Name: deck-open-slide-canvas
Rating: 56.8 (1 reviews)
Author: nexu-io

deck-open-slide-canvas

OpenDesign's architecture review: the local daemon + agent-runtime design, the tradeoffs, and the decision to lock. Built as a decision-grade product management deck for staff eng, tech leads, security.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/_official/examples/deck-open-slide-canvas/SKILL.md

The canonical home for this skill is deck-open-slide-canvas in nexu-io/open-design

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 lean and highly actionable, with exact design specifications a model can directly apply, and is well-organized for a simple single-file skill. Its main gap is the absence of an explicit validation step for the strict no-overflow/per-page-fit constraint.

Suggestions

Add an explicit validation checkpoint for the hard no-overflow rule (e.g., 'After building each slide, verify content fits 1920x1080 with no scrollbars; if it overflows, reduce density or scale before proceeding').

Provide a minimal copy-paste HTML skeleton (the <section class="slide"> wrapper, Tailwind CDN include, and scale transform) so output is fully copy-paste ready.

Optionally express the build as a short numbered sequence (choose palette -> draft slide plan per content type -> lay out with one visual focal point -> validate fit) to make the workflow explicit.

Dimension	Reasoning	Score
Conciseness	Dense, spec-driven content with exact CSS values, hex codes, a full type scale, and named fonts; every line is a concrete constraint with no concept-explanation padding, assuming Claude's competence.	5 / 5
Actionability	Provides concrete executable specs ('width: 1920px; height: 1080px', 'transform: scale(...)', exact padding/font values, hex palettes, required <section> structure), but lacks a complete copy-paste HTML skeleton template.	4 / 5
Workflow Clarity	Sections are logically ordered but there is no explicit multi-step sequence, and the hard 'no overflow / must fit 1920x1080' constraint — a batch-like per-slide risk — has no validation checkpoint, capping the score at 3.	3 / 5
Progressive Disclosure	A simple, under-50-line single-file skill with no bundle files and well-organized labeled sections (intent, specs, palettes, layout, fonts, details), satisfying the simple-skill exception.	5 / 5
	Total	17 / 20 Passed

Description

51%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 clearly conveys what the skill produces but lacks any 'when to use' trigger guidance and relies on product-specific jargon rather than natural user phrasings. It is reasonably distinct and specific but underperforms on trigger completeness.

Suggestions

Add a 'Use when...' clause with natural trigger phrases (e.g., 'Use when building an architecture review deck, an architecture decision record, or a technical tradeoff deck for staff eng audiences').

Replace product-specific jargon like 'decision-grade' with concrete, user-facing terms and synonyms users would actually say (e.g., 'architecture review', 'technical decision deck', 'ADR slide').

Lead with the skill's action verbs (e.g., 'Builds... organizes... produces...') in third person so capabilities read as concrete actions, not just content nouns.

Dimension	Reasoning	Score
Specificity	Names concrete content elements ('the local daemon + agent-runtime design, the tradeoffs, and the decision to lock', 'decision-grade product management deck'), listing several specifics, though as content nouns rather than skill actions.	4 / 5
Completeness	The 'what' is clear (an architecture-review decision deck) but there is no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Terms are product-specific jargon ('OpenDesign's architecture review', 'decision-grade deck') rather than natural phrases a user would say; common trigger phrasings like 'architecture decision' or 'architecture review deck' are weakly present.	2 / 5
Distinctiveness Conflict Risk	The product-specific subject ('OpenDesign's architecture review') and named audience ('staff eng, tech leads, security') give it a mostly distinct niche with only minor overlap with generic deck/slide skills.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: plugins/_official/examples/deck-open-slide-canvas/SKILL.md
Commit: 1b47e60

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.