← All skills
exploratory-run
97 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
By pdl-openair/OpenAIR (GitHub) · coding · 16 stars · scanned at commit cb37612
在代码、资源、环境和单次实验目标都已明确后，使用已验证环境真实启动一次受控实验，取得真实退出状态与有界 stdout/stderr，并形成稳定执行记录。
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 coding skill.
Found in 31 places.
Show 17 more
- skills/cs_research/exploratory-run/adapter/execution_process.py, line 74
def _terminate_windows_tree(process: subprocess.Popen[bytes]) -> tuple[bool, dict[str, object]]: - skills/cs_research/exploratory-run/adapter/execution_process.py, line 80
except (OSError, subprocess.TimeoutExpired): - skills/cs_research/exploratory-run/adapter/execution_process.py, line 85
result = subprocess.run( - skills/cs_research/exploratory-run/adapter/execution_process.py, line 92
except (OSError, subprocess.TimeoutExpired) as error: - skills/cs_research/exploratory-run/adapter/execution_process.py, line 97
except subprocess.TimeoutExpired: - skills/cs_research/exploratory-run/adapter/execution_process.py, line 106
def _terminate_posix_tree(process: subprocess.Popen[bytes]) -> tuple[bool, dict[str, object]]: - skills/cs_research/exploratory-run/adapter/execution_process.py, line 115
except subprocess.TimeoutExpired: - skills/cs_research/exploratory-run/adapter/execution_process.py, line 120
def terminate_process_tree(process: subprocess.Popen[bytes]) -> tuple[bool, dict[str, object]]: - skills/cs_research/exploratory-run/adapter/execution_process.py, line 139
"stdout": subprocess.PIPE, - skills/cs_research/exploratory-run/adapter/execution_process.py, line 140
"stderr": subprocess.PIPE, - skills/cs_research/exploratory-run/adapter/execution_process.py, line 145
popen_kwargs["creationflags"] = subprocess.CREATE_NEW_PROCESS_GROUP - skills/cs_research/exploratory-run/adapter/execution_process.py, line 150
process = subprocess.Popen([str(executable), *argv], **popen_kwargs) - skills/cs_research/exploratory-run/adapter/execution_process.py, line 174
except subprocess.TimeoutExpired: - skills/cs_research/exploratory-run/adapter/execution_process.py, line 178
except (OSError, subprocess.SubprocessError) as error: - skills/cs_research/exploratory-run/tests/test_execution_process_cleanup.py, line 38
with subprocess.Popen( - skills/cs_research/exploratory-run/tests/test_execution_process_cleanup.py, line 42
stdout=subprocess.PIPE, - skills/cs_research/exploratory-run/tests/test_execution_process_cleanup.py, line 43
stderr=subprocess.PIPE,
and 11 more places
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'exploratory-run' ] || [ -L ~/.agents/skills/'exploratory-run' ]; then echo 'A skill folder named exploratory-run already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/pdl-openair/OpenAIR' "$d" && git -C "$d" checkout --quiet 'cb37612d98d6155a133121a1f0d7cd3e06c985a8' -- 'skills/cs_research/exploratory-run' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/cs_research/exploratory-run' ~/.agents/skills/'exploratory-run' && 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/'exploratory-run' ~/.claude/skills/'exploratory-run' (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 pdl-openair/OpenAIR shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/pdl-openair/OpenAIR/)
Score history
| Date | Version | Score |
|---|
| 2026-11-11 | cb37612 | 97 |