← All skills
undercover-game-referee
97 / 100 · Low risk
Fine to try. Some of what it can do is expected: a devops skill usually runs commands, installs tools and uses cloud credentials.
By inclusionAI/Avernet (GitHub) · devops · 602 stars · scanned at commit f978637
主持谁是卧底，按当前节点或唤醒执行事实层命令与主持稿，保持发言、投票、遗言和终局流程。
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 devops skill.
Found in 11 places.
Show 8 more
- singlebox/agents/6bots_undercover_game_profile/referee/skills/undercover-game-referee/tests/test_bcs_identity.py, line 117
return subprocess.CompletedProcess(command, 0, json.dumps(self.session), "") - singlebox/agents/6bots_undercover_game_profile/referee/skills/undercover-game-referee/tests/test_bcs_identity.py, line 118
return subprocess.CompletedProcess(command, 1, "", "401 Unauthorized") - singlebox/agents/6bots_undercover_game_profile/referee/skills/undercover-game-referee/tests/test_finish.py, line 51
with patch.dict(os.environ, {"OPENCLAW_DATA_DIR": self.temp.name}, clear=True), patch.object(uc.subprocess, "run", return_value=subprocess.CompletedProcess([], - singlebox/agents/6bots_undercover_game_profile/referee/skills/undercover-game-referee/tests/test_finish.py, line 61
return subprocess.CompletedProcess(cmd, 0, output, "") - singlebox/agents/6bots_undercover_game_profile/referee/skills/undercover-game-referee/tests/test_finish.py, line 69
with self.subTest(message=message), patch.object(uc.subprocess, "run", return_value=subprocess.CompletedProcess([], 1, "", message)): - singlebox/agents/6bots_undercover_game_profile/referee/skills/undercover-game-referee/tests/test_finish.py, line 72
with patch.object(uc.subprocess, "run", return_value=subprocess.CompletedProcess([], 0, '{"status":"completed"}', "")): - singlebox/agents/6bots_undercover_game_profile/referee/skills/undercover-game-referee/tests/test_finish.py, line 76
with patch.object(uc.subprocess, "run", return_value=subprocess.CompletedProcess([], 0, "invalid response", "")): - singlebox/agents/6bots_undercover_game_profile/referee/skills/undercover-game-referee/tests/test_tie_break_pk.py, line 33
result = subprocess.run(["python3", str(SCRIPT), name, "--session", self.session, *args], capture_output=True, text=True)
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'undercover-game-referee' ] || [ -L ~/.agents/skills/'undercover-game-referee' ]; then echo 'A skill folder named undercover-game-referee already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/inclusionAI/Avernet' "$d" && git -C "$d" checkout --quiet 'f97863707dfe9c4d140b8b39cfc0564fa168627d' -- 'singlebox/agents/6bots_undercover_game_profile/referee/skills/undercover-game-referee' && mkdir -p ~/.agents/skills && cp -R "$d"/'singlebox/agents/6bots_undercover_game_profile/referee/skills/undercover-game-referee' ~/.agents/skills/'undercover-game-referee' && 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/'undercover-game-referee' ~/.claude/skills/'undercover-game-referee' (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 inclusionAI/Avernet shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/inclusionAI/Avernet/)
Score history
| Date | Version | Score |
|---|
| 2026-11-12 | f978637 | 97 |
| 2026-11-08 | 58db87b | 97 |
| 2026-11-06 | 65e270d | 97 |