Bigdata.com SDK + REST Toolkit
When the Bigdata.com (RavenPack) MCP only returns synthesized prose, this skill drops to the official SDK and /v1 REST endpoints for raw financials, prices, estimates and sentiment.
What it does
The Bigdata.com MCP server answers a chat turn nicely but withholds the machine-readable substrate: no per-chunk sentiment numbers, no entity spans, no fiscal-period time series. This skill bundles bigdata_toolkit, which pairs the official bigdata-client SDK with a thin REST passthrough to the documented /v1/* endpoints (same backend, same JWT).
- Analyst estimates, earnings surprise, event calendar, ratings and price targets
- Income / balance / cash-flow statements, TTM metrics and ratios, daily OHLC, dividends, revenue by geography and product
- Daily entity-sentiment series, co-mention (supply-chain/competitor) graph, company screener
- Annotated news, filing and transcript chunks with numeric sentiment plus entity character spans
- Chunk-billing awareness:
CostTrackerfor real spend,CostModelto veto over-budget jobs, batch search at 50% cost
Who it's for
- Quants and research analysts with a paid Bigdata.com / RavenPack
bd_v2_key - Anyone whose MCP result felt thin and who wants the underlying sentiment score
- Data engineers building a reusable, cost-aware investment-research pull layer
Examples
- "Show NVIDIA's next four quarters of revenue/EPS consensus" →
resolve_idthenanalyst_estimates(period="quarter"). - "Build a universe of US semiconductor names above $10B market cap and attach each one's latest earnings surprise" →
company_screener+latest_surprise. - "Estimate quota cost before this backfill and abort if it exceeds budget" →
CostModelveto up front,CostTracker.delta()to measure actual chunk spend.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/daymade/claude-code-skills/HEAD/daymade-financial/bigdata-skill/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
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/bigdata-skill⚠ 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 - Install the skill:
mkdir -p ~/.claude/skills && cp -r claude-code-skills/daymade-financial/bigdata-skill ~/.claude/skills/bigdata-skill - Export your Bigdata.com API key (never hardcode it):
export BIGDATA_API_KEY=bd_v2_xxxxxxxx - Create an isolated Python env and install the official SDK:
uv venv .venv --python 3.12thenuv pip install --python .venv/bin/python bigdata-client(add--index-url <mirror>on a slow/blocked PyPI). - If your network requires a proxy:
export HTTPS_PROXY=http://host:port; for TLS-intercepting proxies useBigdataClient(verify_ssl="<proxy-CA>.pem"). - Smoke-test the whole path:
cd ~/.claude/skills/bigdata-skill && PYTHONPATH=scripts /path/to/.venv/bin/python scripts/probe_example.py - Restart Claude Code, then ask something like "pull NVIDIA analyst estimates from Bigdata.com" and the skill will trigger automatically.