Force a structured second pass on something just generated — a spec, plan, design decision, financial model, code architecture, prose. Use when output looks "fine" but you suspect there's more depth, when a decision is high-stakes, when stress-testing assumptions, or when a workflow hits a fork and you want to think through alternatives before committing. Picks one of nine reasoning methods (pre-mortem, inversion, first principles, red team / blue team, Socratic, constraint removal, stakeholder mapping, analogical, second-order effects) and applies it to the recent output. Triggers: "elicit", "stress test this", "pre-mortem", "what could go wrong", "rethink this", "second pass", "challenge this". Note: for financial-model stress tests, defer to vault-auditor. For code adversarial review, defer to compound-engineering:review:adversarial-reviewer. For agent prompts, defer to rex-redteam.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryProduct & designStars0
About this skill
Force a structured second pass on something just generated — a spec, plan, design decision, financial model, code architecture, prose. Use when output looks "fine" but you suspect there's more depth, when a decision is high-stakes, when stress-testing assumptions, or when a workflow hits a fork and you want to think through alternatives before committing. Picks one of nine reasoning methods (pre-mortem, inversion, first principles, red team / blue team, Socratic, constraint removal, stakeholder mapping, analogical, second-order effects) and applies it to the recent output. Triggers: "elicit", "stress test this", "pre-mortem", "what could go wrong", "rethink this", "second pass", "challenge this". Note: for financial-model stress tests, defer to vault-auditor. For code adversarial review, defer to compound-engineering:review:adversarial-reviewer. For agent prompts, defer to rex-redteam.
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Force a structured second pass on something just generated — a spec, plan, design decision, financial model, code architecture, prose. Use when output looks "fine" but you suspect there's more depth, when a decision is high-stakes, when stress-testing assumptions, or when a workflow hits a fork and you want to think through alternatives before committing. Picks one of nine reasoning methods (pre-mortem, inversion, first principles, red team / blue team, Socratic, constraint removal, stakeholder mapping, analogical, second-order effects) and applies it to the recent output. Triggers: "elicit", "stress test this", "pre-mortem", "what could go wrong", "rethink this", "second pass", "challenge this". Note: for financial-model stress tests, defer to `vault-auditor`. For code adversarial review, defer to `compound-engineering:review:adversarial-reviewer`. For agent prompts, defer to `rex-redteam`.
About this listing
Category
Product & design
Reported license
Not specified
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLI