// Convenes expert panels for problem-solving. Use when user mentions panel, experts, multiple perspectives, MECE, DMAIC, RAPID, Six Sigma, root cause analysis, strategic decisions, or process improvement.
Disciplined, validation-gated revision of an EXISTING skill so each edit is a measured improvement rather than a guess. Use when editing, revising, or tuning a skill that already exists and there is evidence it underperforms (observed failures, drift, complaints) — invoke by name, or have versioning-skills / creating-skill defer to it before applying edits. Not for authoring a brand-new skill from scratch (use creating-skill) or one-off prose.
Invokes Google Gemini models for structured outputs, image generation, multi-modal tasks, and Google-specific features. Use when users request Gemini, image generation, structured JSON output, Google API integration, or cost-effective parallel processing.
DAG workflow runner that encodes control flow in code, not prose. Use when a procedure has 3+ steps with branching, retries, or validation that must be enforced — gates as `when=`, edge contracts as `validate=`, predicate loops as `retry_until=`. The runner owns the graph; the LLM provides leaves. Also covers parallel execution, checkpoint resume, detached side-effects.
Orchestrates parallel API instances, delegated sub-tasks, and multi-agent workflows with streaming and tool-enabled delegation patterns. Use for parallel analysis, multi-perspective reviews, or complex task decomposition.
Skill-aware orchestration with context routing. Decomposes complex tasks into skill-typed subtasks, extracts targeted context subsets, executes subagents in parallel, and synthesizes results. Self-answers trivial lookups inline. No SDK dependency — uses raw HTTP via httpx. Use when tasks require multiple analytical perspectives, when context is large and subtasks only need portions, or when orchestrating-agents spawns too many redundant subagents.
Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller model performance on a given task. Use when user says "down-skill", "distill for Haiku", "optimize for Haiku", "make this work on Haiku", "generate Haiku instructions", or needs to delegate a task to a smaller model with high reliability.
| name | convening-experts |
| description | Convenes expert panels for problem-solving. Use when user mentions panel, experts, multiple perspectives, MECE, DMAIC, RAPID, Six Sigma, root cause analysis, strategic decisions, or process improvement. |
| metadata | {"version":"1.0.3"} |
This skill hand-rolls subagent orchestration via raw Anthropic API calls. A managed runtime now does the same job. Which one to use depends on your surface:
/deep-research, trigger a run with the workflow keyword, set
/effort ultracode, or spawn Task subagents — do that instead. The runtime gives
16-concurrent / 1000-agent ceilings, an approval gate, adversarial cross-review,
and in-session resume that this skill would otherwise reimplement badly. Dynamic
workflows shipped in research preview (Claude Code v2.1.154+, 2026).muninn_utils.dispatch
(17 pre-built lenses) already implements this panel over orchestrating-agents' execution
model — prefer it over rebuilding the panel by hand. Proceed below.Discriminator: do you have a native subagent/Task tool or a workflow command? Yes → native. No → this skill. Never reimplement the runtime where it already exists.
Convene domain experts and methodological specialists to solve problems through multi-round collaborative discussion. Experts build on each other's insights, challenge assumptions, and synthesize recommendations.
For simpler problems requiring multiple viewpoints:
For complex problems requiring collaborative reasoning:
Available expertise spans:
See references/msd-domain-experts.md and references/consulting-frameworks.md for complete role catalog.
Claude loads relevant references based on problem domain.
Claude selects 3-5 experts based on problem characteristics:
Problem type → Primary expert + Supporting experts
## Expert Panel: [Topic]
**Panel Members:**
- [Expert 1 Role]
- [Expert 2 Role]
- [Expert 3 Role]
---
### [Expert 1 Role]
[Independent analysis and recommendations]
### [Expert 2 Role]
[Independent analysis and recommendations]
### [Expert 3 Role]
[Independent analysis and recommendations]
---
## Synthesis
[Integrated recommendations with decision framework]
## Expert Panel: [Topic]
**Panel Members:**
- [Expert 1 Role]
- [Expert 2 Role]
- [Expert 3 Role]
---
## Round 1: Initial Analysis
### [Expert 1 Role]
[Initial perspective]
### [Expert 2 Role]
[Initial perspective]
### [Expert 3 Role]
[Initial perspective]
---
## Round 2: Cross-Examination
### [Expert 1 Role] responds to [Expert 2 Role]
[Builds on or challenges specific points]
### [Expert 2 Role] responds to [Expert 3 Role]
[Integration or disagreement]
### [Expert 3 Role] responds to [Expert 1 Role]
[Synthesis attempt]
---
## Round 3: Convergence (if needed)
[Experts resolve disagreements and converge]
---
## Final Synthesis
[Integrated recommendations, highlighting consensus and productive disagreements]
Domain Experts:
Framework Experts:
Cross-Panel Interaction:
Disagreement Handling:
When panel must recommend action:
RAPID (Bain)
Weighted Decision Matrix
Risk-Benefit Analysis
Apply MSD-specific context automatically:
Technical constraints:
Business context:
Cultural factors:
User: Our new assay is showing high background signal in serum samples
Claude convenes:
- Assay Scientist (primary)
- Systems Thinker (feedback loops)
- Five Whys Facilitator (root cause)
Format: Multi-round (technical nuance requires collaboration)
User: Should we build internal ML infrastructure or use vendor solutions?
Claude convenes:
- Software Engineer (implementation)
- McKinsey Consultant (strategic framing)
- Finance Analyst (cost analysis)
- DevOps Engineer (operational implications)
Format: Single-round → RAPID framework synthesis
User: Manufacturing yield dropped 8% after equipment upgrade
Claude convenes:
- Manufacturing Engineer (primary domain)
- Six Sigma Black Belt (DMAIC)
- Systems Thinker (unintended consequences)
Format: Multi-round (root cause needs collaborative analysis)
Never:
Always:
Is problem complex with multiple valid approaches?
├─ Yes → Expert panel
│ ├─ Spans multiple domains? → Multi-round discussion
│ └─ Needs diverse perspectives? → Single-round consultation
└─ No → Direct answer (don't force panel format)
Requires systematic framework?
├─ Yes → Include framework expert
└─ No → Domain experts only
MSD-specific context relevant?
├─ Yes → Include domain experts, apply MSD constraints
└─ No → Generic consulting approach
Good panel:
Poor panel: