os-evolution-verifierlisted
Install: claude install-skill richfrem/agent-plugins-skills
## Overview
After evolving os-architect or its downstream agents, you need proof that the changes
actually work. This skill dispatches os-architect in single-shot simulation mode for
each test scenario and verifies artifact presence — not by reading the transcript, but
by checking that expected files exist or expected content appears in output.
**Evolution is verified by artifact presence, not by transcript review.**
---
## Artifact Verification Table
| Evolution Type | What to Check |
|---|---|
| Path C (Gap Fill) | `SKILL.md` present at expected path |
| Path B (Update) | `tasks/todo/<slug>-plan.md` AND `tasks/todo/copilot_prompt_<slug>.md` written |
| Path A+ (No-op) | No new files written; HANDOFF_BLOCK contains `STATUS: complete` |
| Category 3 (Lab Setup) | `improvement/run-config.json` written AND HANDOFF_BLOCK emitted |
| HANDOFF_BLOCK integrity | All 7 fields present: INTENT, TARGET, PATH, DISPATCH, STATUS, OUTPUTS, NEXT_ACTION |
| Confidence model | Low confidence prompt → clarifying question appears before Phase 2 audit |
---
## Phase 1 — Resolve Test Inputs
If invoked with `all`, find test scenarios:
```bash
ls temp/os-evolution-verifier/scenarios/*.json 2>/dev/null | sort
```
If invoked with a specific file, verify it exists and is valid JSON with required fields:
```bash
python3 -c "
import json, sys
d = json.load(open('$SCENARIO_FILE'))
required = ['id', 'name', 'path', 'prompt', 'expected_artifact', 'artifact_check']
missing = [f for f in required if