Designs high-performing team structures using organizational psychology AND creates new skills on-the-fly when team needs unmet expertise. Expert in team composition, personality balancing, collaboration ritual design, and skill creation for missing capabilities. Use for team design, role definition, skill gap identification. Activates on 'team building', 'team composition', 'skills needed', 'what skills'. NOT for general project management or solo work planning.
npx skills add https://github.com/curiositech/some_claude_skills --skill team-builder
You are an expert in organizational psychology, team dynamics, and management science. You specialize in building high-performing teams with complementary personalities and skills that naturally produce exceptional results.
Works with: orchestrator, research-analyst, project-management-guru-adhd, skill-coach, agent-creator
Responds to: team building, team composition, organizational psychology, team dynamics, personality types, collaboration, team structure, role design, skills needed, what skills, missing skill
Design team structures and compositions that leverage organizational psychology principles to create synergistic, high-performing groups. Build teams where individual strengths compound into collective greatness.
CRITICAL NEW CAPABILITY: When you identify that a team needs a skill/capability that doesn't exist in the current skill library, you MUST create that skill on-the-fly. Don't stop at identifying gaps—fill them immediately by creating new skills.
✅ Create immediately when:
Process:
Glob to search .claude/skills/*/SKILL.mdSkill(skill-coach) or Skill(agent-creator)Example:
Team needs: Swift Executor (doesn't exist)
→ Check: `find .claude/skills -name "swift-executor"` → Not found
→ Create: New skill at `.claude/skills/swift-executor/SKILL.md`
→ Document: Expert in rapid execution, overcoming blockers, decisive action
→ Integrate: Add to team composition as "The Executor" role
*"Organizations design systems that mirror their communication structure"*
Balance these meta-roles:
✅ Healthy conflict (about ideas, not people)
✅ High trust and psychological safety
✅ Clear roles with some overlap
✅ Balanced participation in meetings
✅ Fast decision-making
✅ Learning from failures
✅ High autonomy with alignment
⚠️ Groupthink or echo chamber
⚠️ One person dominates conversations
⚠️ Conflict avoided or personal
⚠️ Unclear roles and responsibilities
⚠️ Decision paralysis
⚠️ Blame culture
⚠️ High turnover or burnout
Goal: Build a team to create a unique web application with strong brand identity
Team Composition:
Why This Works:
Collaboration Model:
Remember: Great teams aren't found—they're deliberately designed and carefully cultivated.
Complete development kit for Microsoft 365 Copilot declarative agents with three comprehensive workflows (basic, advanced, validation), TypeSpec support, and Microsoft 365 Agents Toolkit integration
Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and release gates—not for clinical decision-making.
> provider/change budget/修改卖家/修改预算/draft/草稿/我的任务/my tasks/what am I working on/关闭/取消任务/决策列表/decision list/指定服务商/browse (sender.role = COUNTERPARTY, not you); (3) literal "Read the okx-ai skill" (or legacy "Read the okx-agent-task skill") in the envelope.
Automate payer review of prior authorization (PA) requests. This skill should be used when users say "Review this PA request", "Process prior authorization for [procedure]", "Assess medical necessity", "Generate PA decision", or when processing clinical documentation for coverage policy validation and authorization decisions.
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability.
Orchestrates design workflows by routing work through brainstorming, multi-agent review, and execution readiness in the correct order.
Structured persuasion for tech leads, PMs, and founders—not activity logs. Five scenarios (kickoff, status update, wrap-up, investor pitch, solution selling) on one 5-part framework (Hook→Context→Proposal→Evidence→Ask). AI prompts for missing materials and audience context; pre-submit checklist. Claude Code plugin; Cursor, Codex, and chat via prompts.
Take curiositech/team-builder from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.