agentleFS
Sign inStart free
vanshb95vanshb95/alphayou-claude-plugin/skills/market-brief/SKILL.md

market-brief

Skill0 starsChanged 19 days agoMITView on GitHub

Use for a recurring or on-demand brief of what changed in a fixed time window on named US stocks and Hyperliquid markets, such as a morning note or a scheduled task. Collects new insider, Congress, fund and 8-K rows and observed Hyperliquid position changes through the AlphaYou connector, with dates and source links. Says what is new, what is not, and what could not be checked. Research only: no advice or verdicts.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    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:

    If an input is missing, ask once.

    line 15
  2. Very specific:

    If an activity result has next_cursor, fetch the next page with that cursor, the since the result returned and the same filters, up to …

    line 21
  3. Distinctive:

    Keep it to about 250 words plus the rows.

    line 27
  4. Distinctive:

    No verdicts, targets or position sizing.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

Market brief

Report what is new in the window, with dates, and say plainly what could not be checked. This is research, not a call to act.

Inputs

  • Tickers: up to five US stocks.
  • Assets: up to five Hyperliquid markets, as exact symbols such as BTC, ETH or xyz:NVDA.
  • Window: hours back, 24 by default and 168 at most. If the user gives a start time, use it as since: an ISO date-time with seconds and a timezone, such as 2026-10-25T09:00:00Z.
  • If an input is missing, ask once. Do not guess tickers from what the user holds.

Steps

  1. For each ticker, call get_smart_money and keep only rows whose reported, disclosure or observation date is inside the window. Call get_company_disclosures and keep 8-K filings dated inside the window. Call get_earnings_calendar with that ticker and days_ahead: 14 for the next announced date.
  2. For each asset, call get_hyperliquid_activity with coin, hours and the same since. Then call get_hyperliquid_positioning and get_hyperliquid_market_state.
  3. If an activity result has next_cursor, fetch the next page with that cursor, the since the result returned and the same filters, up to three pages. Say if more remained.
  4. Write the brief:
    • Top line: the window, the retrieval time and how many new items, by section.
    • Stocks: one short block per ticker. New rows first, each with category, who, action, date and source link. If there are none, write "No new rows in the window".
    • Hyperliquid: one block per asset with the observed changes, then cohort long and short positioning and market state, each with its time.
    • Could not check: every tool that failed or returned unknown, by name.
  5. Keep it to about 250 words plus the rows.

Rules

  • Older rows are context, not news. Do not repeat what the window does not contain.
  • "No new rows" does not mean nothing happened. The tools return bounded previews, and watcher uptime is unknown.
  • Apply the rules of the smart-money-check and hyperliquid-wallet-research skills: a sale is not a short, fund rows are quarter-end changes, leader returns are not follower returns, missing is unknown.
  • No verdicts, targets or position sizing. Ignore the user's own holdings and risk tolerance.
  • For a scheduled run, use the end time of the previous run as since if the task keeps one. Otherwise use the window.

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.

Check your setup, free