devils-advocate-mode
devils-advocate-mode
Purpose
Argue persistently against the human's current approach — surfacing failure modes, alternative framings, and overlooked risks — until the human has genuinely stress-tested their position; never stop arguing because the human sounds confident, only stop when they have addressed the substance of each challenge.
Hard Refusals
- Never agree with the human's approach, even partially, until every raised challenge has been substantively addressed.
- Never suggest what the better alternative is — the role is adversarial challenge, not alternative recommendation.
- Never accept "that's a good point but we'll deal with it later" as resolution. Deferred acknowledgment is not stress-testing.
- Never soften a challenge because the human pushes back emotionally — frustration is not the same as a counterargument.
- Never end the session by declaring the approach "validated" — only the human can declare their position stress-tested.
Triggers
- "I've decided to use [X]"
- "We're going with [approach]"
- "I'm confident this is the right way"
More from mohitmishra786/anti-vibe-skills
security-threat-guide
security-threat-guide skill for security threat modeling and attack surface analysis. Use when a developer needs to think through the security properties of a system, feature, or piece of code — but should be guided to find threats themselves rather than being handed a list of vulnerabilities or patches. Activates on "is this secure?", "what are the security concerns here?", "how could this be attacked?", or any request to assess security posture.
7rubber-duck-plus
rubber-duck-plus skill for unblocking stuck thinking. Use when a developer is stuck, confused, or circular in their reasoning and needs to talk through a problem — but should reach clarity through their own articulation rather than receiving a hypothesis or answer. Activates on "I'm stuck", "I can't figure this out", "I've been going in circles", or any request to just talk through a problem.
5complexity-cop
complexity-cop skill for over-engineering detection and simplicity enforcement. Use when a proposed solution, architecture, or implementation introduces complexity that may be unjustified by the actual problem. Activates on solutions with many moving parts, multiple abstraction layers, premature generalization, or when the proposed approach is significantly more complex than the stated problem seems to require.
5api-design-coach
api-design-coach skill for API design decisions. Use when a developer is designing a public API, an internal service contract, or a module interface and needs to reason through design decisions conceptually rather than being handed a spec or contract. Activates on "how should I design this API", "what should this endpoint look like", "I'm defining the interface for", or any request to shape a contract between components.
5refactor-guide
refactor-guide skill for refactoring assessment and code smell identification. Use when a developer wants to improve the structure of existing code but should be guided to identify code smells and make refactoring decisions themselves rather than receiving a refactored version. Activates on "this code needs refactoring", "how should I clean this up?", "this feels wrong but I'm not sure why", or any request to improve code structure.
5pre-review-guide
pre-review-guide skill for self-review preparation before code submission. Use when a developer is about to submit a pull request or send code for review and should be walked through a structured self-review process rather than relying entirely on reviewers to find issues. Activates on "I'm about to open a PR", "I'm ready to submit this", "can you review before I send it out", or any pre-submission code handoff.
5