agentleFS
Sign inStart free
VorElzeVorElze/hermes-office-skills/skills/ai-assistant-editor-setup/SKILL.md

ai-assistant-editor-setup

Skill0 starsChanged 19 days agoMITView on GitHub

Use when setting up an AI assistant extension in VS Code.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify → send a trivial test message and confirm it can read a workspace file before declaring the setup done.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

AI assistant setup in a desktop editor

When to Use

User asks to install, enable, or configure an AI coding assistant inside VS Code or a derivative (Cursor, Windsurf, VSCodium) — first-time provider setup (e.g. Cline), or "it doesn't open / doesn't respond".

Procedure

  1. Open the assistant from ITS OWN activity-bar icon (or its command in the Command Palette). Never start from the editor's built-in Chat panel — that is a different assistant and will answer setup instructions confidently while the target one stays unconfigured.
  2. Gear icon in the assistant's panel → API Provider. Choose managed account/subscription, or BYOK when the user already has a proxy or API key (usually cheapest for a user who pays for a proxy).
  3. BYOK endpoint styles:
    • Anthropic-style proxy: provider Anthropic, Base URL = the proxy endpoint, paste key.
    • OpenAI-style: provider OpenAI Compatible, Base URL ends in /v1 with NO trailing slash, paste key, type the exact Model ID (custom endpoints do not auto-populate model lists).
  4. Fill the collapsible Model Configuration: context window, max output tokens, price (display only), and tool/computer-use mode ON — with it off the assistant is chat-only and file/terminal actions silently no-op.
  5. Verify → send a trivial test message and confirm it can read a workspace file before declaring the setup done.

Pitfalls

  • Two variants of the same assistant installed (stable + nightly/preview) split its commands: palette entries return "No matching results". Keep one variant (prefer the stable marketplace build), uninstall the other, fully restart the editor (File → Exit, not reload window).
  • The activity bar can be moved or hidden — the tell is explorer icons on the RIGHT edge of the window. There is no "Show Activity Bar" command (searching it returns "No matching results" and looks like the feature is gone); use View: Move Activity Bar to Side, then right-click the bar and re-enable the assistant's icon.
  • UI field names move between versions — check the vendor docs (Cline: docs.cline.bot) for current labels instead of asserting them from memory.

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