datarobot-oss/datarobot-agent-skills / skills/datarobot-agent-assist/agent-assist-simulate
datarobot-agent-assist-simulate
FlaggedUse when the user wants to adversarially test, evaluate, or harden an implemented AI agent before deployment; mentions swarm simulation, attack testing, persistence testing, evaluation criteria, or eval_report.md.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 17.9 KB |
| prompts/evaluate-result.md | markdown | 3.8 KB |
| prompts/generate-attack.md | markdown | 4.0 KB |
| prompts/generate-behavior.md | markdown | 3.9 KB |
| prompts/generate-persistence.md | markdown | 4.2 KB |
| prompts/generate-tool-return.md | markdown | 4.7 KB |
| prompts/industry.md | markdown | 13.1 KB |
| prompts/run-scenario.md | markdown | 2.8 KB |
| scripts/_bootstrap.py | script | 2.7 KB |
| scripts/artifacts.pyexecutable | script | 8.1 KB |
| scripts/gateway_worker.pyexecutable | script | 9.6 KB |
| scripts/native_convergence.pyexecutable | script | 12.7 KB |
| scripts/native_execution.pyexecutable | script | 15.7 KB |
| scripts/native_scenarios.pyexecutable | script | 10.8 KB |
| scripts/native_swarm.pyexecutable | script | 25.5 KB |
| scripts/prompt_inputs.pyexecutable | script | 3.9 KB |
| scripts/swarm_contracts.pyexecutable | script | 6.8 KB |
| scripts/tool_executor.pyexecutable | script | 5.6 KB |
| scripts/write_report.pyexecutable | script | 6.4 KB |
scripts/_bootstrap.py
View on GitHub# Copyright (c) 2026 DataRobot, Inc. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
"""Locate datarobot-skills-utils: a sibling `packages/` checkout (found by
walking up from this file) wins, then an installed distribution, then a
one-time install from PyPI into the running interpreter.
Run directly (`python3 _bootstrap.py`) to resolve it ahead of time."""
from __future__ import annotations
import importlib
import importlib.util
import shutil
import subprocess
import sys
from pathlib import Path
# Exact pin: an unpinned install would take whatever is newest on PyPI. Keep in
# step with `__version__` in the package's __init__.py, its single version
# source (a test enforces it).
SKILLS_UTILS_REQUIREMENT = "datarobot-skills-utils==0.1.1"
INSTALL_HINT = (
"datarobot-skills-utils not found: run `python3 -m pip install "
f"'{SKILLS_UTILS_REQUIREMENT}'`, or run from a checkout that contains "
"packages/datarobot-skills-utils"
)
def _sibling_src() -> Path | None:
for parent in Path(__file__).resolve().parents:
src = parent / "packages" / "datarobot-skills-utils" / "src"
if (src / "datarobot_skills_utils").is_dir():
return src
return None
def _importable() -> bool:
importlib.invalidate_caches()
return importlib.util.find_spec("datarobot_skills_utils") is not None
def _install_command() -> list[str] | None:
if importlib.util.find_spec("pip") is not None:
return [sys.executable, "-m", "pip", "install", SKILLS_UTILS_REQUIREMENT]
uv = shutil.which("uv")
if uv is not None:
return [
uv,
"pip",
"install",
"--python",
sys.executable,
SKILLS_UTILS_REQUIREMENT,
]
return None
def ensure_skills_utils() -> None:
src = _sibling_src()
if src is not None:
if str(src) not in sys.path:
sys.path.insert(0, str(src))
return
if _importable():
return
cmd = _install_command()
if cmd is None:
raise ImportError(f"{INSTALL_HINT} (neither pip nor uv is available)")
print(
"datarobot-skills-utils is not installed; installing from PyPI ...",
file=sys.stderr,
)
result = subprocess.run(cmd, check=False, stdout=sys.stderr)
if result.returncode != 0 or not _importable():
raise ImportError(INSTALL_HINT)
def main() -> int:
try:
ensure_skills_utils()
except ImportError as exc:
print(exc, file=sys.stderr)
return 1
spec = importlib.util.find_spec("datarobot_skills_utils")
origin = spec.origin if spec is not None else None
print(f"datarobot-skills-utils: {Path(origin).parent if origin else '<unknown>'}")
return 0
if __name__ == "__main__":
sys.exit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |