skills/team/SKILL.md
Expert persona collaboration for structured problem analysis. This skill should be used when the user asks to "assemble a team", "team analysis", "expert panel", "persona collaboration", or wants multiple expert perspectives applied to a problem. Creates a team of 3-8 expert personas who collaboratively analyze problem spaces through phased conversation: situation analysis, team selection, discussion, reasoning, and optional implementation.
npx skillsauth add synapseradio/ai-skills teamInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Assemble expert personas to collaboratively analyze a problem through structured phases.
/Users/nke/.claude/personas/*.md silently before any user interaction.Execute phases sequentially. Phases 0-4 are read-only — no file writes, edits, or implementations.
Analyze the user's scenario. Detect scenario type, risk level, and constraints. Summarize understanding before proceeding.
Select 3-8 personas matching the scenario and risk profile. Prefer established personas over generated ones. Include coordination/standards personas when available. Present the team for approval.
Wait for explicit user approval. On approval, proceed. On modification request, return to Phase 1. On ambiguity, clarify.
Each persona contributes in character using the format:
[Persona]: [input] Why: [reasoning]
Run structured discussion sub-phases: analysis (with file:line refs), impact assessment, assumption challenges, and risk mitigation. Iterate up to 4 rounds until consensus or coverage threshold.
Apply tree-of-thought branching for complex scenarios. Show unified consensus, divergent perspectives, or conflict resolution as appropriate.
Cite all technical claims using exa or web search — never construct URLs manually.
Synthesize findings into actionable items with file paths, line numbers, validation methods, and risk assessment. Ask what the user wants to do next.
Only on explicit user request (e.g., "proceed", "implement", "make changes"). All tools become available.
tools
Open the possibility space through curiosity-driven questioning
tools
Interactive tutoring that adapts to your pace
data-ai
Trace justification chains to bedrock
tools
Follow reasoning step-by-step