Earningswhispers

What it does

When your agent uses it

• Business, Finance & HR work in your project

Example prompts

• “Use the earningswhispers skill to earning transcripts completos via API publica de EarningsWhispers”
• “/earningswhispers”

Requirements

• Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Solo ultimo transcript: La API devuelve solo el mas reciente. No hay historico completo.
2. 2Sin search endpoint: No hay forma de descubrir tickers disponibles programaticamente.
3. 3Sin autenticacion Google/Facebook: La pagina web requiere login; la API no.
4. 4Cobertura no exhaustiva: ~33,500 stocks trackeados, pero no todos tienen transcripts (depende de si hacen earnings calls publicos).
5. 5Sin datos historicos: El parametro ccid no habilita acceso a transcripts anteriores.

What it can do on your machine

Read from SKILL.md and the folder at commit 5156f81. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 2 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • earningswhispers.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Earningswhispers loads about 1.9k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 53 tokens; SKILL.md has 603 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~53

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from gauss314/skills at commit 5156f81, republished under its MIT licence (© gauss314). 603 words, ~1,852 tokens.

name

earningswhispers

description

Earnings transcripts completos via API publica de EarningsWhispers. Sin anti-bot, sin auth. 33,500+ stocks globales trackeados. Test ok en mas de 60 tickers, AAPL, MSFT, GGAL, SHEL, TM, VALE etc

license

MIT

metadata.category

finanzas, transcripts, earnings, api, global

metadata.language

es

metadata.source

https://www.earningswhispers.com/

GET https://www.earningswhispers.com/api/conferencecalls?t={TICKER}

Respuesta tipica (~50 KB para GGAL, ~90 KB para AAPL):
[{
  "ccid": 132,
  "ticker": "GGAL",
  "company": "Grupo Financiero Galicia S.A.",
  "ccDate": "2026-05-14T11:00:00",
  "ccYear": 2026,
  "ccQtr": 1,
  "speakers": "JSON string con array de speakers",
  "speakerMap": "JSON string con mapping de nombres y cargos",
  "summary": null,
  "aiSummary": null,
  "status": ""
}]

# Si devuelve datos, tiene transcript
curl "https://www.earningswhispers.com/api/conferencecalls?t=AAPL"

# Si devuelve [] (array vacio), no tiene transcript
curl "https://www.earningswhispers.com/api/conferencecalls?t=XXXX"

python -c "from curl_cffi import requests; print('OK')"

# Cualquier ticker global
python ew_cli.py get AAPL
python ew_cli.py get SHEL --json
python ew_cli.py batch MSFT,GOOG,AMZN --json
python ew_cli.py info GGAL

# Lista de tickers de ejemplo
python ew_cli.py list

from ew_client import EarningsWhispersClient

client = EarningsWhispersClient()

# Transcript de cualquier empresa global
tr = client.get_transcript("AAPL")
print(tr.company)                    # "Apple, Inc."
print(tr.prepared_remarks[:500])

# Como dict (para JSON)
data = tr.to_dict()

# Batch
results = client.get_transcripts_batch(["MSFT", "GOOG", "AMZN"])

tr = client.get_transcript("NVDA")
tr.company          # "NVIDIA Corp."
tr.date             # "2026-05-20T16:30:00"
tr.quarter_label    # "Q1"
tr.year             # 2027 (fiscal year)
tr.prepared_remarks # Texto de la presentacion
tr.qa_section       # Preguntas y respuestas
tr.summary          # Resumen ejecutivo (puede ser None)
tr.ai_summary       # Resumen AI (puede ser None)

© gauss314, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in skills/earningswhispers of gauss314/skills.

• SKILL.md
• references/REFERENCES.md
• scripts/ew_cli.py
• scripts/ew_client.py

Open the folder on GitHubat commit 5156f81