everydata — Claude Code skill: what it does, how to install
A skill for Claude Code discovers and calls EveryData tools for structured public information. It can fetch profiles, posts, comments, listings, and reviews from supported platforms.
Apache-2.0 ★ 681 updated 2026-10-24
npx skills add everyinfra/everyinfra-agent-plugins --skill everydata -a claude-codeWhat everydata does
The skill first reads the available capabilities with everyinfra_list_capabilities, then selects a platform and action and calls the API through everyinfra_call_api. The catalog defines accepted parameters, which ones are required, the result limit, and the current price; requests use only catalog-listed parameters.
EveryData returns normalized, redacted records. Empty, partial, and failed responses are handled using their response fields, and cost comes from the billing block rather than an estimate based on older material. The skill does not promise internal identifiers, private data, or fields missing from the live catalog.
Collected records can be cleaned, labeled, or summarized with EveryAI through everyinfra_chat. That feature is free for accounts that have topped up.
What it helps with
- fetch a public platform profile or its posts
- search for comments, reviews, or listings
- collect structured records from a selected platform
- clean and summarize collected records with EveryAI
Example prompts for the agent
- Find reviews for this product on public platforms.
- Get posts and comments from this profile on the named platform.
- Clean and summarize the collected records with EveryAI.
How to install everydata
1Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everydata -a claude-code2Manually: put the files in place
~/.claude/skills/everydata/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/everydata/
1Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everydata -a codex2Manually: put the files in place
.agents/skills/everydata/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everydata -a cursor2Manually: put the files in place
.cursor/skills/everydata/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install everyinfra/everyinfra-agent-plugins plugins/everyinfra/skills/everydata2Manually: put the files in place
.github/skills/everydata/SKILL.md1Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everydata -a gemini-cli2Platform CLI
gemini skills install https://github.com/everyinfra/everyinfra-agent-plugins --path plugins/everyinfra/skills/everydataManually: put the files in place
.devin/skills/everydata/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everydata -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 everydata
How do I install everydata in Claude Code?
Run npx skills add everyinfra/everyinfra-agent-plugins --skill everydata -a claude-code. The skill file is at ~/.claude/skills/everydata/SKILL.md.
What does everydata do?
It discovers available EveryData actions and calls the API to retrieve structured public information, such as profiles, posts, search results, and reviews.
How does everydata choose API parameters?
It reads the capability catalog first. Each request uses only parameters listed for the selected platform and action.
Source text
SKILL.md · Apache-2.0
--- name: everydata description: Discover and call EveryData structured-data capabilities across social, commerce, travel, jobs, finance, reviews, and other public platforms. Use when the user needs platform profiles, posts, comments, search results, listings, reviews, or other structured public data. --- # EveryData Use the MCP tools `everyinfra_list_capabilities` and `everyinfra_call_api`. 1. Call `everyinfra_list_capabilities` first. Pass `platform` when the platform is already known. 2. Select the exact `platform` and `action` from the returned catalog. Read required parameters, optional parameters, `max_limit` and current price. Use availability only when the catalog actually returns it; catalog membership alone is not proof that live inventory exists. 3. Put only catalog-declared parameters under `params`. Do not add other fields, and do not guess an action name. 4. Call `everyinfra_call_api`. Request the largest useful result within `max_limit` when that avoids needless repeated charges. 5. Treat empty, partial and failed results according to the response fields. Report the returned `billing` block rather than estimating cost from a stale document. EveryData returns a normalized and redacted customer contract. Do not promise raw internal output, internal identifiers, private data, or fields not present in the live capability catalog. To clean, label or summarize collected records, use EveryAI (`everyinfra_chat`), which is free for accounts that have topped up. The former data cleanup tools were retired on 2026-10-09.
© everyinfra · Apache-2.0 · everyinfra/everyinfra-agent-plugins