Menu
Use when: reporting test and validation results with pass/fail status, minimal passing output, and concise failure triage.
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
Use when running workspace tests, choosing a test command, or summarizing results before handoff to debugger.
Use when running workspace tests, choosing a test command, or summarizing results before handoff to debugger.
Use when: running pre-commit or pre-push CI-equivalent checks in any workspace — discovers workflow commands with Cursor tools, filters for local executability, scopes to staged changes, and runs checks cheapest-first.
Use when the user wants to install or customize cursorAssistant in the current project (GitHub install or configure).
Use when: running pre-commit or pre-push CI-equivalent checks in any workspace — discovers workflow commands with Cursor tools, filters for local executability, scopes to staged changes, and runs checks cheapest-first.
Use when: discovering package manifests, assessing dependency health, finding replacements, or confirming import usage before removal — discovery only; mutating installs are handled by the deps agent.
| name | leanVerification |
| description | Use when: reporting test and validation results with pass/fail status, minimal passing output, and concise failure triage. |
| type | reference |
| version | 1.0 |
| license | MIT |
Skill metadata: version "1.0"; tags [lean, verification, testing]; recommended tools [].
Use this skill in workspaces with the lean pack selected.
Apply when running or reporting on tests, linters, type checkers, or any validation step.
Single line only:
Ran: N — pass (M skipped)
No per-test narration. No success confirmations. No "all tests passed" prose. No timing breakdown unless explicitly requested.
For each failure, one block:
FAIL <test-name>
<file>:<line> <error-message>
Follow all failures with a count summary:
Ran: N — failed: F, passed: P, skipped: S
Stack traces: include only the immediate error line plus the assertion line. Omit unrelated framework frames unless the error is ambiguous without them.
<tool>: clean<file>:<line> <code> <message> format, followed by <tool>: F error(s)