Setup Maestro in a project using or adopting Maestro: use for init/install/sync/doctor, global skills, hooks, harness setup, or agent integration diagnosis/repair.
SkillScore77Maintained
Automatic
◆DevOps & SRE pack
Last verified 8/27/2026
What it changes
Passed 14 of 18 test cases with the skill, and 6 of 18 without it.
Without skill32%
With skill77%
Checks it passed that the model alone missed
Uses the --chain flag with maestro loop next
Uses maestro loop outcome to log structured outputs
Runs maestro loop trace CARD-402 to inspect card receipts
and 9 more in the full report
11 fixed6 passed either way4 still failing1 broke
Pass-rate lift
+45 pp
Tokens
+1%
Agent turns
0%
Response time
-69%
Model gemini-3.6-flashMeasured 8/27/2026v117 of 22 cases passed with skill · 18 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 11
Prompt
We need to audit card-scoped receipts for ticket card 'CARD-402' in the Maestro workflow loop. What command performs this audit?
What was checked, without and with the skill
Checked
Without skill
With skill
Runs maestro loop trace CARD-402 to inspect card receipts
Missed
Passed
case-16 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md91 linessingle file
Maestro Setup
Tune a Maestro-enabled repository harness from current repository evidence.
Activate with a known session id:
maestro hook record --event skill_activation --skill maestro-setup --session <session_id>
Recipe checkpoint: Maestro's main workflow is the loop. Use maestro status
for current state and maestro loop next as the read-only router when the next
lifecycle is not obvious. Setup writes still use the existing Maestro verbs
named by this skill (init, install, sync, doctor, upgrade,
uninstall, and shell-init), not hidden setup state. Rule: loop next
recommends; outcome/proof/memory verbs write. maestro loop next --chain
explains current chain position without writing; maestro loop outcome appends
structured outcomes and transition receipts after native work; maestro loop trace <card> audits card-scoped receipts; maestro loop improve is a read-only
proposer. Do not use hidden stores, hidden schedulers, silent recipe mutation,
or proof/QA bypass.
Use
After maestro init.
After maestro install.
When an already-initialized repo needs its Maestro setup updated to the
running binary with minimal repeated token cost.
When maestro doctor reports setup or local agent integration problems.
When a repo's build/test/harness instructions are missing or stale.
Do
Run pwd, then maestro status.
If the repo is already initialized and the request is only to update Maestro
setup, take the cheap rerun path before any broader read-in:
Run maestro sync --dry-run.
If it reports only current/skipped resources, do not run maestro sync.
If it reports drift, run maestro sync, then report only changed resources,
backup paths, and blockers.
Run maestro sync --global-skills only when the user asks for global
skills or maestro doctor reports global skill drift.
Designs or reviews MCP servers so AI agents can use them reliably: outcome-oriented tools, flat constrained parameters, actionable errors via isError, token-efficient responses, composable outputs, and disciplined tool surfaces. Use when building an MCP server, adding tools to one, reviewing MCP tool design, or when the user mentions MCP optimization, tool descriptions, MCP best practices, or agent-friendly MCP design. Also use when the user has too many tools causing agent confusion, bloated re