Use before committing to the public CTObot repo to catch company-specific or proprietary content that has drifted into the public files (AGENTS.md, SOUL.md, docs/, skills/, README). The agent reads the diff (or all files) and reasons about whether the content is generic and shareable or specific to our company…
Use when turning external CTO leadership articles into a clean challenge list for evaluation. Extracts and normalizes the real leadership problems while ignoring vendor pitches, solution marketing, and duplicate phrasing.
Use when red-teaming a CTO operating manual (AGENTS.md, with its CHEATSHEET.md quick reference and SOUL.md persona) against external leadership challenges. Produces a practical pass/partial/fail audit focused on execution gaps, missing artifacts, and adoption risk.
Use when stress-testing an agentic CTO against new-CTO challenge lists, leadership pitfalls, or external CTO guidance. Produces a red-team scorecard with coverage, failure modes, missing artifacts, severity, and pass/partial/fail ratings.
Stress-test an agentic CTO against a catalog of common CTO challenges; compare responses to an operating manual, score response quality, and surface gaps in strategy, execution, delivery, risk, talent, and governance.