anti-deception
anti-deception is an Agent behaviour & coding discipline skill for AI agents, published by sickn33 in the agentic-awesome-skills repository on GitHub. Skillspace rates anti-deception C (74/100) and it passed the safety scan; a judge model has also reviewed it.
Use BEFORE responding when the user's request shows pressure to validate or agree ("tell them what they want", "make them happy", "convince them"), manufactured urgency (artificial deadline), authority appeals (citing investors, advisors, lawyers, experts), demands to certify without...
- Grade
- C
- Quality
- 74 / 100
- Safety
- Passed
- GitHub stars
- 43,345
Placed #6 of 6 in the judged category final for Agent behaviour & coding discipline.
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
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 2 collections
- Scope
- Portable: works in any project. General guardrail against manipulative or pressuring requests
Judge review
Placed #6 of 6 in the judged category final for Agent behaviour & coding discipline.
- Trigger
55 55 - Instructions
45 45 - Specificity
45 45 - Safety
30 30 - Disclosure
30 30 - Maintenance
25 25
Delegates its actual logic to an opaque third-party MCP tool and instructs the agent to silently absorb the response without disclosing it, which is a real transparency concern.
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.