Menu
Run the smallest useful checks for the current change and report exactly what passed, failed, was partial, or was blocked.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Ask which skill or flow fits your situation. A router over the skills in this repo.
Implement a piece of work based on a spec or set of tickets.
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.
Plan a huge chunk of work — more than one agent session can hold — as a shared map of investigation tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
| name | verify |
| description | Run the smallest useful checks for the current change and report exactly what passed, failed, was partial, or was blocked. |
Purpose: answer what checks actually passed. Never claim verified unless commands ran and passed.
Look for obvious build/test config before choosing commands:
package.jsonpyproject.tomlCargo.tomlgo.modRun:
git status --shortgit diff --statgit diff --cached --stat when staged changes existPrefer, in order:
Use package scripts and project conventions when available. If the user provides a command, prefer it unless unsafe.
Run the chosen commands. Capture enough output to prove pass/fail without dumping noise.
If no verification command is available, report blocked.
## Verification result
Status: pass | fail | partial | blocked
## Commands run
- `<command>` — pass/fail
## Evidence
<short summary of relevant output>
## Remaining risk
<what was not checked>
## Recommended next step
<none | /zoo-code-review | /zoo-tweak | /zoo-tdd | /zoo-fix | /zoo-commit-and-document>
Hard rule: never say verified, all good, or tests pass unless commands actually ran and passed.
If no checks are available, use:
Status: blocked
Reason: no verification command found
Do not auto-launch any follow-up command.
Write the full verification report to .scratch/zoo-verify/<date>/zoo-verify-<slug>.md.
Call attempt_completion with:
Do NOT use ask_followup_question or write results as plain text without calling the tool.