CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

55

Quality

62%

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-slides/SKILL.md

The canonical home for this skill is figma-use-slides in openai/plugins

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.

A strong, well-structured skill body: concrete rules with exact failure signatures, executable scripts, an explicitly validated build workflow, and exemplary one-level-deep reference organization. The main weakness is verbosity in the Design Thinking and Speaker Notes sections, which could be tightened or offloaded to references.

Suggestions

Trim the four 'Design Thinking' principles to a compact checklist and move the design philosophy detail into slide-design.md, keeping only the decision rules (inherit vs. full design mode, reference-file interpretation) in the body.

Compress the Speaker Notes section (~50 lines) to the trigger conditions and formatting constraints (speakerNotes accepts markdown; supported/unsupported syntax link), moving the craft guidance into a reference or the properties file.

The 'Sections' subsections (Naming + scoping, Renaming a section) could merge into a single tighter section since each is only 2-4 sentences.

DimensionReasoningScore

Conciseness

The critical rules, gotchas, and two-phase workflow are dense, non-inferable domain knowledge, but the multi-paragraph 'Design Thinking' principles ('take a position', 'give it a signature') and ~50 lines of speaker-notes craft guidance are noticeably padded and partly inferable. It sits between anchor 3 and 4: the over-explanation spans whole sections rather than minor instances.

3 / 5

Actionability

Executable inspection scripts (including correct mixed-fontName handling), a rename snippet, exact error signatures ('TypeError: figma.createPage no such property'), and anchored links to concrete helper and validation scripts. Guidance is copy-paste ready and covers the common cases.

5 / 5

Workflow Clarity

The two-phase deck-building workflow sequences planning and batch execution with explicit validation checkpoints ('Validate every batch with the deterministic batch validation script... in ~3 seconds'), an error-recovery feedback loop ('If it fails, screenshot the affected slides and fix before continuing'), and screenshot checkpoints after the first and final batches.

5 / 5

Progressive Disclosure

The body is a clear overview with a 'Reference Docs' section listing all six real, one-level-deep reference files with one-line descriptions, plus inline anchored links (e.g. slide-gotchas.md#position-after-appendchild-critical) that resolve to actual sections. Navigation is easy and content is appropriately split between the overview and references.

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 its niche clearly but says almost nothing actionable: no concrete capabilities, no user-facing trigger terms, and no 'use when' guidance. It would rarely be selected by a user's natural phrasing ('make me a presentation/deck') and leaves the division of labor with the sibling figma-use skill implicit.

Suggestions

Add an explicit trigger clause, e.g. 'Use when creating, editing, redesigning, or organizing Figma Slides presentations and decks, or when the user mentions slides, decks, speaker notes, or figma.com/slides files.'

Enumerate the concrete capabilities covered by the body: building new decks, editing existing slides, applying brand/reference-file design, organizing sections, and writing speaker notes.

State the division of labor with figma-use in one clause users can act on (e.g. 'figma-use covers general Design-file use; this skill adds Slides-specific rules and workflows').

DimensionReasoningScore

Specificity

'helps agents use Figma's use_figma MCP tool in the Slides context' names the domain and tool but enumerates zero concrete actions (no deck creation, slide editing, speaker notes, or grid organization). Matches anchor 2 ('Names the domain but actions are minimal or generic'); not 3 because no capabilities are listed; not 1 because the domain is concretely identified rather than abstract.

2 / 5

Completeness

The 'what' is vague ('helps agents use... provides context') rather than a capability statement, and the 'when' is entirely absent — there is no 'Use when...' clause. Anchor 2 ('Has a vague what and no when'); not 3 because the what never states a concrete capability, and the missing trigger clause caps completeness at 3 regardless.

2 / 5

Trigger Term Quality

'Figma', 'Slides', and 'use_figma MCP tool' are relevant keywords, but the natural phrases users would say — 'presentation', 'slide deck', 'deck', 'speaker notes' — are all missing. Anchor 3 ('Some relevant keywords but missing common variations or synonyms'); not 4 because a user asking for a 'presentation' or 'deck' would not naturally trigger this description.

3 / 5

Distinctiveness Conflict Risk

The niche is clear (Figma Slides via the use_figma MCP tool) and it explicitly positions itself as complementary to the sibling 'figma-use' skill, which mitigates conflict. Anchor 4 ('Mostly distinct; minor overlap risk with closely related skills'); not 5 because it never states when to choose this skill over figma-use beyond the implicit 'Slides context'.

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: 3 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.