Bigdata.com SDK + REST Financial Data Toolkit
Pull the machine-readable Bigdata.com (RavenPack) substrate — financials, estimates, prices, daily sentiment, annotated chunks — through the official SDK and /v1 REST endpoints with built-in cost guards.
What it does
The Bigdata.com (RavenPack) MCP server returns polished prose and pre-synthesized tearsheets, so the structured fields you'd build a pipeline on are missing. This skill ships bigdata_toolkit, a debugged package that wraps both the official bigdata-client SDK and the /v1/* REST endpoints so you can fetch:
- Company name / ISIN / CUSIP / SEDOL →
rp_entity_id(the gateway key for everything else) - Forward analyst consensus, earnings surprise, earnings & event calendars, ratings and price targets
- Income statement, balance sheet, cash flow, TTM valuation metrics, daily OHLC prices, dividends, revenue by geography/product
- Daily entity-sentiment time series, co-mention (supply-chain/competitor) graphs, and a company screener for universe building
- News, filing and transcript chunks with numeric sentiment plus entity character spans
It also bakes in the hard-won operational details: use ChunkLimit instead of a document limit to avoid a large billing trap, rc() to retry the common first-handshake SSL EOF, CostModel to veto over-budget jobs, and CostTracker to measure actual chunk spend.
Who it's for
- Quant/research users with a paid Bigdata.com account (a
bd_v2_API key) - Anyone building a reproducible investment-research dataset instead of one-off MCP chats
- Teams running large backfills who need cost forecasting before burning query units
Example uses
- "Table NVIDIA's next four quarters of revenue/EPS consensus plus its latest earnings surprise" →
analyst_estimates+latest_surprise, converted to flat records. - "Export a 6-month daily sentiment CSV for my 30-name watchlist" →
entity_sentiment(a free endpoint, zero chunk cost) instead of self-aggregating chunks. - "Screen US semiconductor names above $10B market cap, then attach EV/EBITDA and the next earnings date" →
company_screener+key_metrics_ttm+events_calendar.
· · · Install guide · · ·
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the daymade-financial/bigdata-skill folder from the GitHub repo daymade/claude-code-skills into my ~/.claude/skills/bigdata-skill/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/daymade/claude-code-skills.git && mkdir -p ~/.claude/skills && cp -r claude-code-skills/daymade-financial/bigdata-skill ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Clone the repository:
git clone https://github.com/daymade/claude-code-skills.git - Copy the skill into your Claude Code skills folder:
mkdir -p ~/.claude/skills && cp -r claude-code-skills/daymade-financial/bigdata-skill ~/.claude/skills/ - Export your Bigdata.com API key as an environment variable (never hardcode it):
export BIGDATA_API_KEY=bd_v2_xxxxxxxx - Create an isolated Python env and install the official SDK:
cd ~/.claude/skills/bigdata-skill && uv venv .venv --python 3.12 && uv pip install --python .venv/bin/python bigdata-client - If your network needs a proxy, add
export HTTPS_PROXY=http://host:port; for TLS-intercepting proxies useBigdataClient(verify_ssl="proxy-ca.pem")rather than blind retries. - Run the smoke test:
PYTHONPATH=scripts .venv/bin/python scripts/probe_example.py(entity resolve and quota checks are free). - Restart Claude Code and try a prompt like "Get NVIDIA's analyst estimates from Bigdata.com" to trigger the skill.