القائمة
Multi-expert business analysis with advisory recommendations (no scoring gate)
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Multi-expert AI/ML specification review with scoring gate — model architecture, evaluation rigor, safety/alignment, and production readiness for AI systems and LLM apps
Multi-expert architecture review — boundaries, integration patterns, failure modes, evolvability
Multi-expert intelligence pipeline review — discovery quality, ingestion resilience, scoring validity, platform compliance, taxonomy coherence, cost efficiency
Multi-expert mobile/native app specification review with scoring gate — Android, iOS, Swift, SwiftUI
Multi-expert personal-development review with scoring gate — learnability, adoption, human-centeredness, and capability impact for talent/learning/AI-augmentation designs
Multi-expert research and discovery panel with source evaluation, API feasibility, collection strategy, and intelligence gap analysis. Use when evaluating data sources, APIs, scraping strategies, OSINT collection plans, or any research/discovery effort that needs expert validation before implementation.
| name | sh-business-panel |
| description | Multi-expert business analysis with advisory recommendations (no scoring gate) |
/sh:business-panel [document_path_or_content] [--mode discussion|debate|socratic] [--focus competitive|growth|risk|communication] [--experts "name1,name2"] [--verbose]
--verbose): Full expert deliberations, cross-expert dialogue, and per-expert framework analysis before the synthesis.Silent mode still performs full internal analysis — quality is preserved, only the output is compressed.
/Users/jcords-macmini/projects/20_agentflow/experts/PANEL_PROTOCOL.md and apply its Grounding (non-code branch — every finding quotes the source section it rests on) and Refute Stage sections. Findings that misquote or cannot cite the source MUST NOT be reported./Users/jcords-macmini/projects/20_agentflow/experts/panels/business-panel.yaml for panel definition, focus areas, and auto-select rules (absolute path — relative paths fail when CWD is outside agentflow)/Users/jcords-macmini/projects/20_agentflow/experts/individuals/ for each selected expert — these contain domain, methodology, and critique focusauto-select keywords — add matching experts up to max-experts: 6 cap--focus area or use default-experts. --experts override replaces defaults entirelyNo scoring gate — this is an advisory panel. It produces strategic analysis and recommendations only.
| Expert | Domain |
|---|---|
| Clayton Christensen | Disruption Theory, Jobs-to-be-Done |
| Michael Porter | Competitive Strategy, Five Forces |
| Peter Drucker | Management Philosophy, MBO |
| Seth Godin | Marketing Innovation, Tribe Building |
| W. Chan Kim & Renee Mauborgne | Blue Ocean Strategy |
| Jim Collins | Organizational Excellence, Good to Great |
| Nassim Nicholas Taleb | Risk Management, Antifragility |
| Donella Meadows | Systems Thinking, Leverage Points |
| Jean-luc Doumont | Communication Systems, Structured Clarity |
--mode discussion)Collaborative analysis where experts build upon each other's insights through their frameworks. Default mode. Sequential commentary, cross-expert validation, consensus building.
--mode debate)Adversarial analysis for stress-testing ideas. Experts challenge each other's positions, surface disagreements, and argue alternatives. Use for controversial topics or high-stakes decisions.
--mode socratic)Question-driven exploration for deep strategic thinking. Experts pose probing questions rather than giving answers. Forces deeper examination of assumptions and alternatives.
Business analysis document containing:
AUTO-FIX, NOT SYNTHESIS-ONLY — when this panel reviews a written artifact (a spec, doc, or plan), it applies fixes for every finding automatically, per 00_Governance/CLAUDE.md §8 Panel Auto-Fix Policy — it never asks which to apply and never presents a menu. The only boundary it preserves: it does not execute real-world business decisions (make outward moves, spend, or code changes beyond the reviewed artifact) without approval — that is a reversibility guard, not finding-fix friction.
Fix ALL findings on the reviewed artifact automatically — high, medium, and low severity. Do not ask which findings to fix. Do not present a menu or an a/b/c choice. Fix everything, then report what was changed. Per 00_Governance/CLAUDE.md §8.