advisor-intelligence
Skill1 starsChanged 48 days agoMITView on GitHub
Choose or pin a model for a crew run from the user's roster, without changing global settings.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- advisor-role-advisorSkill
- advisor-role-builderSkill
- advisor-role-checkerSkill
- advisor-role-foremanSkill
- advisorSkill
- advisor-teamSkill
- cosSkill
- rosterSkill
- routerSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Leave the choice to the router unless the user named a model or the pick is plainly wrong for the task.
≈ “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.
Files
Model choice
crew spawn picks the model itself. The router judges the task against the user's roster
(crew roster shows each model's roles, cost, what it is for and not for, and its track
record); without a router, a spawn takes the roster's first model for the role, then the role
defaults in ~/.config/crew/config.json. crew route --role R --task T shows the pick
without launching anything.
Leave the choice to the router unless the user named a model or the pick is plainly wrong for
the task. Then pin one from the roster, crew spawn --model <host>/<model>@<effort>, and say
why in one line. A model outside the roster needs the user's say-so. If the user wants
routing off for this session, run crew router off (children inherit it; crew router reset
undoes it). With no roster yet, the user can build one with the roster skill.
For a native read-only lookup, pick the cheapest model the host offers that can do it
(Claude Code: model: "haiku" or "sonnet"), never your own model by default.
A skill cannot change your running root model. Do not modify global settings, authentication or permissions to follow this guide.
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
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.