agentleFS
makeevmakeev/alphai-claude-skills/skills/insider-radar/SKILL.md

insider-radar

Skill1 starsChanged 36 days agoMITView on GitHub

Scan SEC Form 4 insider trades for a ticker, a watchlist or the whole market using the AlphAI MCP — open-market buys, cluster buying by several insiders, and discretionary sales told apart from pre-planned 10b5-1 ones. Use when the user asks about "insider buying", "insider selling", "Form 4 activity", "who's buying <ticker>", "are insiders buying", or wants an insider-activity sweep.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Single ticker: Call alphai_insider_news(ticker="<SYM>").

    line 16
  2. Very specific:

    Watchlist: Call alphai_insider_news(ticker=...) once per name.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Insider radar

Surface what company insiders do with their own stock: SEC Form 4 trades by officers, directors and 10% owners. AlphAI turns each filing into a relevance-scored news row with a structured insider block (side, shares, total_value_usd, is_10b5_1, role, transaction_date, filed_at), so the numbers come from the filing, not from a press rewrite.

Steps

  1. Single ticker. Call alphai_insider_news(ticker="<SYM>"). If the user wants only the strongest signal, raise the floor with min_relevance=8.
  2. Discretionary trades only. A 10b5-1 sale was scheduled months earlier and carries no timing decision. When the user asks "is anyone choosing to sell or buy", pass is_10b5_1=false to drop planned trades.
  3. Cluster buying. For "are insiders buying" across a name or the market, call alphai_insider_clusters() (or symbol="<SYM>"): issuers where several different insiders bought on the open market in one run. IPO/PIPE allocations, ESPP and plan lots are already filtered out of the default open_market view. Free accounts reach 30 days back, Basic and Pro 90.
  4. Watchlist. Call alphai_insider_news(ticker=...) once per name. If the user gave none, call alphai_insider_news() unfiltered for the broad tape.
  5. Time-box on request. For "this week" / "since earnings", pass from_date (ISO, UTC). Paginate with cursor only if they ask for more.

Output

  • Notable buys — open-market purchases first: ticker · who/role · size · relevance. These are what most users actually want.
  • Cluster buying — if alphai_insider_clusters found any: ticker · number of independent buyers · total · the window.
  • Notable sells — say whether each is discretionary or under a 10b5-1 plan (is_10b5_1), and the seller's role.
  • Read — one line: leaning accumulation, distribution, or just routine?

Guardrails

  • An insider sale is not automatically bearish (taxes, diversification, scheduled plans). Say what the filing shows; don't over-read it.
  • One filing can span several tranches sharing a row — report the event, not a count of line items.
  • filed_at can be days after transaction_date; say which date you mean.
  • AlphAI does not carry fund-holdings filings (13F, 13G, 13D). If the user asks what a fund owns, say so plainly; press coverage of a stake may still turn up via alphai_news_search(query="<fund> stake <company>").
  • Lead with relevance_score; "no notable insider activity in the window" is a valid, useful answer.
  • News, not advice.

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.