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.

53

Quality

60%

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 ./plugins/figma/skills/figma-use-slides/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

This is a strong, high-signal skill body: it leads with precise, environment-specific gotchas and error signatures, provides executable inspection code, and sequences deck-building through a validated two-phase workflow with feedback loops. Its weaknesses are moderate verbosity in the advisory prose sections and a couple of topics that belong in reference files rather than the main body.

Suggestions

Tighten the speaker-notes prose (the 'what good notes look like' and 'what to avoid' subsections) into compact bullet rules — the whispering-colleague framing and full-script caveat can each be one line.

Consider moving the detailed speaker-notes and sections guidance into a reference file (e.g. slide-notes.md), keeping SKILL.md to the decision rules (when to write notes, formatting limits) with a link.

Verify the cross-skill link ../figma-use/SKILL.md resolves in deployment environments — it is the only reference outside this bundle's references/ directory and reads as a broken link if that sibling skill is absent.

DimensionReasoningScore

Conciseness

The body is dense with genuinely non-obvious knowledge (the (−240, −240) appendChild offset bug, opaque SLIDE_GRID/SLIDE_ROW nodes, createPage throwing in Slides) and explains nothing Claude already knows, but the speaker-notes and design-thinking sections carry prose-heavy passages ("feel like a trusted colleague leaning over and whispering", multi-paragraph design philosophy) that could be tightened — 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the minor trims of level 4.

3 / 5

Actionability

Copy-paste-ready inspection scripts (the grid listing and the findAllWithCriteria + font-loading text extraction), exact error-message strings ('no such property createPage'), precise batch sizing (3–5 slides per call), and anchored links to the helper preamble and deterministic validation script — fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

The two-phase plan→build workflow is clearly sequenced with explicit validation checkpoints for every batch (deterministic overlap/clip/bounds script, screenshot at first and final batches) and an explicit error-recovery loop ('If it fails, screenshot the affected slides and fix before continuing'); inspect-before-create and never-delete-unless-asked guardrails cover the destructive cases, so no cap applies.

5 / 5

Progressive Disclosure

All six referenced files (slide-gotchas, slide-lifecycle, slide-grid, slide-content, slide-properties, slide-design) exist, are exactly one level deep, and are cataloged with per-file descriptions in the 'Reference Docs' section; the deduction is that sizable bodies of guidance (speaker notes, sections) sit inline in SKILL.md where the pattern elsewhere pushes detail into references.

4 / 5

Total

17

/

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 is short and honest but undersells the skill: it identifies the niche (Slides context for the use_figma MCP tool) yet names no concrete capabilities and provides no 'Use when' trigger guidance. It also omits natural user vocabulary like deck, presentation, and speaker notes, so routing relies on the body rather than the description.

Suggestions

Add a 'Use when...' clause naming the concrete triggers, e.g. 'Use when creating or editing Figma Slides decks, applying brand styling to slides, or adding speaker notes.'

List the skill's concrete capabilities (create/edit decks, organize sections, write speaker notes, brand-match from reference files) instead of the generic 'helps agents use the tool'.

Include natural user vocabulary — deck, presentation, slides, speaker notes — as trigger terms alongside the technical MCP tool name.

DimensionReasoningScore

Specificity

The description names the domain ("Figma's use_figma MCP tool in the Slides context") but lists no concrete actions — "helps agents use" is generic, matching the 'Names the domain but actions are minimal or generic' anchor rather than the 1-2 concrete actions of level 3.

2 / 5

Completeness

The 'what' is vague ("This skill helps agents use...") and there is no 'Use when...' clause or equivalent trigger guidance anywhere — exactly the anchor 'Has a vague what and no when'; the missing when-clause caps this at 3, and the vague what pulls it below.

2 / 5

Trigger Term Quality

"Figma" and "Slides" are natural user terms, but common phrases a user would actually say — deck, presentation, slides deck, speaker notes — are absent, matching 'Some relevant keywords but missing common variations or synonyms.'

3 / 5

Distinctiveness Conflict Risk

It carves a clear Slides niche and explicitly positions against the sibling figma-use skill, but both share the 'Figma' trigger space so a user mentioning Figma generically could route to the wrong skill — matching 'Mostly distinct; minor overlap risk with closely related skills.'

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
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.