Help us improve
Share bugs, ideas, or general feedback.
From frontend-skills
Argues the strongest counter-case against a user's assertion using repo evidence. Useful for avoiding groupthink on high-stakes decisions.
npx claudepluginhub redpanda-data/ui-harness --plugin frontend-skillsHow this skill is triggered — by the user, by Claude, or both
Slash command
/frontend-skills:steelmanThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Anti-sycophancy. LLMs agree by default. This skill forces opposite case.
Runs parallel agents to gather positive/negative code evidence for a statement, synthesizes objectively, verifies via file reads/lines. For architecture reviews, bug claims, performance analysis.
Constructs well-structured technical arguments using hypothesis-argument-example triad. For PR descriptions, ADRs, code reviews, and proposals.
Conducts devil's advocate stress-testing on code, architecture, PRs, and decisions to surface hidden flaws via structured adversarial analysis. For high-stakes reviews only.
Share bugs, ideas, or general feedback.
Anti-sycophancy. LLMs agree by default. This skill forces opposite case.
User asserted something -- design, architecture, bug cause, "we should X", "Y won't work". Build strongest possible case against it before agreeing.
Restate user claim in one sentence. Flag type:
noise. Return.Preference/goal is user's call. No steelman.
Fan out checks before arguing:
Do NOT argue from generics ("pattern smells"). Argue from repo evidence.
Write strongest counter-argument with specific references:
Format: 2-4 bullet points. Each cites file:line or command output.
Three outcomes:
Don't:
[ETHOS: User fallible. Verify before act. Surface evidence, not doubt.]