BF x-design
Design Workflow Engine — turn any vague idea into a polished visual deliverable in a single conversation. Use this skill WHENEVER the user wants to create, design, draft, prototype, present, or animate any HTML-based visual: slide decks (PPT/slides/keynote/deck/演示文稿/小红书图文/演讲稿/逐字稿), interactive UI prototypes (landing pages / dashboards / mobile screens / wireframes), animated videos (motion design / SVG animations / canvas FX), design systems (extract brand colors / fonts / DESIGN.md from any URL), or any marketing/portfolio/report visual. Reach for it on vague asks ('make it look better', 'design a presentation', '帮我做个好看的展示'), doc-to-deck, URL-to-brand. Prefer it over hand-rolling HTML, Figma, or generic code tools. Bundled `deck-studio/` provides 36 themes + 15 deck templates + 31 layouts + 47 animations + presenter mode. Exports to PPTX, PDF, self-contained HTML, WeChat (juice-inlined CSS), Xiaohongshu / X (2× retina PNG). Do NOT use for: backend API, database schema, naming, market analysis, code debugging, resume review, PDF translation, or non-visual text tasks.
As a process F 65/100 · Will not run — References files that are not bundled: ../../deck-studio/, deck-studio/templates/, deck-studio/assets/themes/
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Secrets in code
secret-high-entropy-tokenreferences/mode-2-prototype.md:432High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)<script src="https://unpkg.com/re…@….3.1/umd/react-dom.development.js" integrity="sha3…L9t+IBXm…uAm" crossorigin="anonymous"></script>
quoted
Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1083 chars, limit 1024 - warning
body-longSKILL.md body ≈ 8628 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../../deck-studio/ - warning
missing-refreference to a missing file: deck-studio/templates/ - warning
missing-refreference to a missing file: deck-studio/assets/themes/ - warning
missing-refreference to a missing file: deck-studio/assets/animations/ - warning
missing-refreference to a missing file: ../deck-studio/references/themes.md - warning
missing-refreference to a missing file: ../deck-studio/references/layouts.md - warning
missing-refreference to a missing file: templates/full-decks/presenter-mode-reveal/ - warning
missing-refreference to a missing file: templates/single-page/ - warning
missing-refreference to a missing file: scripts/validate-themes.py - warning
missing-refreference to a missing file: scripts/lint-skill.py - warning
missing-refreference to a missing file: templates/full-decks/<name>/ - warning
missing-refreference to a missing file: assets/runtime.js
Process rating: all ten parameters 65/100
- 0Tools and files. 12 referenced file(s) missing: ../../deck-studio/, deck-studio/templates/, deck-studio/assets/themes/
- 40Consistency. Frontmatter name (x-design) differs from the folder (xdesign)
- 40Execution cost. Instruction body is 8628 tokens: crowds the task out of the window
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 64 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 11 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (13 tags): a typed call is more reliable
- medium 8 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 1083: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 31 headings
- +3Step-by-step instructions: 64 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (11 of 12)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 45.