ze-recruit
Skill2 starsChanged 47 days agoUnlicenseView on GitHub
Recruits an agent with the right role and model tier and confirms its brief arrived. Use when the Maestro staffs a floor or a lane.
In this repository43 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- system-one-modelsSkill
- animateSkill
- animation-performanceSkill
- animation-vocabularySkill
- apple-designSkill
- break-uiSkill
- codebase-designSkill
- correctSkill
- diagram-designSkill
- doc-styleSkill
- domain-modelingSkill
- emil-design-engSkill
- find-animation-opportunitiesSkill
- grillingSkill
- impeccableSkill
- improve-animationsSkill
- improve-codebase-architectureSkill
- pick-ui-librarySkill
- prototypeSkill
- researchSkill
- review-animationsSkill
- speckit-analyzeSkill
- speckit-checklistSkill
- speckit-clarifySkill
- speckit-constitutionSkill
- speckit-convergeSkill
- speckit-implementSkill
- speckit-planSkill
- speckit-process-after-implementSkill
- speckit-process-after-tasksSkill
- speckit-specifySkill
- speckit-tasksSkill
- speckit-taskstoissuesSkill
- design-taste-frontendSkill
- ui-ux-pro-maxSkill
- ze-advisorSkill
- ze-continueSkill
- ze-land-floorSkill
- ze-pauseSkill
- ze-request-reviewSkill
- ze-web-verifySkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Write the brief to a file in your own scratchpad first.
- Very specific: line 18
If it exits 1, the brief did not arrive.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Recruit an agent (Maestro only)
Write the brief to a file in your own scratchpad first. The brief must name: the state-file path (journal/state/<terminal id>.md), the scratchpad rule, the pre-review checklist, the commit trailer, the reviewer's name and the throwaway ze_e2e_* DB.
Then run exactly:
scripts/process/recruit.sh "<Name>" <role> <tier> "<Floor>" <brief-file> --note "<Floor> Handoffs"
role:maestro,architect,eng,jr,review,qaordocs.scripts/process/roles.tomllists which tiers each role may use. The script refuses a mismatch such as an engineer on Opus.- It lints the brief, recruits with
ZE_ROLEset, waits for the terminal to be ready, sends the brief with a "reply ready" ping, and retries once withrecruit --replace. --connect "<Agent>"(repeatable) wires the new agent to that agent right after the recruit.maestri askreaches connected agents only, so review requests and verdicts depend on it. Pass the floor's reviewer for every lead and engineer, and the lead for every lane agent. When you recruit the reviewer after the crew, wire each one withmaestri connect "<Reviewer>" "<Agent>" --agent.- If it exits 1, the brief did not arrive. Read the agent's terminal with
maestri checkbefore trying again; do not assume the agent is working.
Preview with --dry-run.
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.

