agentleFS
Sign inStart free
search-atlas-groupsearch-atlas-group/amm-founding-circle/skills/cli-llm-routing/SKILL.md

cli-llm-routing

Skill0 starsChanged 5 months agoMITView on GitHub

Use installed AI CLIs for second opinions, latest-docs checks, and long-context review. Avoid raw provider API calls unless a project explicitly requires API integration.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Prefer installed CLI tools for ad hoc AI consultation.

    line 15
  2. Distinctive:

    call provider REST APIs for one-off consultation.

    line 28
  3. Distinctive:

    run shell commands suggested by another model without reviewing them.

    line 29
  4. Distinctive:

    Treat the result as advice, not authority.

    line 47

≈ “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

cli-llm-routing

Prefer installed CLI tools for ad hoc AI consultation. They use your normal login flow, keep credentials out of prompts, and make the command visible.

Use A Second Model When

  • the task involves current documentation;
  • you need a skeptical architecture review;
  • the context is too long for the current session;
  • the answer affects a large amount of work.

Do Not

  • paste API keys into prompts;
  • call provider REST APIs for one-off consultation;
  • run shell commands suggested by another model without reviewing them;
  • assume the second model has your full chat context.

Prompt Shape

Context:
<short, sufficient context>

Question:
<specific decision or review request>

Return:
<bullets, risks, recommendation, sources if web was used>

Output Handling

Treat the result as advice, not authority. Pull useful reasoning back into your main session and verify commands before running them.

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