CtrlK
BlogDocsLog inGet started
Tessl Logo

deck-open-slide-canvas

Locked 1920x1080 canvas deck with React component-level free composition, not bound to a fixed template.

57

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/deck-open-slide-canvas/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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 excellent lean, concrete design spec: exact numeric constraints, named palettes, and hard prohibitions leave little ambiguity about the target output. Its main weaknesses are the absence of an ordered build sequence with a verification checkpoint for the no-overflow rule, and the lack of a minimal HTML slide skeleton that would make the scale/viewport adaptation executable rather than descriptive.

Suggestions

Add a short ordered workflow, e.g. 1) pick one palette for the whole deck, 2) choose a per-slide layout from the menu, 3) verify each page fits 1920×1080 with no scrollbar before finishing.

Include a minimal single-slide HTML skeleton showing the 1920×1080 section, the transform: scale() viewport adaptation, and the corner marks so the core mechanism is copy-paste ready.

Turn the overflow prohibition into an explicit validation step (e.g. 'after composing each slide, confirm content fits within 1920×1080; if not, reduce type size or trim content').

DimensionReasoningScore

Conciseness

The body is a dense constraint spec (~33 lines) with zero padding: every line states a hard rule (type scale, padding tiers, palette hexes, font stack) and nothing explains concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

Guidance is highly concrete — exact px type scale ('2xs:18 · ... · 5xl:220'), padding values '96 / 128 / 160', four palettes with hex codes, named fonts, and explicit behaviors (keyboard ←/→, hash sync, '№N/M' corner mark). It falls short of fully copy-paste ready because the 'transform: scale(...)' viewport adaptation is only sketched and no minimal slide HTML skeleton is given, matching the 'mostly executable guidance; concrete code or commands with minor gaps' anchor.

4 / 5

Workflow Clarity

The constraint sections are clear but there is no ordered process (pick palette → compose each page → assemble deck) and no explicit validation checkpoint: the overflow prohibition ('绝对禁止 overflow: 每页内容必须 fit in 1920×1080') is stated as a rule, not as a check step, matching the 'sequence present but checkpoints missing or implicit' anchor.

3 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references, and the body is organized into seven clearly labeled sections (意图/硬性技术规格/调色板/布局自由度/字体/设计细节), so the simple-skill exception applies: well-organized sections alone warrant a 5.

5 / 5

Total

17

/

20

Passed

Description

53%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 compact and communicates a specific artifact (locked 1920x1080 React free-composition deck), but it is a passive descriptor rather than a capability statement, and it entirely lacks a 'when to use' trigger clause. Adding an explicit 'Use when...' sentence and natural synonyms like 'slides' or 'presentation' would substantially improve it.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for slides, a presentation deck, or a free-composition 1920x1080 canvas deck and doesn't want a fixed template.'

Lead with concrete action verbs (e.g. 'Builds/Creates a locked 1920x1080 canvas deck by composing React-style components per slide') so the capability, not just the artifact, is stated.

Include natural user synonyms such as 'slides', 'presentation', and 'deck design' alongside 'deck' and 'canvas' to improve trigger coverage.

DimensionReasoningScore

Specificity

Names the domain with concrete specifics ("Locked 1920x1080 canvas deck", "React component-level free composition") but states no action verbs or capabilities beyond describing the artifact, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor rather than the multi-action anchor above.

3 / 5

Completeness

The 'what' is clear (a locked 1920x1080 free-composition deck), but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Relevant keywords like "canvas", "deck", "React", and "1920x1080" appear, but common variations users would naturally say ("slides", "presentation", "slide deck", "deck design") are missing, matching the 'some relevant keywords but missing common variations or synonyms' anchor.

3 / 5

Distinctiveness Conflict Risk

The phrase "not bound to a fixed template" plus the locked 1920x1080 canvas niche distinguishes it from template-bound deck skills; there remains minor overlap risk with other presentation/slide skills, matching the 'mostly distinct' anchor.

4 / 5

Total

13

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nexu-io/open-design
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.