agentleFS
tellmefrankietellmefrankie/ai-investment-skills/investment-briefing-agent/SKILL.md

investment-briefing-agent

Skill14 starsChanged 6 months agoMITView on GitHub

A battle-tested multi-wave investment briefing system that generates comprehensive market analysis using real-time data. Built from 6+ months of live portfolio management experience. Runs a 9-wave analysis pipeline to produce institutional-grade investment briefings: Every analysis enforces these rules automatically: - No narrative repetition — each run uses fresh data - Numbers over narratives — "P/C 0.55, real call 28%" not "bullish" - Cross-verification required — 2+ sources for any price/claim - Sell checklist — no panic sells, check if bottom,…

1 other project uses a version of this.

Adopted by

Most recently taken up by

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:

    Every analysis enforces these rules automatically:

    line 21
  2. Distinctive:

    No narrative repetition — each run uses fresh data

    line 22
  3. Distinctive:

    Full bundle — $29 one-time: All 9 waves + Anti-Narrative Harness + all skills below → https://jaehyunpark.gumroad.com/l/tcyahy

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Investment Briefing Agent

A battle-tested multi-wave investment briefing system that generates comprehensive market analysis using real-time data. Built from 6+ months of live portfolio management experience.

What it does

Runs a 9-wave analysis pipeline to produce institutional-grade investment briefings:

  1. Macro Analysis — S&P 500, Nasdaq, VIX, yields, oil, DXY, Fed signals
  2. Sector Rotation — All 11 S&P sectors, identify leaders/laggards
  3. Technical Scanner — RSI, SMA (20/50/200), MACD, support/resistance for each holding
  4. News Sweep — 48h news, earnings, analyst changes, insider activity per ticker
  5. Opportunity Finder — New swing trade candidates ranked by expected value
  6. Critic Review — Adversarial review of all signals, counter-evidence search
  7. Portfolio Simulation — Scenario modeling (bull/base/bear) with probabilities
  8. Deep Connections — Cross-asset correlations, hidden relationships
  9. Meta-Critic — Final synthesis and action plan

Anti-Narrative Harness (Built-in)

Every analysis enforces these rules automatically:

  • No narrative repetition — each run uses fresh data
  • Numbers over narratives — "P/C 0.55, real call 28%" not "bullish"
  • Cross-verification required — 2+ sources for any price/claim
  • Sell checklist — no panic sells, check if bottom, verify with critic

Configuration

Set your portfolio in the prompt:

Run investment briefing for my portfolio:
- AAPL: 100 shares @ $175
- NVDA: 50 shares @ $120
- TSLA: 30 shares @ $245

Include macro, sector, technicals, news, and critic review.
Focus on: earnings catalysts, options flow anomalies, sector rotation signals.

Requirements

  • WebSearch tool access (for real-time market data)
  • Works best with Claude Opus for critic/meta-critic waves

Pricing

Free tier: Macro + Sector analysis only (waves 1-2) Full bundle — $29 one-time: All 9 waves + Anti-Narrative Harness + all skills below → https://jaehyunpark.gumroad.com/l/tcyahy

Author

Built by a CTO who runs this system daily for real portfolio management. Not a demo — this is production code refined over 6 months of live trading decisions.

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.