Skip to content
SkillScript-led3,409 tokens in use

Institutional Flow Tracker

Screens stocks for quarterly changes in 13F institutional ownership and runs a per-ticker deep dive with top holders and a data reliability grade.

7,427 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/institutional-flow-tracker

Skill label

measured from its files

What installing Institutional Flow Tracker costs

63tokens idle
3,409tokens in use
16,289tokens, 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/analyze_single_stock.py, scripts/data_quality.py, scripts/fmp_client.py, scripts/track_institution_portfolio.py, scripts/track_institutional_flow.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
  • Frontmatter8/15
  • Structure23/25
  • Examples9/15
  • Output15/15
  • Size15/15
  • Resources12/15

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 44
  • Writes files−8

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

    scripts/analyze_single_stock.py, line 468
  • Reads credentials−15

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

    scripts/analyze_single_stock.py, line 501
  • Reaches the network−10

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

    scripts/fmp_client.py, line 33

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

Institutional Flow Tracker uses Financial Modeling Prep data drawn from 13F filings to show how institutional ownership of US stocks changed from one quarter to the next. A screening script lists stocks with the largest changes, and a second script analyzes one ticker over up to eight quarters.

Each result carries a coverage-based reliability grade from A to C, and grade C stocks are left out of screening. The skill describes ownership data and its 45-day reporting lag and gives no investment advice.

What You Get

  • A screened list of stocks with ownership percentage, change in shares held and change in the number of institutions
  • A single-stock report covering up to eight quarters of ownership history
  • The top 20 institutional holders with position changes and a concentration measure
  • A reliability grade A, B or C on every result
  • Markdown reports plus optional JSON output

Common Use Cases

  • Checking whether institutional holders of a stock added or reduced positions last quarter
  • Scanning a sector for stocks with large ownership changes
  • Running a review of portfolio holdings after each 13F filing deadline
  • Looking for a named institution in a stock’s top holders table

What Makes It Unique

Results are graded by coverage: grade A needs a comparable prior quarter and at least 50 filing holders, grade B at least 10, and grade C results are excluded from screening. The skill states its limits openly, including the 45-day filing lag, the exclusion of short positions and the fact that institution-level portfolio tracking is a placeholder that points to outside sources.

Under The Hood

Claude runs Python scripts from the skill folder through the shell, with an FMP API key from the FMP_API_KEY environment variable or a command-line flag. The scripts call the Financial Modeling Prep web API for 13F ownership summaries, compute changes and grades locally, and write Markdown and JSON reports to a reports folder. The skill also points to reference guides on 13F data and how to read the results. Python 3.9 or later and the requests package are needed.

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