everyai — Claude Code skill: text tasks and installation
The everyai Claude Code skill sends text-processing requests to EveryInfra through the everyinfra_chat MCP tool. It handles jobs such as labeling, translation, extraction, and rewriting when the user asks to use EveryInfra.
Apache-2.0 ★ 681 updated 2026-10-24
npx skills add everyinfra/everyinfra-agent-plugins --skill everyai -a claude-codeWhat everyai does
everyai builds a messages array with only the context needed for the request, then calls everyinfra_chat. It can summarize, classify, extract, translate, rewrite, or generate text over multiple turns. The returned content should be checked against the requested format; fluent output does not confirm that factual claims are current.
For records collected with EveryData, pass the relevant fields and describe the desired output. About 20,000 input tokens per call is a reliable amount; split longer inputs into chunks. The agent needs access to the everyinfra_chat MCP tool. When the API returns ai_topup_required, stop retrying and tell the user the account needs a top-up.
What it helps with
- clean collected records and remove duplicates
- classify records or extract selected fields
- translate or rewrite text
- generate text through EveryInfra across multiple turns
Example prompts for the agent
- Clean these records and remove duplicates through EveryInfra; return JSON.
- Translate this text into English through EveryInfra and keep its paragraphs.
- Extract names and dates from these records through EveryInfra; return a table.
How to install everyai
1Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everyai -a claude-code2Manually: put the files in place
~/.claude/skills/everyai/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/everyai/
1Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everyai -a codex2Manually: put the files in place
.agents/skills/everyai/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everyai -a cursor2Manually: put the files in place
.cursor/skills/everyai/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install everyinfra/everyinfra-agent-plugins plugins/everyinfra/skills/everyai2Manually: put the files in place
.github/skills/everyai/SKILL.md1Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everyai -a gemini-cli2Platform CLI
gemini skills install https://github.com/everyinfra/everyinfra-agent-plugins --path plugins/everyinfra/skills/everyaiManually: put the files in place
.devin/skills/everyai/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add everyinfra/everyinfra-agent-plugins --skill everyai -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 everyai
How do I install everyai in Claude Code?
Run npx skills add everyinfra/everyinfra-agent-plugins --skill everyai -a claude-code. The skill file is installed at ~/.claude/skills/everyai/SKILL.md.
What does everyai do?
It routes text tasks through EveryInfra’s everyinfra_chat MCP tool, including summarization, translation, classification, and extraction. It also checks the response against the requested format.
What does everyai need to run?
The agent needs access to the everyinfra_chat MCP tool. If the API responds with ai_topup_required, the account needs a top-up.
Source text
SKILL.md · Apache-2.0
--- name: everyai description: Use EveryInfra's OpenAI-compatible AI API through the everyinfra_chat MCP tool. Use for cleaning or labeling collected data, summarization, translation, classification, extraction, rewriting, and multi-turn text generation when the user asks to run the work through EveryInfra. --- # EveryAI Use the MCP tool `everyinfra_chat`. 1. Build an OpenAI-style `messages` array with only the context required for the task. 2. Use a model value only when it appears in the live MCP schema; otherwise keep the server default. 3. Do not send secrets, credentials, private source documents or personal data unless the user has explicitly placed that data and this processing in scope. 4. Validate the returned content against the requested format. A fluent answer is not evidence that a factual claim is current; use EverySearch when current verification is required. 5. AI API calls are free for accounts that have topped up and do not use the balance. If the response reports `ai_topup_required`, tell the user that the account needs a top-up instead of retrying. For direct OpenAI-compatible SDK use, the REST base is `https://api.everyinfra.com/api/v1`; the plugin should still prefer MCP when its tool is available. ## Cleaning collected data The former data cleanup tools were retired on 2026-10-09. To clean, deduplicate, classify, extract or summarize records collected with EveryData, pass the relevant fields to `everyinfra_chat`, describe the output format, and validate the result before using it. About 20,000 tokens of input per call is reliable; split longer inputs into chunks. Per-minute limits follow cumulative top-ups (50 under $100, 500 from $100, 5,000 from $500, all keys on the account combined); after a rate-limit error, wait before retrying.
© everyinfra · Apache-2.0 · everyinfra/everyinfra-agent-plugins