Evidence-first skills for Codex, Cursor, and Claude Code: research, debugging, planning, execution, review, and goal loops.
Skill Claude CodeCodex
Use when the user explicitly wants to discuss, brainstorm, compare options, or make a material preference decision, or when unclear intent needs guided clarification; do not use for clear execution or a single discoverable detail.
Skill Claude CodeCodex
Use when a failure, regression, crash, flake, or unexpected result has an unknown cause that must be diagnosed before a safe fix; do not use when the cause and narrow fix are already clear.
Skill Claude CodeCodex
Use when the user explicitly asks to persist until a verifiable result, fix until green, monitor through completion, or stay within a stated budget; do not infer persistence from difficulty.
Skill Claude CodeCodex
Use when the user asks to add or refresh concise project-local Teamwork instructions in one named project; do not use to install global tools or create workflow records.
Skill Claude CodeCodex
Use when the user asks for an implementation plan, task breakdown, checklist, roadmap, or handoff and the outcome and direction are already selected; do not use to choose the direction or execute changes.
Skill Claude CodeCodex
Use when a broad or deep external investigation needs multiple source classes, claim-level evidence synthesis, or contradiction resolution; do not use for a narrow lookup or local code inspection.
Skill Claude CodeCodex
Use when the user asks to review, audit, critique, or validate a stable code, document, plan, artifact, or claim; do not use to diagnose an unknown failure or create the initial candidate.
Skill Claude CodeCodex
Use when the user asks to inspect, install, or refresh Teamwork-owned global surfaces; do not use as a prerequisite for another skill or to migrate project documents.