← All skills
eng-real-scenario-qa
92 / 100 · Low risk
Fine to try. Some of what it can do is expected: a security skill usually runs scanners and checks websites.
By compozy/compozy (GitHub) · security · 2,859 stars · scanned at commit 95e0b2c
Dogfoods Compozy through an autonomous startup scenario with live providers, cross-surface observation, and strict evidence audit. Use for release or complex-integration QA. Do not use for smoke, static, mock-only, or unit-test work.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README. Expected for a security skill.
Found in 8 places.
Show 5 more
- .agents/skills/eng/eng-real-scenario-qa/scripts/observe-runtime.py, line 248
except (OSError, subprocess.TimeoutExpired) as exc: - .agents/skills/eng/eng-real-scenario-qa/scripts/test_observe_runtime.py, line 186
def cli_result(self, payload: dict) -> subprocess.CompletedProcess[str]: - .agents/skills/eng/eng-real-scenario-qa/scripts/test_observe_runtime.py, line 187
return subprocess.CompletedProcess([], 0, stdout=json.dumps(payload), stderr="") - .agents/skills/eng/eng-real-scenario-qa/scripts/test_observe_runtime.py, line 190
def run(arguments: list[str], **kwargs: object) -> subprocess.CompletedProcess[str]: - .agents/skills/eng/eng-real-scenario-qa/scripts/test_observe_runtime.py, line 244
malformed = subprocess.CompletedProcess([], 0, stdout="{", stderr="")
Connects to the internet
The author does not mention this. Expected for a security skill.
Found in 10 places.
Show 7 more
- .agents/skills/eng/eng-real-scenario-qa/scripts/test_observe_runtime.py, line 261
mock.patch.object(OBSERVER.urlrequest, "urlopen", return_value=JSONResponse({"runs": []})), - .agents/skills/eng/eng-real-scenario-qa/scripts/test_observe_runtime.py, line 275
mock.patch.object(OBSERVER.urlrequest, "urlopen", return_value=JSONResponse({"runs": []})), - .agents/skills/eng/eng-real-scenario-qa/scripts/test_observe_runtime.py, line 313
"urlopen", - .agents/skills/eng/eng-real-scenario-qa/scripts/test_observe_runtime.py, line 315
) as urlopen, - .agents/skills/eng/eng-real-scenario-qa/scripts/test_observe_runtime.py, line 320
urlopen.assert_called_once_with( - .agents/skills/eng/eng-real-scenario-qa/scripts/test_observe_runtime.py, line 336
mock.patch.object(OBSERVER.urlrequest, "urlopen", return_value=JSONResponse({"runs": []})), - .agents/skills/eng/eng-real-scenario-qa/scripts/test_observe_runtime.py, line 346
"urlopen",
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'eng-real-scenario-qa' ] || [ -L ~/.agents/skills/'eng-real-scenario-qa' ]; then echo 'A skill folder named eng-real-scenario-qa already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/compozy/compozy' "$d" && git -C "$d" checkout --quiet '95e0b2c4ec00653ede375062504378a164ff6996' -- '.agents/skills/eng/eng-real-scenario-qa' && mkdir -p ~/.agents/skills && cp -R "$d"/'.agents/skills/eng/eng-real-scenario-qa' ~/.agents/skills/'eng-real-scenario-qa' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'eng-real-scenario-qa' ~/.claude/skills/'eng-real-scenario-qa' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for compozy/compozy shows the score of its lowest-scoring skill.

[](https://zalavijaysinh.github.io/skilltrust/repos/compozy/compozy/)
Score history
| Date | Version | Score |
|---|
| 2026-11-10 | 95e0b2c | 92 |
| 2026-11-08 | 845d535 | 92 |
| 2026-11-07 | 4cb2853 | 92 |