Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Fluxwing Enhancer

ASecurity

Progressively enhance uxscii components from sketch to production quality.

18 stars
0 votes
0 copies
2 views
Added 12/19/2025
ai-agentstypescriptpythonbashdocumentation

Security Analysis

A100/100

Scanned 2/12/2026

Install to Claude Code

$npx -y skills add trabian/fluxwing-skills --skill fluxwing-enhancer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Fluxwing Enhancer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Fluxwing Enhancer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/trabian-fluxwing-enhancer/badge)](https://www.skillsdirectory.com/skills/trabian-fluxwing-enhancer)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: Fluxwing Enhancer
description: Enhance uxscii components from sketch to production fidelity. Use when working with .uxm files marked as "fidelity: sketch" or when user wants to add detail and polish to components.
version: 0.0.1
author: Trabian
allowed-tools: Read, Write, Edit, Glob, Grep, Task, TodoWrite
---

# Fluxwing Enhancer

Progressively enhance uxscii components from sketch to production quality.

## Data Location Rules

**READ from:**
- `./fluxwing/components/` - User components to enhance
- `{SKILL_ROOT}/../fluxwing-component-creator/templates/state-additions/` - State templates
- `{SKILL_ROOT}/docs/` - Enhancement documentation

**LOAD for copy-on-update logic:**
- `{SKILL_ROOT}/../shared/docs/copy-versioning.md` - Versioning pattern for fidelity enhancements

**WRITE to:**
- `./fluxwing/components/` - New versioned components (copy-on-update: {id}-v{N+1})
- `./fluxwing/screens/` - Updated screen .rendered.md (if applicable)

**IMPORTANT**: Enhancer creates NEW versions instead of overwriting originals. Each fidelity enhancement creates a new `-v{N}` copy.

## Fidelity Levels

### sketch (Fast Scaffold Output)
- Basic .uxm with minimal metadata
- May lack .md file or have simple .md
- Single "default" state
- Creation time: ~10 seconds

**Characteristics:**
- Minimal description
- Generic tags
- No examples
- Basic props only

### basic (First Enhancement)
- Enriched metadata (better description, tags)
- Simple .md with clean ASCII
- Default state only
- Enhancement time: ~30 seconds

**Improvements over sketch:**
- Detailed description
- Specific tags
- Clean ASCII art
- Documented variables

### detailed (Second Enhancement)
- Rich metadata with usage examples
- Polished .md with careful ASCII art
- 2-3 interaction states (hover, focus)
- Enhancement time: ~90 seconds

**Improvements over basic:**
- Usage examples in metadata
- Hover + focus states
- Polished ASCII
- Props.examples array

### production (Final Polish)
- Complete metadata with accessibility details
- Publication-quality ASCII
- All relevant states (hover, focus, disabled, active, error)
- Full documentation
- Enhancement time: ~180 seconds

**Improvements over detailed:**
- All applicable states
- Complete accessibility metadata
- Keyboard shortcuts
- Publication-quality ASCII
- Edge case documentation

## Your Task

Help users enhance components from current fidelity to target fidelity.

### Workflow

#### Step 1: Inventory Components

Check what components exist and their current fidelity:

```bash
ls ./fluxwing/components/*.uxm
```

For each component, read fidelity level:
```bash
python3 -c "import json; print(json.load(open('./fluxwing/components/button.uxm'))['metadata'].get('fidelity', 'detailed'))"
```

List components by fidelity:
- sketch: [component-ids]
- basic: [component-ids]
- detailed: [component-ids]
- production: [component-ids]

#### Step 2: Determine Target Fidelity

Ask user or use defaults:

**User specifies:**
- "Enhance to basic"
- "Upgrade to detailed"
- "Make production-ready"

**Auto-select (if not specified):**
- sketch → detailed (most common, best balance)
- basic → detailed
- detailed → production

#### Step 3: Spawn Enhancement Agents

**If enhancing multiple components (3+):**
- Spawn agents in parallel (one per component)
- Each agent enhances independently
- Wait for all to complete

**If enhancing single component:**
- Spawn single agent
- Focus on quality

**Enhancement Agent Prompt:**

```typescript
Task({
  subagent_type: "general-purpose",
  model: "sonnet", // Quality matters for enhancement
  description: "Enhance ${componentId} to ${targetFidelity} (copy)",
  prompt: `Enhance uxscii component from ${currentFidelity} to ${targetFidelity} using copy-on-update pattern.

Component: ${componentId}
Current fidelity: ${currentFidelity}
Target fidelity: ${targetFidelity}

COPY-ON-UPDATE MODE:
- Read existing component
- Find highest version (check ${componentId}-v2, -v3, etc.)
- Create NEW versioned copy: ${componentId}-v{N+1}
- DO NOT overwrite original
- Preserve metadata.created, update metadata.modified

Your task:
1. Read ./fluxwing/components/${componentId}.uxm
2. Read ./fluxwing/components/${componentId}.md (if exists)
3. Load copy-versioning docs: {SKILL_ROOT}/../shared/docs/copy-versioning.md
4. Find highest version of ${componentId} (original is v1)
5. Calculate next version number: v{N+1}
6. Load enhancement patterns: {SKILL_ROOT}/docs/enhancement-patterns.md
7. Load state templates: {SKILL_ROOT}/../fluxwing-component-creator/templates/state-additions/

8. Create versioned copy with enhancements:

   **Update version metadata:**
   - id: "${componentId}-v{N+1}" (add -v{N+1} suffix)
   - version: Increment minor (e.g., 1.0.0 → 1.1.0)
   - metadata.created: PRESERVE from source
   - metadata.modified: SET to current timestamp
   - metadata.fidelity: UPDATE to "${targetFidelity}"

   ${targetFidelity === 'basic' ? `
   For "basic" fidelity:
   - Improve metadata.description (1-2 sentences, specific)
   - Add specific tags (not just generic type)
   - Create/improve .md with clean ASCII art
   - Keep single default state
   - Update fidelity field to "basic"
   ` : ''}

   ${targetFidelity === 'detailed' ? `
   For "detailed" fidelity:
   - All "basic" enhancements (if not already done)
   - Add hover state (use {SKILL_ROOT}/../fluxwing-component-creator/templates/state-additions/hover.json)
   - Add focus state (use {SKILL_ROOT}/../fluxwing-component-creator/templates/state-additions/focus.json)
   - Polish ASCII art (smooth alignment, consistent spacing)
   - Add props.examples array (2-3 usage examples)
   - Update fidelity field to "detailed"
   ` : ''}

   ${targetFidelity === 'production' ? `
   For "production" fidelity:
   - All "detailed" enhancements (if not already done)
   - Add disabled state (if applicable for component type)
   - Add error state (if applicable for component type)
   - Complete accessibility metadata:
     - aria-label templates
     - keyboard shortcuts
     - screen reader descriptions
   - Add behavior.keyboardShortcuts (if interactive)
   - Publication-quality ASCII (pixel-perfect alignment)
   - Document edge cases in description
   - Update fidelity field to "production"
   ` : ''}

9. Save NEW versioned files:
   - ./fluxwing/components/${componentId}-v{N+1}.uxm
   - ./fluxwing/components/${componentId}-v{N+1}.md
   - DO NOT overwrite original ${componentId}.uxm

10. Verify JSON is valid
11. Return enhancement summary with version info

Target time: ${targetTime[targetFidelity]} seconds

Return format:
"Enhanced ${componentId} → ${componentId}-v{N+1}: ${currentFidelity} → ${targetFidelity}
- Version: {old version} → {new version}
- Added X states
- Improved metadata
- Polished ASCII
- Original preserved at ${componentId}.uxm"
`
})
```

#### Step 4: Regenerate Screen (If Applicable)

If components belong to a screen, regenerate .rendered.md:

```bash
# Find which screen uses this component
grep -l "${componentId}" ./fluxwing/screens/*.uxm
```

If found, respawn composer to regenerate .rendered.md with enhanced components.

#### Step 5: Report Results

```markdown
# Enhancement Complete ✓

## Components Enhanced

${enhancedComponents.map(c => `
### ${c.id}
- Before: ${c.oldFidelity}
- After: ${c.newFidelity}
- Time: ${c.time}s
- Changes:
  - ${c.changes.join('\n  - ')}
`).join('\n')}

## Total Time: ${totalTime}s

## Screens Updated
${updatedScreens.length > 0 ? updatedScreens.map(s => `- ${s}.rendered.md regenerated`).join('\n') : 'None'}

## Next Steps
1. Review enhanced components: \`ls ./fluxwing/components/\`
2. View updated screen: \`cat ./fluxwing/screens/${screenName}.rendered.md\`
3. Customize as needed
```

## Example Usage

**User:** "Enhance all components in banking-chat to detailed"

**Enhancer:**
1. Finds 6 sketch components
2. Spawns 6 enhancement agents (parallel)
3. Each agent: sketch → detailed (~90s)
4. Regenerates banking-chat.rendered.md
5. Total time: ~120 seconds

**User:** "Make submit-button production-ready"

**Enhancer:**
1. Finds submit-button (detailed fidelity)
2. Spawns 1 enhancement agent
3. Agent: detailed → production (~180s)
4. Updates screen if applicable
5. Total time: ~180 seconds

## Success Criteria

- ✓ Components upgraded to target fidelity
- ✓ All states added as specified
- ✓ ASCII art improved
- ✓ Metadata enriched
- ✓ Screen .rendered.md regenerated (if applicable)
- ✓ All files validate against schema

You are building a progressive enhancement system for maximum flexibility!

Attribution

trabiantrabian
View sourceMore from trabian →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →