RedTeam
RedTeam is a Structured reasoning & decision frameworks skill for AI agents, published by danielmiessler in the LifeOS repository on GitHub. Skillspace rates RedTeam C (79/100) and it passed the safety scan; a judge model has also reviewed it.
Adversarial analysis deploying parallel expert agents to stress-test ideas, strategies, and plans — decomposes into atomic claims, attacks them, then steelmans and counter-argues, producing severity-ranked findings with remediation. USE WHEN red team, attack idea, counterarguments, critique, stress test, devil's advocate, find weaknesses, break this, poke holes, strongest objection. NOT FOR collaborative debate to find best path (use Council).
- Grade
- C
- Quality
- 79 / 100
- Safety
- Passed
- GitHub stars
- 16,717
Placed #4 of 6 in the judged category final for Structured reasoning & decision frameworks.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 97 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Portable: works in any project. General adversarial critique method anyone can apply
Judge review
Placed #4 of 6 in the judged category final for Structured reasoning & decision frameworks.
- Trigger
75 75 - Instructions
78 78 - Specificity
78 78 - Safety
48 48 - Disclosure
72 72 - Maintenance
68 68
A precisely specified deliverable (steelman plus ranked, severity-ordered counter-argument) undercut by a coercive, unconditional mandatory-notification step.
Sharper triggers and a precisely specified deliverable (steelman plus ranked counter-argument) than its sibling, but carries the same coercive mandatory-notification pattern.
Not checked yet
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.