Skip to content
SkillMixed3,759 tokens in use

Portfolio Manager

A portfolio review workflow that reads holdings from the Alpaca MCP Server or a local CSV, then reports allocation, diversification, risk, position-level views and rebalancing candidates.

7,428 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/portfolio-manager

Skill label

measured from its files

What installing Portfolio Manager costs

68tokens idle
3,759tokens in use
47,762tokens, 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 Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/check_alpaca_connection.py, scripts/normalize_alpaca_positions.py, scripts/reconcile_positions.py, scripts/review_csv.py.

Touches

shelldetectednetworkdetectedwrites filesdetectedcredentialsdetected

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
  • Frontmatter12/15
  • Structure23/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources11/15

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 →
Needs attention
  • Runs shell commands−5

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

    SKILL.md, line 66
  • Writes to a key folder or startup file−25

    writes to a key folder or a shell startup file

    references/alpaca-mcp-setup.md, line 76
  • Writes to a key folder or startup file−25

    writes to a key folder or a shell startup file

    references/alpaca-mcp-setup.md, line 77
  • Writes to a key folder or startup file−25

    writes to a key folder or a shell startup file

    references/alpaca-mcp-setup.md, line 78
  • Reaches the network−10

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

    scripts/check_alpaca_connection.py, line 27
  • Reads credentials−15

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

    scripts/check_alpaca_connection.py, line 37
  • Writes to a key folder or startup file−25

    writes to a key folder or a shell startup file

    scripts/check_alpaca_connection.py, line 54
  • Writes to a key folder or startup file−25

    writes to a key folder or a shell startup file

    scripts/check_alpaca_connection.py, line 55
  • Writes files−8

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

    scripts/normalize_alpaca_positions.py, line 99

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

Portfolio Manager analyzes an investment portfolio in seven steps. It fetches account equity, positions and history from Alpaca through the MCP server, or through a REST fallback, enriches each holding with market data, and examines allocation, concentration, risk metrics and performance. It then reviews the largest positions and lists rebalancing candidates ranked by priority.

A limited offline mode reviews a CSV of holdings or saved Alpaca positions JSON with no credentials and reports gross allocation and unrealized profit and loss only. The report carries an informational-only disclaimer, and the skill never places orders.

What You Get

  • A Markdown portfolio report with allocation, diversification, risk and performance sections
  • Per-position reviews for the top holdings with a stated action label
  • Rebalancing candidates ranked by priority with a rationale each
  • An offline CSV review with gross allocation and per-position unrealized profit and loss
  • Holdings reconciliation reports that compare broker and memory snapshots

Common Use Cases

  • Reviewing allocation and sector concentration across a brokerage account
  • Checking a paper trading account through the connection check script
  • Running a limited review of a CSV export without any credentials
  • Reconciling broker positions with a saved snapshot before a weekly allocation review

What Makes It Unique

It supports three data routes in one skill: the Alpaca MCP Server, a REST fallback for scheduled jobs that do not expose MCP tools, and an offline CSV mode. It tells Claude to compute exposure against equity so a margin-funded account does not look benign, and it includes a reconciliation gate that stops the review when snapshot completeness or freshness cannot be established. Related skills handle dividend review monitoring and tax planning.

Under The Hood

Claude uses the Alpaca MCP tools for account info, positions and portfolio history when they are connected, and can fall back to the Alpaca REST API using your Alpaca key, secret and paper-or-live setting from environment variables. The connection check script runs from the shell, prints a redacted diagnostic and places no orders. Claude can also use web search for fundamentals and news on holdings. The CSV and reconciliation scripts read local files and write JSON and Markdown reports, and the final analysis report is saved to the repository root. The setup reference suggests that you append your Alpaca key and secret to a shell startup file such as .bashrc and create a config file under your home folder; that is a step for you to take and the scripts do not do it. The connection check script only prints those same suggestions in its error message. Personal holdings stay on your machine in the offline mode.

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