides decks; write speaker notes; organize slides into named sections' — this lifts specificity from naming the domain to listing capabilities.

Include natural synonyms users would actually say — 'presentation', 'deck', 'slide deck', 'Figma Slides' — so trigger_term_quality covers the common phrasings instead of only the technical tool name use_figma.

DimensionReasoningScore

Specificity

"This skill helps agents use Figma's use_figma MCP tool in the Slides context" names the domain, but the only action is the generic verb "use" — no concrete capabilities (creating decks, editing slides, adding speaker notes, organizing sections) are stated. It matches the anchor 'Names the domain but actions are minimal or generic'; it is not a 3 because no concrete action is actually listed.

2 / 5

Completeness

There is a clear-enough 'what' (Slides-specific context for the use_figma MCP tool), but there is no 'Use when...' clause or equivalent trigger guidance anywhere — the judging guideline caps completeness at 3 for this. It cannot score 4 because 'when' is entirely absent rather than merely implicit.

3 / 5

Trigger Term Quality

Relevant keywords are present ("Figma", "use_figma MCP tool", "Slides") but the natural phrases a user would say — "deck", "presentation", "slide deck" — are absent. This fits 'Some relevant keywords but missing common variations or synonyms' rather than the good-coverage anchor of 4.

3 / 5

Distinctiveness Conflict Risk

"in the Slides context" plus explicit positioning against the companion "figma-use" skill carves a clear niche with mostly distinct triggers. It is not a 5 because the missing everyday terms ("presentation", "deck") mean a request like 'make a Figma deck' could plausibly route to the foundational figma-use skill instead.

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: 3 suspicious

Warning

Total

15

/

16

Passed

Repository

Devin-AXIS/iPolloWork

Path

examples/plugin-packages/figma/skills/figma-use-slides/SKILL.md

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.