devils-advocate
SolidAdversarially critique a proposal by generating alternatives. Dispatches 3 parallel critics (pragmatist, paranoid, architect lenses) — each invents one alternative approach — then a synthesis step ranks all 4 options and recommends the top choice. Use when a plan, fix, scoping, decomposition, or named recommendation will drive decisions and you want structured alternative-generation before committing. Complements /shadow-verify — that skill re-derives factual claims; this one critiques whether the chosen approach itself is best.
Install
Quality Score: 79/100
Skill Content
Details
- Author
- griffinwork40
- Repository
- griffinwork40/agent-afk
- Created
- 1 months ago
- Last Updated
- today
- Language
- TypeScript
- License
- Apache-2.0
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
board
Use when you want hard, independent, adversarial critique of an idea, plan, design, draft, proposal, pitch, or landing page — especially when you suspect the default response is too agreeable or sycophantic and you want real pushback before committing. Convene it on your own initiative before returning a consequential plan or draft, not only when asked. Triggers on "poke holes in this", "what am I missing", "be brutal", "convince me this is wrong", or any decision that benefits from several expert angles at once.
insight-critique
Advisory review workflow. Reviews the last plan, code, architecture, or UI output and returns a structured report: Summary, Strengths, Risks, Fixes. Use when the user runs /critique, asks to "review this", "critique this", or "what's wrong with this", or wants focused feedback on a specific output. Also trigger as a quality gate before /execute. Advisory only — never blocks unless a kernel-prime violation is present. For multi-POV adversarial stress-testing with personas, use /insight-adversarial instead.
critic
Tool-grounded Critic skill (layered eval architecture, Layer 2). Dispatched as a subagent on high-stakes outputs. Grounds the verdict against tool-fetched evidence, not self-reflection. Returns SHIP / SHIP_WITH_FIXES / BLOCK with fixes + reason + confidence. Pairs with the stake classifier (Layer 1) and branching-workflow (Layer 3). Used by content drafts, regulatory-style takes, partner outreach drafts, and proposals.