agentleFS
Sign inStart free
Nyquest-aiNyquest-ai/nyquest-claude-mcp/skills/setup/SKILL.md

setup

Skill2 starsChanged 17 days agoMITView on GitHub

Walk the user through turning on Nyquest full mode with a free API key, or show the current mode and level. Use when the user runs /nyquest:setup, asks how to enable full mode, or asks how to set or remove their Nyquest API key.

  • Reads credentials

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call the Nyquest savings tool.

    line 10
  2. Very specific:

    If the user passed a key as the argument (it starts with nq-v1-), call configure(apiKey=<key>), which saves it in ~/.nyquest/config.json, …

    line 13
  3. Distinctive:

    If the user wants full mode and gave no key, explain in a few short lines:

    line 17
  4. Very specific:

    If the user wants to leave full mode: when the key comes from the plugin configuration, tell them to clear it with /plugin configure …

    line 34
  5. Very specific:

    If the user mentions a key in the NYQUEST_API_KEY environment variable: since 0.6.0 the plugin no longer reads it.

    line 37
  6. Distinctive:

    Never print a key back to the user.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 171 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Goal: get the user into the mode they want with as few steps as possible.

  1. Call the Nyquest savings tool. Its first line gives the mode, where the key in effect comes from (key from the plugin configuration, key from ~/.nyquest/config.json, no API key, or that a key does not start with nq-v1-), and the level.
  2. If the user passed a key as the argument (it starts with nq-v1-), call configure(apiKey=<key>), which saves it in ~/.nyquest/config.json, and confirm the resulting mode in one line. Add once that /plugin configure nyquest keeps a key where Claude Code keeps its own login instead of in a plain file. Stop.
  3. If the user wants full mode and gave no key, explain in a few short lines:
    • Full mode is free. It adds platform condensation for prose results, recall(ask=...) answers, and account savings totals. Local mode keeps working without it.
    • What leaves the machine in full mode: prose from web and agent tools (WebFetch, WebSearch, Agent, digest_url), with secrets redacted, is sent to the Nyquest platform and processed by third-party model providers. Bash, PowerShell, file and MCP output never leaves the machine unless the user opts a tool in with configure(remoteTool="Bash", remoteEnabled=true). Every park also reports counts only (tool, class, sizes), never content.
    • Get a key at https://app.nyquest.ai (sign in, create an API key; it starts with nq-v1-).
    • Recommended: in a terminal session, run /plugin configure nyquest and paste the key into the masked field, then restart Claude Code. Claude Code keeps the key where it keeps its own login (the macOS Keychain, or its protected credentials file elsewhere) and hands it only to this plugin, and the key never enters the chat. In VS Code, the gear on the plugin's row in Manage plugins does the same.
    • Where /plugin is not available, such as the desktop app: run /nyquest:setup nq-v1-... or say "set my Nyquest API key to ...". That saves the key in ~/.nyquest/config.json.
  4. If the user wants to leave full mode: when the key comes from the plugin configuration, tell them to clear it with /plugin configure nyquest and restart; when it comes from ~/.nyquest/config.json, call configure(apiKey="") and confirm.
  5. If the user mentions a key in the NYQUEST_API_KEY environment variable: since 0.6.0 the plugin no longer reads it. Point them to step 3 to move the key into the plugin configuration.
  6. Never print a key back to the user; refer to it as "your key".

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free