agentsclimarketplace
Sign in

Clearstreet earnings radar

Skill clear-street/clearstreet-skills/skills/clearstreet-earnings-radar

Pull a forward-looking earnings calendar — every US-listed company reporting between two dates, with EPS and revenue estimates, optionally annotated with each name's prior-quarter surprise. Use when the user asks "who reports this week?", "earnings calendar for [dates]", or "any big prints tomorrow?". For a single-ticker drill-down, chain to clearstreet-fundamentals-deep-dive; for analyst views, use clearstreet-omni-research.From its SKILL.md

Install
npx -y skills add clear-street/clearstreet-skills --skill clearstreet-earnings-radar

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, 518 tokens by cl100k_base, as published. Nobody here has run it

Earnings Radar

Show a forward-looking earnings calendar, ranked per day by estimated revenue, optionally annotated with each company's prior-quarter surprise.

Prerequisites

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

Quick start

# Reporting today through Friday, US-listed, top 30 by estimated revenue
python3 scripts/radar.py --days 5 --currency USD --top 30

Usage

radar.py [--days N | --from YYYY-MM-DD --to YYYY-MM-DD]
         [--currency USD] [--top N] [--filter-symbols S1,S2]
         [--include-prior-surprise] [--json]
FlagDefaultDescription
--days5Forward window from today
--from / --to—Explicit date window (overrides --days)
--currency(none)Filter by reporting currency (e.g. USD)
--top40Max rows per date, ranked by revenue estimate
--filter-symbols(none)Comma-separated ticker whitelist
--include-prior-surpriseoffAdd last quarter's EPS/revenue surprise (one extra call per row)
--jsonoffRaw JSON output

Examples

AskCommand
"Who reports this week?"radar.py --days 5 --currency USD
"Earnings calendar next 14 days"radar.py --days 14
"Big prints tomorrow?"radar.py --from 2026-06-18 --to 2026-06-18 --top 20

Workflow

  1. Translate the user's date phrase into a --days value or a --from/--to window.
  2. Run radar.py.
  3. Present the returned markdown.
  4. For a single-ticker drill-down, chain to clearstreet-fundamentals-deep-dive.

See reference.md for endpoint and field details.

Safety

Read-only. Estimates are consensus figures and subject to change. Output is informational, not investment advice.

What ships with it: 3 files

12.0 KB alongside SKILL.md, 2 of them executable

scripts/

Gives 0 of the 12 instructions most research analysis skills give in 518 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

  • Translate user date phrases into date arguments
  • Run radar.py with appropriate flags
  • Present the returned markdown
  • Chain to fundamentals-deep-dive for single-ticker drill-downs

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.