Cli llm routing
Skill search-atlas-group/amm-founding-circle/skills/cli-llm-routing
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.From its SKILL.md
npx -y skills add search-atlas-group/amm-founding-circle --skill cli-llm-routingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.2 KB, 198 tokens by cl100k_base, as published. Nobody here has run it
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.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.