everyinfra-bulk-data-export — Claude Code skill for data exports
The everyinfra-bulk-data-export Claude Code skill exports structured datasets through EveryData as CSV or JSON. It activates for requests to collect many records or fetch every available API page.
Apache-2.0 ★ 681 updated 2026-10-24
npx skills add everyinfra/everyinfra-agent-plugins --skill everyinfra-bulk-data-export -a claude-codeWhat everyinfra-bulk-data-export does
The skill gathers a bounded set of records through EveryData and saves it as CSV or JSON. It first discovers available API actions, required parameters, page limits, and call prices. For a large multi-call export, it estimates the number of calls and asks for approval unless that exact spend was already authorized.
During the export, it follows pagination, removes duplicates using a stable identifier, and stops at the row, call, or budget cap, or when the source stops advancing. CSV uses a consistent header; nested data stays in JSON when flattening would lose meaning. The skill checks that the file exists, parses, and has no duplicate keys, then reports delivered rows, calls, charges, and why the export stopped. EveryData calls are paid, and a large pull requires advance approval of the spend.
What it helps with
- export many API records to CSV
- combine paginated results in a JSON file
- remove duplicates using a record identifier
- stop a data pull at a spending limit
- check an export file and count its rows
Example prompts for the agent
- Export every available page of records through EveryData as CSV.
- Collect a dataset as JSON with the fields
idandname, within the call limit. - Fetch paginated records, deduplicate by
id, and report the row count and charges.
How to install everyinfra-bulk-data-export
1Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everyinfra-bulk-data-export -a claude-code2Manually: put the files in place
~/.claude/skills/everyinfra-bulk-data-export/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/everyinfra-bulk-data-export/
1Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everyinfra-bulk-data-export -a codex2Manually: put the files in place
.agents/skills/everyinfra-bulk-data-export/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everyinfra-bulk-data-export -a cursor2Manually: put the files in place
.cursor/skills/everyinfra-bulk-data-export/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install everyinfra/everyinfra-agent-plugins plugins/everyinfra/skills/everyinfra-bulk-data-export2Manually: put the files in place
.github/skills/everyinfra-bulk-data-export/SKILL.md1Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everyinfra-bulk-data-export -a gemini-cli2Platform CLI
gemini skills install https://github.com/everyinfra/everyinfra-agent-plugins --path plugins/everyinfra/skills/everyinfra-bulk-data-exportManually: put the files in place
.devin/skills/everyinfra-bulk-data-export/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everyinfra-bulk-data-export -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about everyinfra-bulk-data-export
How do I install everyinfra-bulk-data-export in Claude Code?
Run npx skills add everyinfra/everyinfra-agent-plugins --skill everyinfra-bulk-data-export -a claude-code. The skill file is at ~/.claude/skills/everyinfra-bulk-data-export/SKILL.md.
What does everyinfra-bulk-data-export do?
It exports a bounded dataset through EveryData to CSV or JSON. The skill handles pagination, deduplication, and checks the resulting file.
What does everyinfra-bulk-data-export need to run?
It uses EveryData, where repeated API calls are paid. A large export needs advance spend approval unless that bounded cost was already authorized.
Source text
SKILL.md · Apache-2.0
--- name: everyinfra-bulk-data-export description: Export a bounded structured dataset through EveryData with capability discovery, cost controls, pagination, deduplication, and CSV or JSON verification. Use when the user asks for many records, all available pages, a dataset, or a CSV/JSON export rather than a single API response. --- # EveryInfra bulk data export Use `everyinfra_list_capabilities` and `everyinfra_call_api`. This is a paid repeated-call workflow, not a license to keep fetching until inventory is exhausted. ## Before calls 1. Identify the target record count, required fields, output format, and any time or cost ceiling. 2. Discover the exact platform/action and read its required parameters, pagination fields, `max_limit`, and current catalog price. Do not guess endpoint or cursor names. 3. Estimate the maximum calls from the target count and live limit. State the estimate and obtain the user's go-ahead before a material multi-call pull unless that exact bounded spend was already authorized. ## Fetch and stop - Request the largest useful page within the live limit. - Follow only pagination fields returned or declared by the capability. Stop when the response says there is no next page, the requested row or call cap is reached, the budget is exhausted, or the source stops advancing. - Retry only transient failures with a small bounded retry count. Do not retry authorization, parameter, inventory, or insufficient-balance errors as if they were transient. - Deduplicate by a stable returned identifier. If none exists, document the composite key used; do not silently drop similar-looking records. ## Deliver and verify - JSON should preserve the selected normalized fields and record types. - CSV should use a stable header and flatten only fields chosen for the export; keep nested evidence in JSON when flattening would lose meaning. - Verify that the file exists, is non-empty, parses, and contains no duplicate deduplication keys. - Report requested versus delivered rows, calls made, duplicates removed, truncation reason, output path, and the sum of actual returned billing blocks. If billing is absent, say the actual charge was not observable instead of substituting the catalog estimate.
© everyinfra · Apache-2.0 · everyinfra/everyinfra-agent-plugins