agentleFS
hunthung-codehunthung-code/fashion-director/skills/trend-intelligence/SKILL.md

trend-intelligence

Skill4 starsChanged 5 months agoMITView on GitHub

Real-time fashion and lifestyle trend scanning powered by WebSearch. Produces seasonal trend reports, micro-trend alerts, and runway analysis summaries. Trigger phrases: "趨勢掃描" / "最新風向" / "這季流行什麼" / "runway report" / "trend report" / "市場趨勢" / "現在流行" / "macro trend" / "micro trend" / "WGSN style report" / "trend brief" Also auto-invoked by creative-direction (Step 2) to anchor visual concepts. Run searches across these source categories: Runway & Editorial - [season] [category] runway trends [year] — Vogue Runway, WWD, Business of…

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Run searches across these source categories:

    line 29
  2. Distinctive:

    Run at minimum 4 searches before drafting.

    line 44
  3. Distinctive:

    If geography focus is Asia-Pacific, prioritize Korean / Japanese / Taiwanese market signals — Western-centric reports often lag 1–2 seasons …

    line 88

≈ “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

trend-intelligence

Real-time fashion and lifestyle trend scanning powered by WebSearch. Produces seasonal trend reports, micro-trend alerts, and runway analysis summaries.

When to invoke

Trigger phrases: "趨勢掃描" / "最新風向" / "這季流行什麼" / "runway report" / "trend report" / "市場趨勢" / "現在流行" / "macro trend" / "micro trend" / "WGSN style report" / "trend brief"

Also auto-invoked by creative-direction (Step 2) to anchor visual concepts.

What this skill produces

  1. Seasonal Macro Brief — 3–5 macro trend pillars for current/upcoming season with evidence
  2. Micro-Trend Radar — fast-moving signals (3–6 months horizon) with source citations
  3. Category-Specific Trend Sheet — drill into one style vertical (tech-wear / luxury / sportswear etc.)
  4. Competitive Signal Report — what key brands are pushing right now

Process

Step 1 — Scope Definition

Clarify before searching:

  • Style category (menswear / womenswear / luxury / sportswear / street / tech-wear / unisex)
  • Geography focus (global / Asia-Pacific / Europe / North America)
  • Time horizon (current season SS/FW + next season preview)
  • Price tier (mass / contemporary / premium / luxury / ultra-luxury)

Step 2 — Multi-Source WebSearch

Run searches across these source categories:

Runway & Editorial

  • [season] [category] runway trends [year] — Vogue Runway, WWD, Business of Fashion
  • [brand] [season] collection key pieces [year]

Consumer & Social Signal

  • [category] trending [geography] [year] — Pinterest Predicts, Google Trends fashion
  • TikTok fashion trend [category] [year]

Industry Reports

  • McKinsey State of Fashion [year] (annual)
  • [category] market trend report [year]
  • sustainable fashion trend [year] (if relevant)

Run at minimum 4 searches before drafting. Cite every claim.

Step 3 — Trend Synthesis

Organize findings into this structure:

## [Season/Year] Trend Brief: [Category]

### Macro Pillars (3–5)
Each pillar:
- Pillar Name: [memorable label]
- Signal: [what you're seeing across runway / retail / social]
- Evidence: [2–3 specific examples with sources]
- Brand Window: [how this brand can enter / what to avoid]
- Shelf Life: [emerging / building / peak / fading]

### Micro-Trend Radar
Fast-moving items to watch (3–6 month window):
- [Item / silhouette / color / material] — Signal: [where it's appearing] — Risk: [fad vs. staying power]

### Key Brand Movements
What 3–5 relevant brands are pushing this season:
- [Brand]: [what they're doing and why it matters]

### Macro Context
1–2 cultural / economic forces shaping the season:
- [Force]: [how it translates to product / aesthetic choices]

### Watch List (Next Season Preview)
2–3 signals that will likely build for next season.

Step 4 — Brand Filtering (if brand config exists)

Cross-reference findings with brand's established aesthetic and rejected territory. Flag:

  • ✅ Trends that align with brand DNA
  • ⚠️ Trends that require careful interpretation
  • ❌ Trends to actively avoid (competitor territory or off-brand)

Rules

  • Never cite trend names from memory alone — verify with WebSearch that the term is currently being used in the industry.
  • Date all searches. Fashion trends expire fast; a report from 6+ months ago is noise, not signal.
  • Distinguish macro (2–3 year arc) from micro (1–2 season window). Conflating them misleads clients.
  • If geography focus is Asia-Pacific, prioritize Korean / Japanese / Taiwanese market signals — Western-centric reports often lag 1–2 seasons on AP adoption.
  • 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.