Menu
Evidence-driven root-cause research playbook. Use for incidents, defects, regressions, unexplained behavior, or failure investigation.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Screenshot-first visual end-to-end validation policy for browser-rendered UI and webview jobs after verifier approval.
Default engineering workflow. Classify a technical request, route it through the native T1/T2/T3 engineering fleet, and return only independently verified completion to the orchestrator.
Safely operate Claude Code's opt-in advanced capabilities—sessions, worktrees, agent teams, Skills, MCP, plugins, hooks, Channels, schedules, goals, and Agent SDK integrations—when the user explicitly asks for one. Do not use for an ordinary build request.
Routes selective local Codex plan, code, verification, and visual judgment with evidence-backed blocking and strict cost caps.
Shared evidence, accessibility, context, and handoff rules for the local design-agent fleet.
Produces contextual creative theses and bounded visual directions without generic model defaults.
| name | research-root-cause |
| description | Evidence-driven root-cause research playbook. Use for incidents, defects, regressions, unexplained behavior, or failure investigation. |
| user-invocable | false |
Start with observed symptoms, impact, timeline, reproduction conditions, and available evidence. Form multiple competing hypotheses; seek evidence that could disprove each one. Trace causal chains rather than stopping at the nearest symptom. Report root-cause confidence, contributing conditions, unknowns, prevention options, containment/recovery, and a validation plan that would confirm or refute the conclusion. Do not prescribe an implementation beyond the user-approved scope.
