agentleFS
Sign inStart free
aman-bhandariaman-bhandari/claude-code-agent-skills-framework/.claude/skills/trend-scout/SKILL.md

trend-scouting

Skill0 starsChanged 7 months agoMITView on GitHub

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.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When checking curriculum alignment (/system-check)

    line 15
  2. Distinctive:

    Search for shifts in requirements vs.

    line 37
  3. Distinctive:

    Always connect findings to the student's learning path.

    line 71
  4. Distinctive:

    Keep digest to 5-10 bullet points.

    line 72

≈ “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 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

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.

Check your setup, free