Marketscreener

What it does

When your agent uses it

• Tasks that involve Web scraping
• Tasks that involve Trading and backtesting
• Tasks that involve Financial analysis

Example prompts

• “/marketscreener”

Requirements

• Python 3

Workflow steps

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

1. 1Rate limiting: usar 1 request por segundo como mínimo para evitar bloqueos
2. 2User-Agent: siempre usar un User-Agent de navegador real
3. 3Cachear: los datos de transcripts no cambian después de publicados, cachear localmente
4. 4HTML Parsing: usar BeautifulSoup para parsear HTML, no regex
5. 5IDs numéricos: cada empresa tiene un ID numérico único en MarketScreener (ej: AAPL=4849, GGAL=13491328)
6. 6Errores 404: si no se encuentra una página, puede que la empresa no esté cubierta

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.

  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:

  • marketscreener.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

Marketscreener loads about 1.1k tokens when it runs, and up to ~4.2k if it reads all its reference files. Until then it costs about 51 tokens; SKILL.md has 321 words of instructions outside code blocks.

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

~51

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

~1.1k

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

~4.2k

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). 321 words, ~1,069 tokens.

name

marketscreener

description

Scraper de MarketScreener (S&P Capital IQ): earnings transcripts, cotizaciones, perfiles empresa, financials, valuation, consenso analistas, noticias, insider trading, ratings. Sin API key.

license

MIT

metadata.category

finanzas, scraper, stocks, transcripts, earnings, eeuu, global, ADRs

metadata.language

es

metadata.source

https://www.marketscreener.com

from marketscreener_client import MarketScreenerClient

client = MarketScreenerClient()

# Último earnings transcript de GGAL
transcript = client.get_transcript("GGAL")
print(transcript["title"])
print(transcript["prepared_remarks"][:500])

# Cotización de AAPL
quote = client.get_quote("AAPL")
print(f"${quote['price']} ({quote['change_pct']}%)")

# Perfil de empresa
profile = client.get_profile("GGAL")
print(profile["name"], profile["industry"])

# Financials
fin = client.get_financials("AAPL", statement="income")
print(fin["2025"]["revenue"])

# Consenso de analistas
consensus = client.get_consensus("AAPL")
print(f"Target: ${consensus['target_mean']}, Recomendación: {consensus['rating']}")

© 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/marketscreener of gauss314/skills.

• SKILL.md
• references/ENDPOINTS.md
• scripts/marketscreener_cli.py
• scripts/marketscreener_client.py

Open the folder on GitHubat commit 5156f81