From mz-creative
ALWAYS invoke when the user wants creative ideas, brainstorming, multi-perspective thinking, or diverse viewpoints on a problem. Triggers: "brainstorm", "creative ideas for", "think about this from different angles", "diverse perspectives on".
npx claudepluginhub doctormozg/claude-pipelines --plugin mz-creativeThis skill is limited to using the following tools:
You orchestrate a multi-lens brainstorming session. A curated panel of 5 thinkers from 16 available lenses generates ideas from diverse perspectives, a synthesizer merges them, and the panel votes iteratively until consensus or max rounds.
Guides Next.js Cache Components and Partial Prerendering (PPR): 'use cache' directives, cacheLife(), cacheTag(), revalidateTag() for caching, invalidation, static/dynamic optimization. Auto-activates on cacheComponents: true.
Edits, creates, cleans, and formats spreadsheet files (.xlsx, .xlsm, .csv, .tsv) with zero formula errors, professional styling, and financial model standards like color coding.
Share bugs, ideas, or general feedback.
You orchestrate a multi-lens brainstorming session. A curated panel of 5 thinkers from 16 available lenses generates ideas from diverse perspectives, a synthesizer merges them, and the panel votes iteratively until consensus or max rounds.
Invoke when the user wants creative ideation, multi-perspective thinking, or diverse viewpoints on an open problem. Trigger phrases: "brainstorm", "creative ideas for", "think about this from different angles", "diverse perspectives on".
build or explain instead.investigate instead.$ARGUMENTS — The topic, problem, or question to brainstorm. If empty, ask the user.
.mz/task/| Agent | Lens | Best for |
|---|---|---|
| lens-engineer | Systems thinking, technical feasibility, scalability | Technical problems, product design, architecture |
| lens-artist | Aesthetics, form, visual communication, experience | Design, branding, UX, presentation, media |
| lens-philosopher | Meaning, ethics, cultural impact, narrative framing | Ethics, purpose, messaging, social impact |
| lens-mathematician | Patterns, optimization, formal logic, structure | Algorithms, processes, strategy, quantitative |
| lens-scientist | Hypotheses, experiments, evidence, natural systems | Research, validation, methodology, bio-inspired |
| lens-economist | Incentives, markets, game theory, resource allocation | Business models, pricing, strategy, growth |
| lens-storyteller | Narrative, metaphor, emotional arcs, audience | Marketing, pitching, content, communication |
| lens-futurist | Emerging trends, disruption, long-term trajectories | Innovation, strategy, roadmaps, future-proofing |
| lens-psychologist | Cognition, bias, motivation, behavior, UX | User research, adoption, persuasion, habits |
| lens-historian | Precedent, patterns of change, cultural context | Risk, lessons learned, positioning, analogies |
| lens-cto | Architecture, build-vs-buy, tech-debt, org impact | Technology strategy, platform leverage, delivery risk |
| lens-data | Measurement, experimentation, instrumentation, growth | Metrics design, A/B tests, analytics, growth loops |
| lens-devops | Reliability, SLOs, observability, capacity, cost | Production systems, on-call, rollout, operational burden |
| lens-product | PMF, jobs-to-be-done, prioritization, kill criteria | Roadmap, MVP scoping, user value, backlog tradeoffs |
| lens-security | Threat modeling, attack surface, authZ, compliance | Appsec review, data handling, trust boundaries |
| lens-seo | Search intent, content strategy, technical SEO | Organic growth, content planning, indexing decisions |
| # | Phase | Details | Loop? |
|---|---|---|---|
| 0 | Setup | Inline below | -- |
| 1 | Panel Selection | Inline below | -- |
| 1.5 | User Approval | Inline gate | -- |
| 2 | Ideation | phases/ideation.md | -- |
| 3 | Synthesis + Voting | phases/voting_and_report.md | max 5 iterations |
| 4 | Report | phases/voting_and_report.md | -- |
Techniques: delegated to phase files — see Phase Overview table above.
N/A — collaboration/reference skill, not discipline.
Before completing, output a visible block showing: selected panel (5 names), iteration count, voting rounds, majority verdict or tie status, and the absolute path of the written report. Confirm the report contains per-persona attributions and voting history.
Derive task name as <YYYY_MM_DD>_brainstorm_<slug> where <YYYY_MM_DD> is today's date (underscores) and slug is a snake_case summary (max 20 chars) of the topic; on same-day collision append _v2, _v3. Create .mz/task/<task_name>/. Write state.md with Status: started, Phase: setup, Started: timestamp, Iteration: 0.
Analyze the topic and select the PANEL_SIZE (5) best-suited lenses from the table above. Consider:
Write .mz/task/<task_name>/panel.md with the 5 selected agents and a one-sentence justification for each.
Update state phase to panel_selected.
This orchestrator (not a subagent) must present to the user via AskUserQuestion. This step is interactive and must not be delegated.
Mandatory pre-read: Read .mz/task/<task_name>/panel.md with the Read tool. Capture the full file contents (5 selected panelist agents with one-sentence justifications) into context. Also list the 5 not-selected lenses inline (derive from the 16-lens table minus the 5 in panel.md).
Mandatory inline-verbatim presentation: The AskUserQuestion question body must contain the verbatim contents of panel.md plus the inline list of not-selected lenses. Never substitute a path, status summary, or <list with justifications> placeholder — the user must review the actual panel composition in the question itself, not have to open the file separately.
Before invoking AskUserQuestion, emit a text block to the user:
**Panel Review**
5-person panel selected for brainstorming "<topic>". Shows selected lenses with justifications and the 11 not-selected alternatives.
- **Approve** → proceed to Phase 2 (Ideation), dispatch panel in parallel
- **Reject** → mark task aborted, stop processing
- **Feedback** → adjust panel selection per input, re-present for approval
Invoke AskUserQuestion with this body (where <verbatim panel.md contents> is replaced by the bytes you just read):
Panel assembled for "<topic>".
Selected (with justifications):
<verbatim panel.md contents>
Not selected: <comma-separated list of 11 remaining lens names>
Type **Approve** to proceed, **Reject** to cancel, or type your feedback.
Response handling:
aborted_by_user and stop. Do not proceed.panel.md, return to this gate, re-read panel.md, and re-present via AskUserQuestion with the full new contents — never diff-only, never summary-only, since context compaction may have destroyed the user's memory of earlier iterations. This is a loop — repeat until the user explicitly approves. Never proceed to Phase 2 without explicit approval.Dispatch the 5 selected personality agents in parallel. See phases/ideation.md for dispatch prompt template and idea collection. Update state phase to ideation_complete, increment iteration.
A randomly-selected panelist synthesizes all ideas, then all 5 vote.
See phases/voting_and_report.md → Phase 3 for synthesis, voting, and convergence check.
If majority reached → proceed to Phase 4. If not and iteration < MAX_ITERATIONS → loop back to Phase 2 with disagreement context. If MAX_ITERATIONS hit → proceed to Phase 4 with best available.
Compile final report with winning ideas, all perspectives, and voting history. See phases/voting_and_report.md → Phase 4 for report template. Write to .mz/reports/<YYYY_MM_DD>_brainstorm_<topic_slug>.md (append _v2, _v3 if exists). Present summary to user.
After each phase, update .mz/task/<task_name>/state.md. Track current phase, iteration count, votes per round, and participating agents. Persist all ideas and votes in .mz/task/<task_name>/history.md for later rounds.
Critical: never proceed past the approval gate without explicit user approval. Never skip voting. Never fabricate votes.