Clearstreet omni research

Skill clear-street/clearstreet-skills/skills/clearstreet-omni-research

Send a prompt to Omni, Clear Street's financial AI copilot, and return the answer. Omni can draw on market data, fundamentals, analyst consensus, earnings, news, and — when entitled — the user's own positions and orders. Two modes: Instant for fast answers, Deep Insights for more reasoned analysis. Use for free-form questions with market context — "ask Omni…", "what does Omni think about…", "compare X vs Y", "summarize today's market". For structured single-ticker output use clearstreet-fundamentals-deep-dive; for filtered lists use clearstreet-screener.From its SKILL.md

Install

npx -y skills add clear-street/clearstreet-skills --skill clearstreet-omni-research

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

3.7 KB, 815 tokens by cl100k_base, as published. Nobody here has run it

Omni Research

Ask Omni a question and get the answer back in the terminal. The script creates a thread, polls until the response completes, and prints Omni's markdown.

Prerequisites

Python 3.9+ (standard library only)
CLEARSTREET_API_KEY set in the environment — see the repo README
For portfolio-aware questions, the API key needs an omni.account_data entitlement on a trading account. Without it, Omni answers general market questions but can't see your positions or orders.

Quick start

# Fast answer
python3 scripts/ask_omni.py "What is NVDA's forward P/E and analyst consensus?"

# Deeper single-ticker analysis (long-running, ~5 min) — only when explicitly requested
python3 scripts/ask_omni.py --deep --ticker NVDA "Give a thorough qualitative view on NVDA."

# Show Omni's reasoning trace
python3 scripts/ask_omni.py --thinking "Top 5 tech stocks reporting earnings this week"

Usage

ask_omni.py [--deep --ticker SYMBOL] [--thinking] [--thread THREAD_ID]
            [--account-id ID] [--capabilities CAP1,CAP2] [--timeout SECS] [--json]
            "your question"

Flag	Default	Description
`prompt`	(required)	Free-form question
`--deep`	off	Deep Insights mode — deeper reasoning on one ticker. Long-running (~5 min) and requires `--ticker`. Use only when the user explicitly asks for a deep/thorough analysis.
`--ticker`	(none)	Ticker the deep analysis targets, e.g. `NVDA` (required with `--deep`)
`--thinking`	off	Print Omni's tool-use trace before the answer
`--thread`	(none)	Continue an existing thread
`--account-id`	env / auto	`CLEARSTREET_ACCOUNT_ID`, else the first account the key sees
`--capabilities`	(none)	`PREFILL_ORDER`, `OPEN_CHART`, `OPEN_SCREENER`, `OPEN_ENTITLEMENT_CONSENT`
`--timeout`	120 / 600	Seconds to wait (120 instant, 600 deep)
`--json`	off	Full response payload including structured actions

Examples

Ask	Command
"Ask Omni about NVDA's outlook"	`ask_omni.py "What's the outlook for NVDA?"`
"Give me a thorough view on AAPL"	`ask_omni.py --deep --ticker AAPL "Thorough view on AAPL for a long-term hold"`
"Summarize today's market"	`ask_omni.py "Summarize today's US market — winners, losers, notable names"`

Workflow

Pass the user's question as the prompt.
Default to Instant. Only use --deep (with --ticker SYMBOL) when the user explicitly asks for a deep or thorough analysis — it's a single-ticker, long-running task (~5 min), so tell the user it will take a few minutes before you start it.
Print the markdown response and mention the thread_id for follow-ups.
Replace any [SYMBOL](ticker:SYMBOL) links with plain ticker text — those render only in Clear Street apps.

See reference.md for the thread/response lifecycle and payload shape.

Safety

This skill does not place orders. Even with PREFILL_ORDER in capabilities, Omni only suggests order parameters — execution requires a separate, explicit API call. Output is informational, not investment advice.

What ships with it: 3 files

13.0 KB alongside SKILL.md, 2 of them executable

scripts/

ask_omni.pyruns6.6 KB
clearstreet_client.pyruns3.8 KB

reference.md2.6 KB

Gives 0 of the 12 instructions most research analysis skills give in 815 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

Pass user question as prompt
Default to Instant mode
Use deep mode only when explicitly requested
Require ticker symbol for deep mode
Notify user of long wait time for deep mode
Print markdown response

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.