agentsclimarketplace

Clearstreet fundamentals deep dive

Skill clear-street/clearstreet-skills/skills/clearstreet-fundamentals-deep-dive

Generate a one-page research brief for a US stock or ETF using the Clear Street API — fundamentals (market cap, P/E, EPS, beta, sector, 52-week range), analyst consensus (rating + price-target distribution), earnings history (estimate vs actual + surprise %), and the latest quarterly income and cash-flow statements. Use when the user asks to "research", "deep-dive", "analyze", or "give me a one-pager on" a single ticker. For multi-name screens use clearstreet-screener; for an earnings calendar use clearstreet-earnings-radar; for free-form questions use clearstreet-omni-research.From its SKILL.md

Install
npx -y skills add clear-street/clearstreet-skills --skill clearstreet-fundamentals-deep-dive

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.3 KB, 438 tokens by cl100k_base, as published. Nobody here has run it

Fundamentals Deep-Dive

Build a single-ticker research brief by joining several Clear Street API endpoints into one markdown page: snapshot, analyst consensus, earnings history, and the latest quarterly statements.

Prerequisites

  • Python 3.9+ (standard library only)
  • CLEARSTREET_API_KEY set in the environment — see the repo README

Quick start

python3 scripts/deep_dive.py NVDA

Usage

deep_dive.py SYMBOL [--quarters N] [--json]
ArgumentDefaultDescription
SYMBOL(required)Ticker (e.g. NVDA) or instrument UUID
--quarters4Number of earnings quarters to display
--jsonoffEmit the raw merged JSON instead of markdown

Examples

AskCommand
"Research NVDA for me"deep_dive.py NVDA
"Deep-dive on Apple, last 8 quarters"deep_dive.py AAPL --quarters 8
"Income statement and cash flow for TSLA"deep_dive.py TSLA

Workflow

  1. Identify the ticker the user is asking about.
  2. Run python3 scripts/deep_dive.py <SYMBOL>.
  3. Present the markdown brief directly — it's formatted for chat, Slack, or a doc. Show only the fields the brief includes; if you add any instrument-identity details, omit option-only fields (expiry / strike) for stocks and ETFs, and don't surface the internal instrument id (UUID).
  4. For free-form follow-ups ("is it a buy?"), chain to clearstreet-omni-research.

See reference.md for endpoint and field details.

Safety

Read-only. The script issues only GET requests and never touches order or position endpoints. Output is informational, not investment advice.

What ships with it: 3 files

15.0 KB alongside SKILL.md, 2 of them executable

scripts/

Gives 0 of the 12 instructions most research analysis skills give in 438 tokens

Counted across 1,213 of the 2,113 authors here whose files we hold, read 2026-09-06

  • Cite sources for every important claimin 47 of 1213, across 38 files
  • Separate facts from inferences and recommendationsin 21 of 1213, across 12 files
  • Write findings to a markdown filein 19 of 1213
  • Label every insight with a confidence levelin 18 of 1213, across 8 files
  • Read product marketing context before asking questionsin 18 of 1213, across 8 files
  • Rank themes by frequency and intensityin 16 of 1213, across 6 files
  • Establish research mode before proceedingin 16 of 1213, across 6 files
  • Segment survey responses by customer tier or tenurein 16 of 1213, across 6 files
  • Categorize support tickets before analyzingin 16 of 1213, across 6 files
  • Weight research sources from the last twelve monthsin 16 of 1213, across 6 files
  • Use at least five data points per segmentin 15 of 1213, across 5 files
  • Extract verbatim quotes for all research findingsin 15 of 1213, across 5 files

Said here and by no other author read

  • Identify the requested ticker symbol
  • Run the deep dive script with the ticker
  • Present the markdown brief directly
  • Omit internal instrument UUIDs
  • Omit option-only fields for stocks and ETFs
  • Chain to omni-research for follow-up questions

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.