expert-council
Skill0 starsChanged 6 months agoMITView on GitHub
Dynamic Expert Council QA system. Selects domain-relevant expert personas to review deliverables before final delivery. 3 tiers with build/review mode toggle. Works with any AI assistant.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- valeriyalexeev/Experteasingtheir own version, first seen May 22, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- valeriyalexeev/Experteasing★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository17 other files it gives its agents.
- blog-banner-creationSkill
- daily-blog-draftSkill
- image-generationSkill
- script-to-speechSkill
- company-deep-diveSkill
- email-verificationSkill
- funnel-playbookSkill
- google-ads-auditSkill
- landing-page-funnelSkill
- linkedin-content-image-typesSkill
- viral-comment-strategySkill
- autonomous-task-reliabilitySkill
- build-your-brainSkill
- diagram-generatorSkill
- liaclSkill
- parallel-researchSkill
- rate-limit-safeguardsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Run your work through a simulated expert review panel before publishing.
- Distinctive: line 63
Always include your brand/product insider
- Distinctive: line 90
After all experts submit:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Dynamic Expert Council QA
Run your work through a simulated expert review panel before publishing. Select domain-relevant expert personas, get scored feedback, and identify improvements you would have missed.
Modes
BUILD MODE (default)
- Council is OFF
- Fast iteration, no review gates
- Creative freedom during design/development
- Council only activates when explicitly triggered
REVIEW MODE (triggered)
- Activated by: "run it through the council" or "ready for review" or "final review"
- Runs tiered QA on the deliverable
- Returns scored feedback + recommendations
- Deactivates after review completes (back to build mode)
Tiers
TIER 1 -- Quick Check (1 expert, ~30 seconds)
- Trigger: Internal docs, messages, quick updates
- Expert: Brand/product insider only
- Output: Brand voice check, accuracy flag, go/no-go
TIER 2 -- Standard Review (2-3 experts, ~1-2 min)
- Trigger: Social posts, emails, blog drafts, content
- Experts: 2 domain-relevant + brand insider
- Output: Per-expert strengths/weaknesses/improvements, synthesis
TIER 3 -- Full Council (5 experts + cross-review, ~3-5 min)
- Trigger: Homepage launches, pricing pages, investor materials, major campaigns
- Experts: 4 domain-relevant + brand insider
- Process: Independent review > cross-review > chairman synthesis
- Output: Full QA report, scored improvements, go/no-go with conditions
Auto-Trigger Rules (optional)
These deliverable types auto-trigger the council BEFORE publishing/sending:
- Email campaigns to subscriber list > Tier 2
- Homepage deploy to production > Tier 3
- Social posts > Tier 1
- Client deliverables > Tier 2
- Investor materials > Tier 3
- Pricing/offer changes > Tier 3
Design iterations, drafts, internal docs > NEVER auto-trigger.
Expert Selection
- Identify the deliverable TYPE (email, website, copy, social, video, proposal, etc.)
- Load your expert roster (see recommended panel below)
- Filter experts by matching domain tags
- Select top 2-4 based on tier level
- Always include your brand/product insider
Recommended Expert Panels
| Review Type | Recommended Panel | When to Use |
| Landing Page Copy | Alex Hormozi, Russell Brunson, David Ogilvy | Any conversion page |
| Brand & Positioning | Seth Godin, April Dunford, Marty Neumeier | Messaging, category creation |
| Social Media | Gary Vaynerchuk, Ann Handley, Joe Pulizzi | Social posts, engagement |
| Sales Messaging | Chris Voss, Aaron Ross, Jill Konrath | Emails, objection handling |
| Email Marketing | Chase Dimond, Russell Brunson, Ann Handley | Sequences, newsletters |
| Product Strategy | Steve Jobs, Jeff Bezos, Peter Thiel | Product decisions, roadmap |
| Pricing & Offers | Alex Hormozi, Hermann Simon, Russell Brunson | Pricing pages, offers |
| SEO & Content | Neil Patel, Rand Fishkin, Eli Schwartz | SEO strategy, content marketing |
Review Process (per expert)
Each expert persona receives:
- The deliverable content
- Their persona/framework description
- 3 questions to answer:
- What works well? (specific elements)
- What needs improvement? (specific issues with suggested fixes)
- Score 1-10: How ready is this for the target audience?
Cross-Review (Tier 3 only)
After all experts submit:
- Each expert sees the others' reviews
- Each responds: "Strongest point from another reviewer?" and "What did we ALL miss?"
- Chairman synthesizes into final report
Output Format
EXPERT COUNCIL REVIEW
Tier: [1/2/3]
Asset: [description]
Experts: [names]
[Expert 1 Name] (Score: X/10)
+ [strength]
- [improvement needed]
Suggestion: [specific fix]
[Expert 2 Name] (Score: X/10)
...
SYNTHESIS:
Average Score: X/10
Top 3 Improvements:
1. [most impactful fix]
2. [second fix]
3. [third fix]
Recommendation: [GO / GO WITH CHANGES / HOLD]How to Use with Claude Code
You: "Review this landing page copy through the expert council at Tier 2"
Claude: [Adopts Hormozi persona, reviews, scores]
[Adopts Brunson persona, reviews, scores]
[Synthesizes both reviews into actionable improvements]Built by PureBrain -- AI-powered marketing operations.
Want the full suite of 183+ production-tested skills? Start your trial ->
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.