Agent skill · Audited from source
frontend-dev-guidelines
skill · mrgoonie/claudekit-skillsLicence not declaredAudited 29 Oct 2026 · source d655ab03f566
Is it safe? No — BLOCK, grade F (27/100). We read this skill's source at commit d655ab03f566 and observed filesystem, network and shell access and a hard-coded secret (see the findings). The audit raised 25 findings, 6 critical or high. What it does: Create aesthetically beautiful interfaces following proven design principles. Use when building UI/UX, analyzing designs from inspiration sites, generating design images with ai-multimodal, implementing visual hierarchy…
Cite
Cite this page
ModelsAtlas. “frontend-dev-guidelines (mrgoonie/claudekit-skills)”. Retrieved 29 Oct 2026. https://modelsatlas.com/skills/mrgoonie/frontend-dev-guidelines
Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 6 critical or high findings, starting with “Prompt injection” in .claude/skills/better-auth/SKILL.md:3. Do not install it without reading them.
Trust audit
Audit 0.4.1 · source read 29 Oct 2026
BLOCK means the audit found something that could harm you or your machine. Grade F is shared by 105 of 14,816 audited skills.
What the source does
- FilesystemDeclared5 observations
- NetworkDeclared4 observations
- ShellDeclared3 observations
- DependenciesNot pinnedSome versions float
- SecretsFoundSee the findings; values are never shown
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | WARN | 10 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | FAIL | 12 |
L2 Instructions | Prompt injection, authority framing, hidden directives | FAIL | 3 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: critical finding, no behavioural pass, undeclared transfer.
Findings (25)
CRITICALPrompt injectionprompt.transfer_instruction · .claude/skills/better-auth/SKILL.md:3
description: Implement authentication and authorization with Better Auth - a framework-agnostic TypeScript authentication framework. Features include email/password authentication with verification, O
- Why
- an instruction to move sensitive data to an outside destination
- Fix
- remove; a skill never needs the user's secrets off the machine
HIGHCode injectioncode.eval_exec · .claude/skills/ai-multimodal/scripts/media_optimizer.py:107
info['fps'] = eval(stream.get('r_frame_rate', '0/1'))- Why
- evaluates text as code
- Fix
- remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · .claude/skills/chrome-devtools/scripts/evaluate.js:32
return eval(script);
- Why
- evaluates text as code
- Fix
- remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · .claude/skills/chrome-devtools/scripts/lib/selector.js:203
await page.$eval(parsed.selector, el => el.value = '');
- Why
- evaluates text as code
- Fix
- remove; use a parser or a dispatch table
HIGHPrompt injectionprompt.tool_poisoning · .claude/skills/context-engineering/references/context-fundamentals.md:26
<INSTRUCTIONS>Step-by-step procedures</INSTRUCTIONS>
- Why
- a tool description carrying instructions to the agent
- Fix
- tool descriptions describe the tool; nothing else
HIGHPrompt injectionprompt.zero_width · MCP_MANAGEMENT.md:29
So I transferred that MCP processing part to... `gemini-cli` 😂
- Why
- invisible characters in instruction text
- Fix
- strip non-printing characters
MEDIUMInventory / provenanceinv.binary · .claude/skills/better-auth/scripts/.coverage
.coverage
- Why
- a compiled or binary member cannot be reviewed from source
- Fix
- ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.binary · .claude/skills/databases/scripts/.coverage
.coverage
- Why
- a compiled or binary member cannot be reviewed from source
- Fix
- ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.symlink · plugins/ai-ml-tools/skills/ai-multimodal
plugins/ai-ml-tools/skills/ai-multimodal
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · plugins/ai-ml-tools/skills/context-engineering
plugins/ai-ml-tools/skills/context-engineering
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · plugins/ai-ml-tools/skills/google-adk-python
plugins/ai-ml-tools/skills/google-adk-python
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · plugins/backend-tools/skills/backend-development
plugins/backend-tools/skills/backend-development
- Why
- link not followed
- Fix
- —
MEDIUMInventory / provenanceinv.symlink · plugins/backend-tools/skills/better-auth
plugins/backend-tools/skills/better-auth
- Why
- link not followed
- Fix
- —
MEDIUMInformation disclosuredisclose.log_secret · .claude/skills/common/api_key_helper.py:293
print(f"…" + "*" * (len(api_key) - 8))
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.raw_ip · .claude/skills/ai-multimodal/.env.example:25
# GEMINI_BASE_URL=http://127.0.0.1:8045
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.db_uri · .claude/skills/backend-development/references/backend-devops.md:123
- DATA…://…@db:5432/myapp
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.generic · .claude/skills/better-auth/references/email-password-auth.md:132
token: "…"
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.generic · .claude/skills/better-auth/references/email-password-auth.md:166
token: "…",
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.generic · .claude/skills/better-auth/references/email-password-auth.md:167
password: "…"
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWInventory / provenanceinv.binary · .claude/skills/ai-multimodal/scripts/tests/.coverage
.coverage
- Why
- a compiled or binary member cannot be reviewed from source
- Fix
- ship source, or explain the binary in the README
LOWInventory / provenanceinv.binary · .claude/skills/better-auth/scripts/tests/.coverage
.coverage
- Why
- a compiled or binary member cannot be reviewed from source
- Fix
- ship source, or explain the binary in the README
LOWInventory / provenanceinv.binary · .claude/skills/media-processing/scripts/tests/.coverage
.coverage
- Why
- a compiled or binary member cannot be reviewed from source
- Fix
- ship source, or explain the binary in the README
LOWCode injectioncode.eval_exec · .claude/skills/chrome-devtools/scripts/__tests__/selector.test.js:111
it('should block eval( injection', () => {- Why
- evaluates text as code
- Fix
- remove; use a parser or a dispatch table
LOWCode injectioncode.eval_exec · .claude/skills/chrome-devtools/scripts/__tests__/selector.test.js:120
() => parseSelector('//div[Function("return 1")()]'),- Why
- evaluates text as code
- Fix
- remove; use a parser or a dispatch table
LOWNetwork egressnet.metadata_ip · .claude/skills/web-testing/references/vulnerability-payloads.md:69
http://169.254.169.254/ # AWS metadata
- Why
- cloud metadata endpoint: the classic SSRF credential grab
- Fix
- —
Audit 0.4.1 · source sha d655ab03f566 · 29 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publishermrgoonie GitHub userOwner of the repository this skill is read from
- Source foldermrgoonie/claudekit-skillsThe exact folder we audited
- LicenceNot declaredAs the repository states it
- Commit pinned for this verdictd655ab03f566A new audit runs when the source changes
- Repository statusNot archivedLast push 208 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Create aesthetically beautiful interfaces following proven design principles. Use when building UI/UX, analyzing designs from inspiration sites, generating design images with ai-multimodal, implementing visual hierarchy…
---
name: aesthetic
description: Create aesthetically beautiful interfaces following proven design principles. Use when building UI/UX, analyzing designs from inspiration sites, generating design images with ai-multimodal, implementing visual hierarchy and color theory, adding micro-interactions, or creating design documentation. Includes workflows for capturing and analyzing inspiration screenshots with chrome-devtools and ai-multimodal, iterative design image generation until aesthetic standards are met, and comprehensive design system guidance covering BEAUTIFUL (aesthetic principles), RIGHT (functionality/accessibility), SATISFYING (micro-interactions), and PEAK (storytelling) stages. Integrates with chrome-devtools, ai-multimodal, media-processing, ui-styling, and web-frameworks skills.
---
# Aesthetic
Create aesthetically beautiful interfaces by following proven design principles and systematic workflows.
## When to Use This Skill
Use when:
- Building or designing user interfaces
- Analyzing designs from inspiration websites (Dribbble, Mobbin, Behance)
- Generating design images and evaluating aesthetic quality
- Implementing visual hierarchy, typography, color theory
- Adding micro-interactions and animations
- Creating design documentation and style guides
- Need guidance on accessibility and design systems
## Core Framework: Four-Stage Approach
### 1. BEAUTIFUL: Understanding Aesthetics
Study existing designs, identify patterns, extract principles. AI lacks aesthetic sense—standards must come from analyzing high-quality examples and aligning with market tastes.
**Reference**: [`references/design-principles.md`](references/design-principles.md) - Visual hierarchy, typography, color theory, white space principles.
### 2. RIGHT: Ensuring Functionality
Beautiful designs lacking usability are worthless. Study design systems, component architecture, accessibility requirements.
**Reference**: [`references/design-principles.md`](references/design-principles.md) - Design systems, component libraries, WCAG accessibility standards.
### 3. SATISFYING: Micro-Interactions
Incorporate subtle animations with appropriate timing (150-300ms), easing curves (ease-out for entry, ease-in for exit), sequential delays.
**Reference**: [`references/micro-interactions.md`](references/micro-interactions.md) - Duration guidelines, easing curves, performance optimization.
### 4. PEAK: Storytelling Through Design
Elevate with narrative elements—parallax effects, particle systems, thematic consistency. Use restraint: "too much of anything isn't good."
**Reference**: [`references/storytelling-design.md`](references/storytelling-design.md) - Narrative elements, scroll-based storytelling, interactive techniques.
## Workflows
### Workflow 1: Capture & Analyze Inspiration
**Purpose**: Extract design guidelines from inspiration websites.
**Steps**:
1. Browse inspiration sites (Dribbble, Mobbin, Behance, Awwwards)
2. Use **chrome-devtools** skill to capture full-screen screenshots (not full page)
3. Use **ai-multimodal** skill to analyze screenshots and extract:
- Design style (Minimalism, Glassmorphism, Neo-brutalism, etc.)
- Layout structure & grid systems
- Typography system & hierarchy
**IMPORTANT:** Try to predict the font name (Google Fonts) and font size in the given screenshot, don't just use Inter or Poppins.
- Color palette with hex codes
- Visual hierarchy techniques
- Component patterns & styling
- Micro-interactions
- Accessibility considerations
- Overall aesthetic quality rating (1-10)
4. Document findings in project design guidelines using templates
### Workflow 2: Generate & Iterate Design Images
**Purpose**: Create aesthetically pleasing design images through iteration.
**Steps**:
1. Define design prompt with: style, colors, typography, audience, animation specs
2. Use **ai-multimodal** skill to generate design images with Gemini API
3. Use **ai-multimodal** skill to analyze output images and evaluate aesthetic quality
4. If score < 7/10 or fails professional standards:
- Identify specific weaknesses (color, typography, layout, spacing, hierarchy)
- Refine prompt with improvements
- Regenerate with **ai-multimodal** or use **media-processing** skill to modify outputs (resize, crop, filters, composition)
5. Repeat until aesthetic standards met (score ≥ 7/10)
6. Document final design decisions using templates
## Design Documentation
### Create Design Guidelines
Use [`assets/design-guideline-template.md`](assets/design-guideline-template.md) to document:
- Color patterns & psychology
- Typography system & hierarchy
- Layout principles & spacing
- Component styling standards
- Accessibility considerations
- Design highlights & rationale
Save in project `./docs/design-guideline.md`.
### Create Design Story
Use [`assets/design-story-template.md`](assets/design-story-template.md) to document:
- Narrative elements & themes
- Emotional journey
- User journey & peak moments
- Design decision rationale
Save in project `./docs/design-story.md`.
## Resources & Integration
### Related Skills
- **ai-multimodal**: Analyze documents, screenshots & videos, generate design images, edit generated images, evaluate aesthetic quality using Gemini API
- **chrome-devtools**: Capture full-screen screenshots from inspiration websites, navigate between pages, interact with elements, read console logs & network requests
- **media-processing**: Refine generated images (FFmpeg for video, ImageMagick for images)
- **ui-styling**: Implement designs with shadcn/ui components + Tailwind CSS utility-first styling
- **web-frameworks**: Build with Next.js (App Router, Server Components, SSR/SSG)
### Reference Documentation
**References**: [`references/design-resources.md`](references/design-resources.md) - Inspiration platforms, design systems, AI tools, MCP integrations, development strategies.
## Key Principles
1. Aesthetic standards come from humans, not AI—study Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit d655ab0
pip install google-genai python-dotenv pillow pip install httpie npm install -g 0x npm install -g clinic npm install better-auth npm install drizzle-orm better-auth
git clone https://github.com/mrgoonie/claudekit-skills git -C claudekit-skills checkout d655ab03f566
Commands as the repository documents them: shown, never run by us. Our verdict covers commit d655ab03f566 only.
Works in which agents?
What its own text says, not a test
| Agent | Status | More |
|---|---|---|
| Claude Code | Mentioned in its text, not tested | Skills for Claude Code · About Claude Code |
| Claude Desktop | Mentioned in its text, not tested | Skills for Claude Desktop · About Claude Desktop |
| Cursor | Mentioned in its text, not tested | Skills for Cursor · About Cursor |
| Gemini CLI | Mentioned in its text, not tested | Skills for Gemini CLI · About Gemini CLI |
| OpenClaw | Mentioned in its text, not tested | Skills for OpenClaw · About OpenClaw |
| Windsurf | Mentioned in its text, not tested | Skills for Windsurf · About Windsurf |
Audit history
Every audit, every source change
- ✕BLOCK F 27 / 100
first audit · source
d655ab03f566
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/mrgoonie/frontend-dev-guidelines/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
AgentWorkforce/relay
Infrastructure for coding agents
artokun/comfyui-mcp
Train custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the user wants to train a WAN or Z-Image LoRA; covers local +…
metalbear-co/mirrord
Help users chaos test their app with mirrord: inject artificial latency or connection errors into a mirrord session's outgoing traffic via per-session chaos rules managed with the `mirrord chaos` CLI. Use when a user…
Add this badge to your README
[](https://modelsatlas.com/skills/mrgoonie/frontend-dev-guidelines/)
<a href="https://modelsatlas.com/skills/mrgoonie/frontend-dev-guidelines/"><img src="https://modelsatlas.com/skills/mrgoonie/frontend-dev-guidelines/badge.svg" alt="ModelsAtlas: BLOCK F"></a>
Questions about frontend-dev-guidelines
What does the frontend-dev-guidelines skill do?
Is frontend-dev-guidelines safe to install?
What can frontend-dev-guidelines access on my machine?
Which assistants does frontend-dev-guidelines work with?
How current is this page?
Sources
- github.com/mrgoonie/claudekit-skills — the audited source at commit d655ab03f566 and every finding aboveObserved · 29 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the frontend-dev-guidelines skill do?
- Is frontend-dev-guidelines safe to install?
- What can frontend-dev-guidelines access on my machine?