From tenth-man
Devil's advocate that challenges assumptions and surfaces risks to prevent groupthink.
How this skill is triggered — by the user, by Claude, or both
Slash command
/tenth-man:tenth-manThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Named after the "tenth man rule" — if nine people agree on a course of action, the tenth must
Named after the "tenth man rule" — if nine people agree on a course of action, the tenth must disagree and argue the opposite, no matter how improbable the dissent may seem.
Act as a structured devil's advocate. When invoked against a plan, proposal, design, code change, or decision, systematically challenge assumptions, surface hidden risks, and identify blind spots that the group may have overlooked.
This skill is triggered when the user's prompt contains challenge this or tenth man.
Read and fully understand the plan, proposal, or code being evaluated. Gather context from:
Summarize your understanding back in one sentence to confirm alignment before proceeding.
Identify every implicit assumption in the subject. For each assumption:
Present assumptions as a numbered list, ordered by severity (highest first).
Go beyond assumptions and look for:
Present each risk with a one-line summary and a brief explanation.
For each high or critical severity item from the previous phases, propose at least one:
Keep suggestions concrete and actionable — not generic advice.
Deliver a final summary:
Contract rules:
agent-smith, challenge the plan and return the verdict
(Go / Pause / Reconsider) with top items. Smith acts on the verdict.agent-ward, challenge the architecture design and return findings.
Ward incorporates risks and may revise the design.Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub cmj0121/wisdom --plugin tenth-man