CtrlK
BlogDocsLog inGet started
Tessl Logo

frontend-slides

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files.

52

Quality

58%

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/AI-Agents-Safe-Coding-Skills-claude/skills/frontend-slides/SKILL.md

The canonical home for this skill is frontend-slides in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 well-sequenced, highly actionable workflow with strong concrete CSS/viewport guidance, but it is weakened by redundant aesthetics coaching and by a broken progressive-disclosure layer where most referenced bundle files do not actually exist.

Suggestions

Tighten the Design Aesthetics section: collapse the bullets, the 'Avoid generic AI-generated aesthetics' list, and the closing 'think outside the box' paragraph into a single concise list to remove redundancy.

Ship the referenced bundle files (STYLE_PRESETS.md, viewport-base.css, html-template.md, animation-patterns.md) under the expected paths, or remove the references and inline the minimal content — the Supporting Files table currently points to content that is not present.

Add an explicit post-generation verification checkpoint in Phase 3 (e.g., 'Verify every .slide is overflow:hidden and content fits at 1280x720; if it overflows, split the slide and regenerate') to close the viewport-fit feedback loop.

DimensionReasoningScore

Conciseness

Mostly efficient and actionable, but the Design Aesthetics section restates the 'avoid AI slop / generic fonts' message across the bullets, the 'Avoid generic AI-generated aesthetics' list, and a closing exhortation ('it is critical that you think outside the box!'), which is redundant and could be tightened, matching the 'mostly efficient with some unnecessary explanation' anchor.

3 / 5

Actionability

Concrete, executable guidance is pervasive: exact CSS rules ('height: 100vh; height: 100dvh; overflow: hidden;', 'clamp(min, preferred, max)'), the '-clamp() -> calc(-1 * clamp())' gotcha, a density-limits table, exact commands ('python scripts/extract-pptx.py <input.pptx> <output_dir>'), and preview save paths; it falls short of 5 because full templates/code are deferred to reference files and the AskUserQuestion calls are described in prose rather than as ready tool invocations.

4 / 5

Workflow Clarity

Phases 0-5 are clearly sequenced with branching and real checkpoints (Mode C's 5-point verify checklist, 'Confirm via AskUserQuestion', 'Confirm with user' in Phase 4), fitting the clear-sequence-most-checkpoints anchor; it does not reach 5 because Phase 3 (new generation) lacks an explicit post-generation 'verify each slide fits the viewport' feedback loop, which the NON-NEGOTIABLE viewport rule implicitly demands.

4 / 5

Progressive Disclosure

The reference design is well-signaled and one-level-deep with a clear Supporting Files table (purpose + when-to-read per file), but scoring against the actual bundle reveals 4 of the 5 referenced files (STYLE_PRESETS.md, viewport-base.css, html-template.md, animation-patterns.md) are absent from the bundle, so the disclosure navigates mostly to missing content — between good-structure (4) and poorly-signaled (3).

3 / 5

Total

14

/

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 conveys a clear, mostly distinct niche but is capped by a missing 'Use when...' trigger clause and limited keyword/variation coverage. 'Stunning' adds fluff without specificity.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., 'Use when the user asks to create a slide deck, pitch deck, or presentation, or to convert a .pptx file to a web presentation').

Broaden trigger terms to include natural synonyms and extensions users actually say: 'slides', 'slide deck', 'pitch deck', 'PPT', 'PPTX', '.pptx'.

Drop the vague 'stunning' and list one or two more concrete capabilities (e.g., keyboard navigation, in-browser inline editing, or exporting to HTML) to lift specificity toward 4-5.

DimensionReasoningScore

Specificity

Names the domain ('HTML presentations', 'PowerPoint files') and two concrete actions ('Create ... from scratch', 'by converting PowerPoint files'), matching the anchor for 1-2 concrete actions; 'stunning' is vague fluff and coverage is not comprehensive, so it stays at 3 rather than 4.

3 / 5

Completeness

It clearly states what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance; per the judging guidelines a missing trigger clause caps completeness at 3, matching the anchor for a clear 'what' with 'when' absent.

3 / 5

Trigger Term Quality

Includes some natural terms ('presentations', 'PowerPoint files') but is missing common variations users would say such as 'slides', 'slide deck', 'pitch deck', 'PPT', 'PPTX', or '.pptx', fitting the anchor for some relevant keywords missing synonyms.

3 / 5

Distinctiveness Conflict Risk

'Animation-rich HTML presentations ... from scratch or by converting PowerPoint files' carves a fairly specific niche with distinct triggers, but there is minor overlap risk with a generic presentation/slides skill, fitting the 'mostly distinct, minor overlap' anchor rather than the minimal-conflict anchor at 5.

4 / 5

Total

13

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 9 missing

Warning

Total

14

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.