Skip to content
SkillScript-led2,708 tokens in use

Trading Skills Navigator

Recommends the workflow, skillset, API profile and setup path that fit a trading goal written in everyday language, in English or Japanese, without running any trades.

7,430 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/trading-skills-navigator

Skill label

measured from its files

What installing Trading Skills Navigator costs

157tokens idle
2,708tokens in use
68,797tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/build_snapshot.py, scripts/intent_benchmark.py, scripts/recommend.py.

Touches

shelldetectednetworkdetectedwrites filesdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter8/15
  • Structure17/25
  • Examples12/15
  • Output15/15
  • Size13/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Good
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 59
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/build_snapshot.py, line 101
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    scripts/recommend.py, line 1210

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance52
  • Community68
  • Maturity36
  • Momentum40

Trading Skills Navigator is the on-ramp to a large toolkit of trading skills and workflows. You describe a goal, for example a 15-minute daily market check or swing trading only when the market is favorable, and it recommends a primary workflow, supporting workflows, the skillset to install and whether the path works without paid API keys.

A deterministic Python recommender reads the repository’s skill index and workflow manifests, or a bundled snapshot when run outside the repository, and the agent narrates the result. It explains and routes only: it never places orders or runs other skills for you.

What You Get

  • A primary workflow with cadence, estimated minutes and API profile, plus ordered secondary workflows
  • A setup bundle listing required, recommended and optional skills to install, with the reason for each
  • A clear statement of whether the whole path works without paid API keys
  • A no-path explanation with suggested skills when no shipped workflow matches the goal

Common Use Cases

  • Asking where to start as a new user of the toolkit
  • Finding which workflows work with no paid data keys
  • Describing a persona such as a dividend investor or part-time swing trader and getting the matching bundle

What Makes It Unique

The routing is deterministic, so the same question gives the same answer in Claude Code and in the web app. It reports ambiguous, fallback and unavailable matches as such, and separates a limited offline alternative from the goal the user asked for. A benchmark of labeled English and Japanese cases checks the routing.

Under The Hood

The agent runs one Python script from the shell with the user’s goal and optional flags, and reads the JSON it prints. The script reads local metadata files, namely the skill index and workflow manifests, or a bundled snapshot file when the repository is not present, and needs PyYAML. It uses no network and no API key. Other bundled scripts rebuild the snapshot and run a routing benchmark, and reference files describe intent routing and setup paths for the web app and Claude Code.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers