CtrlK
BlogDocsLog inGet started
Tessl Logo

openkb-html-critic

Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every other. Also catches missing keyboard navigation, bullet-dump / wall-of-text failure modes, broken self-containment (external link/script/img). Patches the file in place; never changes the original content (slide text, numbers, named entities are the author's work, not yours).

76

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

87%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, expert-level instruction body with highly actionable and concrete guidance, organized into clean sections. The main gap is the absence of a verification checkpoint for the destructive in-place file overwrite, which caps workflow clarity.

Suggestions

Add an explicit validation/verification step in the Working method — e.g. re-read the written file (or render-check the patched CSS) to confirm only display: declarations changed and no content was altered — before reporting, since the in-place overwrite is destructive.

Reduce the minor redundancy between the CSS 'Fix' paragraph and the 'Quick scan' note so the display-property rule is stated once.

Consolidate the path/tool guidance so 'How this skill is invoked' and step 1 of 'Working method' do not repeat the same read_file vs read_output_or_skill_file distinction.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (no explanation of what HTML/CSS is) and is dense with earned content — concrete CSS patterns, exact thresholds, and named tools; only light redundancy between the CSS 'Fix' and 'Quick scan' notes keeps it just at the lean-and-efficient anchor.

3 / 3

Actionability

Provides copy-paste-ready, executable guidance: exact CSS to strip, specific key bindings, numeric thresholds (>8 list items, >150 words, 3+ consecutive slides), and exact tool calls (read_output_or_skill_file, write_file) — fully concrete rather than abstract.

3 / 3

Workflow Clarity

The 5-step Working method and ordered checklist give a clear sequence, but the destructive in-place overwrite has no validation/verification checkpoint (no re-read or render check before/after the atomic write), which caps it at 2 per the destructive-operation rule.

2 / 3

Progressive Disclosure

Self-contained with no bundle files and no nested references; content is well-organized into clearly labeled sections (invocation, 5-item checklist, working method, hard rule), which satisfies the well-organized-sections allowance for self-contained skills.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that uses third-person voice and opens with an explicit trigger clause, covering concrete capabilities and failure modes without fluff. Minor nit: a few terms like 'bullet-dump/wall-of-text' are skill-internal jargon rather than user-natural phrasing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — catching CSS specificity bugs in named modifier classes (.divider, .center, .q, .flow), missing keyboard navigation, bullet-dump/wall-of-text failure modes, broken self-containment, and in-place patching — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers what (review/patch HTML decks) and when (an explicit 'Use to review...' trigger clause), satisfying the both-what-and-when anchor rather than capping at 2.

3 / 3

Trigger Term Quality

Leads with the natural trigger 'Use to review a generated HTML deck... for visual quality and structural correctness' alongside concrete terms (CSS specificity bugs, keyboard navigation, self-containment); coverage is good though a few terms (bullet-dump, wall-of-text) lean toward internal jargon.

3 / 3

Distinctiveness Conflict Risk

The niche — reviewing generated single-file HTML decks for CSS specificity/nav/self-containment bugs — is sharply distinct and unlikely to trigger for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
VectifyAI/OpenKB
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.