rbergman/brainstorm
plugins/teams/skills/brainstorm/SKILL.md
Multi-perspective brainstorming using Agent Teams. Spawn 2-3 teammates with different analytical angles who explore a design space simultaneously while the human observes and steers via the lead. Falls back to dm-work:brainstorming for simpler design work.
$ install --global
skillsauthnpx skillsauth add rbergman/dark-matter-marketplace brainstormInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 22, 2026, 3:23 PM58.8s1 file scanned
SKILL.md
- name:
- brainstorm
- description:
- Multi-perspective brainstorming using Agent Teams. Spawn 2-3 teammates with different analytical angles who explore a design space simultaneously while the human observes and steers via the lead. Falls back to dm-work:brainstorming for simpler design work.
Team Brainstorm
Multi-perspective brainstorming using Agent Teams.
When to use team brainstorming
- Complex design decisions with multiple valid approaches
- When you want perspectives you wouldn't naturally consider
- Architecture that spans multiple domains (frontend + backend + infra)
- When 1:1 brainstorming would take too long to explore all angles
When to use dm-work:brainstorming instead
- Simple feature design
- When human wants direct interactive dialogue
- When the design space is small (2-3 obvious approaches)
- Token budget is a concern
Default perspectives
| Role | Analytical frame | Model | |------|-----------------|-------| | User Advocate | Focuses on UX, simplicity, user goals | opus | | Technical Skeptic | Finds complexity, maintenance burden, failure modes | opus | | Creative Explorer | Proposes unconventional approaches, challenges assumptions | opus |
Lead adds/replaces perspectives based on the specific domain.
Protocol
Phase 1 — Context (lead)
- Review project context (files, docs, commits)
- Frame the design question for teammates
- Assign perspectives
Phase 2 — Parallel exploration (teammates, simultaneous)
- Each teammate explores the design space from their angle
- They share early findings with each other
- Cross-pollination encouraged — build on each other's ideas
Phase 3 — Convergence (lead + human)
- Lead summarizes perspectives for the human
- Human steers: "I like the skeptic's point about X, but the explorer's idea about Y"
- Iterate until design crystallizes
Phase 4 — Design document (lead)
- Write validated design to
docs/plans/YYYY-MM-DD-<topic>-design.md - Include which perspectives informed which decisions
Comparison with dm-work:brainstorming
| Aspect | dm-work:brainstorming | dm-team:brainstorm | |--------|----------------------|------------------------| | Interaction | 1:1 dialogue | Multi-perspective team | | Speed | Faster for simple designs | Faster for complex designs | | Token cost | Lower | Higher | | Perspectives | Sequential (one at a time) | Simultaneous | | Best for | Simple features, quick decisions | Complex architecture, trade-off heavy |
Related
- dm-work:brainstorming — 1:1 alternative
- dm-team:council — for decisions, not designs
- dm-team:compositions — brainstorm team template
Related Skills
rbergman/repo-init
development
VerifiedTrustedCommunity
Initialize a new repository with standard scaffolding - git, gitignore, AGENTS.md, justfile, mise, beads, and timbers. Use when starting a new project or setting up an existing repo for Claude Code workflows.
5SKILL.mdUpdated Apr 22, 2026
rbergman/lead
data-ai
VerifiedTrustedCommunity
Activate at session start when using Agent Teams for complex multi-agent work. Establishes team lead role with delegation protocols, teammate spawning, model selection, and beads integration. You coordinate the team; teammates implement.
5SKILL.mdUpdated Apr 22, 2026
rbergman/worktrees
data-ai
VerifiedTrustedCommunity
Use when creating a worktree, setting up a worktree, starting feature work that needs isolation, or before executing implementation plans. Covers git worktree creation under .worktrees/, gitignore setup, beads integration, and merge guardrails.
4SKILL.mdUpdated Apr 22, 2026
rbergman/subagent
data-ai
VerifiedTrustedCommunity
Activate when you are a delegated subagent (not the orchestrator). Establishes subagent protocol with terse returns, details to history/, file ownership boundaries, and escalation rules. You implement; orchestrator reviews and commits.
4SKILL.mdUpdated Apr 22, 2026