# Trend Scouting

> Actively scans the AI engineering landscape using WebSearch for trending repos, blogs, job postings, new tools, and framework releases. Triggers on /trends, during weekly reflections, or when checking industry relevance. Surfaces findings relevant to current topic and flags curriculum adjustments.

- Skill: `aman-bhandari/trend-scouting` (Agent Skill)
- Install (CLI): `npx skillmds@latest add aman-bhandari/trend-scouting`
- Raw SKILL.md: https://api.skillmd.com/api/skills/aman-bhandari/trend-scouting/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: aman-bhandari (https://skillmd.com/u/aman-bhandari)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/aman-bhandari/trend-scouting

---


# Trend Scout -- Industry Intelligence

Actively scan the AI engineering landscape to keep the learning system current and the student hireable.

## Trigger

- `/trends` or "what's trending"
- During weekly reflection (`/reflect`)
- When checking curriculum alignment (`/system-check`)

## Execution

1. **Search these sources using WebSearch:**

   **GitHub Trending:**
   - Python repos: trending daily/weekly
   - AI/ML/agents/LLM tooling repos
   - MCP servers and clients

   **Key Blogs (check latest posts):**
   - Simon Willison (simonwillison.net)
   - Chip Huyen (huyenchip.com)
   - Hamel Husain (hamel.dev)
   - Lilian Weng (lilianweng.github.io)
   - swyx / Latent.Space (latent.space)
   - Anthropic engineering blog
   - LangChain blog

   **Job Market:**
   - "AI engineer" recent job postings -- what skills are listed
   - Search for shifts in requirements vs. our baseline data

   **New Releases:**
   - Claude API / Claude Code updates
   - LangGraph, CrewAI, OpenAI Agents SDK releases
   - New MCP servers worth knowing about
   - Python ecosystem updates relevant to AI engineering

2. **Filter for relevance:**
   - Is this relevant to the student's current topic?
   - Is this something the market demands? (cross-reference with market data in memory)
   - Is this a trend (sustained adoption) or hype (Twitter excitement, no production use)?

3. **Output digest:**
   ```
   TREND SCOUT -- {date}

   Current topic: {sprint name}

   Relevant to your learning:
   - [finding] -- why it matters, what to do about it

   Market signals:
   - [signal] -- implication for your path

   Curriculum adjustment needed?
   - [yes/no + specific recommendation]
   ```

4. **Persist:** Save significant findings to memory. Update `knowledge/wiki/career/market-trends.md` if wiki exists.

## Rules

- Distinguish trends from hype. Look for: production adoption, hiring signals, major company backing.
- Always connect findings to the student's learning path.
- Keep digest to 5-10 bullet points. Concise, not exhaustive.
- Source everything with URLs.
- Flag curriculum adjustments immediately -- don't wait for Friday.

## Market Baseline (from research)

See memory file `reference_market_requirements.md` for the baseline data:
- Python 82.5%, RAG 35.9%, Agents 14.4% and growing
- 93.1% of roles need skills beyond GenAI
- Evaluation/observability is the hiring differentiator