Skills Explorer Add Skills

bigdata-skill

An agent skill by daymade, from daymade/claude-code-skills. Tags: analytics, api, data, financial-data, research.

What it does

Pull Bigdata.com (RavenPack) financial and news data via the official `bigdata-client` SDK and `/v1/*` REST endpoints — structured financials, prices, analyst estimates, daily entity-sentiment series, annotated chunk search, screener — when the Bigdata MCP returns only pre-synthesized tearsheets but you need the machine-readable substrate. Use when the user mentions Bigdata.com, RavenPack, a `bd_v2_` key, the bigdata MCP, rp_entity_id, chunk/query_unit cost, or wants structured financials, fundamentals, prices, sentiment, or annotated news.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add daymade/claude-code-skills --skill bigdata-skill

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/daymade-financial/bigdata-skill ~/.claude/skills/bigdata-skill

Safety box score

Grade C, moderate risk: 35 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a read-only Bigdata.com research client, but it still reaches out to live external services, requires a real API key, and can upload batch-search inputs to presigned S3 URLs. The main risks are network/data exfiltration to third parties, quota spend, and the fact that it depends on an external `bigdata-client` package that is not bundled in the repo.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution2 (moderate)It asks the agent to execute shipped Python code and install a dependency (`uv pip install --python .venv/bin/python bigdata-client` and `python scripts/probe_example.py`), though it does not eval arbitrary code.
Network access2 (moderate)It calls live Bigdata endpoints over the network (`https://api.bigdata.com/`) and also uses raw `requests.put()` / `requests.get()` against presigned URLs in `scripts/bigdata_toolkit/rest_ext.py`.
Filesystem reach1 (low)The only obvious local writes are bounded to a project venv / scripts path (`uv venv .venv`, `PYTHONPATH=scripts`); there is no recursive delete or system-path editing.
Secrets & credentials2 (moderate)It requires a real API key via `BIGDATA_API_KEY` (`self.api_key = api_key or require_env("BIGDATA_API_KEY")`) and the docs explicitly tell the user to export `bd_v2_...`.
Privilege & persistence0 (none)There is no sudo, global install, service registration, shell startup modification, or OS-level privilege change in the shipped files.
Instruction hijack surface0 (none)I did not find hidden prompt-injection payloads or instructions to ignore higher-priority rules; the directives are normal task guidance, not adversarial text.
Irreversible actions1 (low)It can submit remote batch jobs and searches (`POST v1/search/batches`, `POST .../query`) and consume quota, but it does not send messages, pay, deploy, or delete data.
Transparency1 (low)The skill relies on an external, unpinned package install (`bigdata-client`) rather than only code in the repo, so part of the executed code is outside reviewer visibility.

Before installing

Rated 2026-10-20 by an automated review of 13 files from the skill's repository.

Source

Repository
daymade/claude-code-skills (all skills from this repository)
Path
daymade-financial/bigdata-skill/SKILL.md
Branch
main
Updated
2026-09-20