slide-craft

The design law of a slide page — canvas geometry, the text height table, the type scale, contrast pairs, spacing rhythm, and which element type carries which content. Load it when patching slide elements one at a time, when a fix is about colour or contrast, when text has to grow or shrink inside a box, when a page feels crowded or empty, or when replacement content needs real rich-text structure. It is the standard `page-clone` and `pro-editing` edit against, not a procedure of its own — those two decide which pages to touch and in what order, this one decides what a good page looks like when you put it back.

Quality

87%

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

Quality

Content

82%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 tightly written, highly actionable rule set for slide-page editing, with exact numbers, formulas, and a strong post-patch validation checklist. It is well-structured but lacks an explicit retry feedback loop and ships no reference bundle, leaving minor room on workflow clarity and progressive disclosure.

Suggestions

Add an explicit validate→fix→retry loop after the 'After the patch' checklist (e.g., 'if any check fails, fix and re-run the checklist') to lift workflow clarity toward 5.

Consider moving the height table and type-scale tables into a references/ file referenced from the body, to improve progressive disclosure and trim the in-body token load.

Trim the narrative framing in the opening two paragraphs ('the rules are the only way to tell a repair from a dent') to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Dense with runtime-specific rules Claude does not already know (canvas 1000×562.5, the height table, renderer HTML-tag behaviour), with tight rule-based prose. Not 5 because the intro carries mild narrative padding ('the rules are the only way to tell a repair from a dent'); not 3 because almost every token is earning its place on runtime specifics.	4 / 5
Actionability	Highly concrete and specific: exact geometry numbers, derived formulas ('text.left = shape.left + (shape.width - text.width) / 2'), lookup tables, contrast ratios (≥4.5:1), and named colour pairs. As an instruction-only skill, the absence of code is not penalized—the guidance is directly executable.	5 / 5
Workflow Clarity	Explicit ordered fix sequences ('shorten the words, then step to the next table row, then widen the box — in that order') and a 7-point 'After the patch' validation checklist. Not 5 because there is no explicit validate→fix→retry feedback loop; not 3 because validation checkpoints are clearly present, so no destructive/batch cap applies.	4 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), so scoring is against in-body structure: clear section headers, tables, a 'Hard rules' summary, and a 'Where this sits' map to peer skills. Well-organized with minor gaps; the ~290-line body is cohesive rather than monolithic. Not 5 because it exceeds the simple-skill (<50 line) exception and inlines tables that could live in a reference file.	4 / 5
	Total	17 / 20 Passed

Description

87%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 and explicitly covers both what the skill does and when to load it, with several concrete trigger scenarios and a well-defined niche that distinguishes it from sibling skills. Trigger terms are good but slightly technical, and capabilities are presented as when-conditions rather than a clean action list.

Dimension	Reasoning	Score
Specificity	Lists several concrete trigger-actions ('patching slide elements one at a time', 'a fix is about colour or contrast', 'text has to grow or shrink inside a box', 'replacement content needs real rich-text structure') alongside design domains. Not 5 because capabilities are framed as when-conditions rather than a clean action list; not 3 because multiple concrete actions are clearly named.	4 / 5
Completeness	Explicitly answers both 'what' ('The design law of a slide page — canvas geometry, the text height table, the type scale, contrast pairs, spacing rhythm…') and 'when' with a 'Load it when…' clause giving multiple concrete trigger phrases.	5 / 5
Trigger Term Quality	Contains natural phrases a user might voice ('a page feels crowded or empty', 'colour or contrast', 'text has to grow or shrink') but also leans technical/idiomatic ('canvas geometry', 'spacing rhythm', 'type scale') without synonym coverage. Good keyword coverage with a few natural variants missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (slide-page design law) and it explicitly carves itself apart from peer skills ('the standard page-clone and pro-editing edit against, not a procedure of its own'), so conflict risk is minimal.	5 / 5
	Total	18 / 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: THU-MAIC/OpenMAIC
Path: skills/agent-runtime/slide-craft/SKILL.md
Commit: 636fab0

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.