agentleFS
hunthung-codehunthung-code/fashion-director/skills/style-specialist/SKILL.md

style-specialist

Skill4 starsChanged 5 months agoMITView on GitHub

Routes to the appropriate style agent based on detected category, then produces a style-specific creative brief. Handles multi-category briefs by combining perspectives. Trigger phrases: "男裝方向" / "女裝建議" / "奢侈品策略" / "科技穿搭" / "運動風格" / "街頭潮流" / "這個品牌的風格定位" / "style brief" / "我的客戶做 [category]" / "menswear" / "womenswear" / "luxury" / "sportswear" / "streetwear" / "tech fashion" Read user message and context for style category signals: Multi-category: If 2+ categories are present (e.g., "luxury sportswear" or "tech + street"), activate both…

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read user message and context for style category signals:

    line 11
  2. Distinctive:

    Multi-category: If 2+ categories are present (e.g., "luxury sportswear" or "tech + street"), activate both agents and synthesize their …

    line 22
  3. Distinctive:

    Unknown category: Default to asking one clarifying question: "這個品牌最主要的客群是誰?他們穿這個去哪裡?" — the answer usually reveals the category.

    line 24
  4. Distinctive:

    If single category: output the agent's style brief directly.

    line 42
  5. Distinctive:

    If multi-category: synthesize into a hybrid brief, clearly marking which elements come from which tradition.

    line 43
  6. Distinctive:

    Add a brief "Category Pitfalls" section — the 2–3 most common mistakes brands make in this space.

    line 46
  7. Distinctive:

    Never assume category from brand name alone.

    line 69

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

style-specialist

Routes to the appropriate style agent based on detected category, then produces a style-specific creative brief. Handles multi-category briefs by combining perspectives.

When to invoke

Trigger phrases: "男裝方向" / "女裝建議" / "奢侈品策略" / "科技穿搭" / "運動風格" / "街頭潮流" / "這個品牌的風格定位" / "style brief" / "我的客戶做 [category]" / "menswear" / "womenswear" / "luxury" / "sportswear" / "streetwear" / "tech fashion"

Detection Logic

Read user message and context for style category signals:

Signal in messageRoute to agent
tech / wearable / functional / 科技感 / 戶外機能tech-wear
男裝 / menswear / 西裝 / 男士 / tailoringmenswear
女裝 / womenswear / 女士 / feminine / 輪廓womenswear
奢侈品 / luxury / 精品 / heritage / 高端 / prestigeluxury
運動 / sport / athletic / athleisure / performancesportswear
街頭 / street / hype / 潮牌 / drop / limited / collabstreet-hype

Multi-category: If 2+ categories are present (e.g., "luxury sportswear" or "tech + street"), activate both agents and synthesize their inputs. Flag the tension points explicitly.

Unknown category: Default to asking one clarifying question: "這個品牌最主要的客群是誰?他們穿這個去哪裡?" — the answer usually reveals the category.

What this skill produces

  1. Style Routing Notice — which agent(s) were activated and why
  2. Category Context Sheet — market overview, key players, aesthetic territory for this category
  3. Style Brief — from the activated agent's perspective, tailored to the specific brand/project
  4. Category Pitfalls — common mistakes brands make in this space

Process

Step 1 — Category Detection

Parse user input. If ambiguous, ask the one clarifying question above.

Step 2 — Agent Activation

Hand off to the appropriate agent(s) with full context. The agent returns its perspective.

Step 3 — Synthesis

If single category: output the agent's style brief directly. If multi-category: synthesize into a hybrid brief, clearly marking which elements come from which tradition.

Step 4 — Pitfall Check

Add a brief "Category Pitfalls" section — the 2–3 most common mistakes brands make in this space.

Output Format

## Style Brief: [Brand/Project Name]
**Category**: [detected category / hybrid]
**Activated Agent(s)**: [agent names]

### Category Context
[2–3 sentences on the current state of this market]

### Style Direction
[Agent-specific brief: aesthetic pillars, reference universe, what to own]

### Category Pitfalls
- [Pitfall 1]: [why it kills brands in this space]
- [Pitfall 2]: ...
- [Pitfall 3]: ...

Rules

  • Never assume category from brand name alone. "Nike" could be sportswear OR street-hype depending on the campaign.
  • Multi-category briefs must name the tension: "luxury × streetwear creates a contradiction around exclusivity — here is how to resolve it."
  • Output in the user's language (繁中 / EN follow context).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.