Devils Advocate Suite
v1.0.0Execute structured adversarial thinking to stress-test high-stakes decisions, identify systemic risks, and prevent groupthink. Use when the user asks for a s...
⭐ 0· 96·0 current·0 all-time
byDavid Escobar@midnightstudioai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (adversarial review, pre-mortem, PR/FAQ, TRIZ) matches the included SKILL.md, evals, and two small Python helpers that implement a risk aggregator and TRIZ lookup. The requested capabilities are proportional to the stated purpose.
Instruction Scope
SKILL.md instructs the agent to run local Python scripts (premortem_aggregator.py, triz_solver.py) and to produce structured critiques. The scripts only process stdin/CLI args and local data; they do not perform network I/O or read arbitrary system paths. Minor mismatch: the skill does not declare required binaries but presumes a Python runtime to execute the scripts.
Install Mechanism
No install spec (instruction-only plus included scripts). No downloads, package installs, or archive extraction. Files are small, readable, and self-contained.
Credentials
The skill requires no environment variables, credentials, or config paths. The code doesn't reference secrets or external services; credential access is not present and would be disproportionate to this purpose.
Persistence & Privilege
The skill is not always-enabled and does not request elevated or persistent privileges. It does not modify other skills or system-wide settings based on the provided material.
Assessment
This skill appears internally coherent and limited to local analysis: the two Python scripts aggregate premortem items and recommend TRIZ principles and do not contact external servers or request credentials. Before installing, confirm your agent environment has Python available (the SKILL.md assumes running python but the registry metadata lists no required binaries). Review the included SKILL.md and scripts yourself if you want to be extra cautious. Also be aware: the skill's output is intentionally adversarial and can produce blunt or pessimistic critiques — avoid pasting extremely sensitive proprietary data into the tool unless you are comfortable with local processing of that data.Like a lobster shell, security has layers — review code before you run it.
latestvk979sggprxq018scxgm9pgtk5n83epcm
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
