agentleFS
davidromeodavidromeo/tradeblocks-skills/CLAUDE.md

tradeblocks-skills

CLAUDE.md3 starsChanged 47 days agoMITView on GitHub

A Claude Code plugin providing guided analysis skills for Option Omega backtests and options trading portfolios. Requires the TradeBlocks MCP server to be running separately. Distributed via the Agent Skills marketplace. Skills are workflow choreographers, not implementations. Each SKILL.md describes a multi-step analysis workflow that invokes MCP tools in sequence. The actual logic lives in the TradeBlocks MCP server (50+ tools for trade queries, simulations, and analysis), which users install separately. Reference files are interpretation guides. Each references/*.md explains how…

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. tradeblocks-org/tradeblocks-skills★ 3100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository11 other files it gives its agents.

The file

We split this CLAUDE.md into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Distinctive:

    No build step — skills are static markdown.

    line 22
  2. Very specific:

    Every skill follows this pattern in its SKILL.md:

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Is

A Claude Code plugin providing guided analysis skills for Option Omega backtests and options trading portfolios. Requires the TradeBlocks MCP server to be running separately. Distributed via the Agent Skills marketplace.

Architecture

.claude-plugin/       Plugin metadata (plugin.json, marketplace.json)
skills/               8 skill directories, each with SKILL.md + references/

Skills are workflow choreographers, not implementations. Each SKILL.md describes a multi-step analysis workflow that invokes MCP tools in sequence. The actual logic lives in the TradeBlocks MCP server (50+ tools for trade queries, simulations, and analysis), which users install separately.

Reference files are interpretation guides. Each references/*.md explains how to read analysis results — thresholds, tables, domain-specific nuance. Skills link to them contextually, not as prerequisites.

Setup

No build step — skills are static markdown. The TradeBlocks MCP server must be installed and running separately.

CI

.github/workflows/ci.yml runs the validate job on every pull request to main and every push to main; branch protection requires it, up to date with main. It validates the plugin and marketplace manifests (claude plugin validate --strict .), validates every skill marketplace.json lists against the Agent Skills specification (agentskills validate from skills-ref), fails on relative Markdown links to missing files (.github/scripts/check-links.mjs), and runs npm test when package.json declares it.

Skill Structure

Every skill follows this pattern in its SKILL.md:

---
name: skill-id
description: one-liner + trigger conditions
compatibility: MCP server requirements
metadata: author, version
---

Followed by: Prerequisites → Process (numbered steps with specific MCP tool calls) → Interpretation Reference → Related Skills.

Plugin Distribution

  • .claude-plugin/plugin.json — name, version, author for the plugin itself
  • .claude-plugin/marketplace.json — lists all skills, sets strict: true, defines marketplace entry
  • Install path: /plugin marketplace add tradeblocks-org/tradeblocks-skills then /plugin install tradeblocks@tradeblocks-skills

Domain Concepts

  • Blocks — named strategy containers in the DuckDB database. Most tools require a blockId from list_blocks.
  • Strategy profiles — persistent metadata about a strategy's structure, entry filters, and expected regimes. Created by profile_strategy, consumed by analysis skills.
  • Curve-fit detection — a first-class concern, especially in DC analysis. Multiple steps dedicated to identifying overfitting via walk-forward efficiency, parameter sensitivity, and out-of-sample degradation.
  • Tail correlation — portfolio/risk skills distinguish normal vs tail correlation (Kendall's tau, joint tail dependence) because trading returns violate Gaussian assumptions.

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.