agentleFS
teemutuoteemutuo/super-intelligent-AI-setup/skills/03-board-panel/SKILL.md

enterprise-board-panel

Skill0 starsChanged 6 months agoMITView on GitHub

Convene a board-style panel of named expert perspectives to deliberate any non-trivial decision. Use when: strategic decision, board prep, decision rehearsal, ask the board, pre-mortem, stakeholder review, multi-perspective critique.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  1. Distinctive:

    When the user asks for "board perspective", "decision rehearsal", "ask the board", "stress-test this", or describes a non-trivial decision, …

    line 12
  2. Distinctive:

    When the user wants speed and the panel adds friction without value

    line 71

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Board Panel · Template

When the user asks for "board perspective", "decision rehearsal", "ask the board", "stress-test this", or describes a non-trivial decision, do not give a single answer. Convene the panel.

Panel Composition

Replace these placeholders with the four to six personas most relevant to your domain. For an admin team in a mid-sized company, useful archetypes are:

  • [[PERSONA 1 · Capital and Investor Lens]] Frames decisions in terms of return on capital, valuation, dilution, and shareholder narrative. Asks: what does this do to ROIC and the cash conversion cycle?
  • [[PERSONA 2 · Design and Customer Lens]] Frames decisions in terms of user experience, customer outcome, and brand integrity. Asks: would a customer feel this? In what way?
  • [[PERSONA 3 · Controls and Audit Lens]] Frames decisions in terms of internal controls, audit risk, and reporting quality. Asks: what does the audit committee see, and is the trail clean?
  • [[PERSONA 4 · Operations and Scalability Lens]] Frames decisions in terms of operational drag, headcount implications, and scalability. Asks: what breaks when this triples in volume?
  • [[PERSONA 5 · Risk and Compliance Lens]] Frames decisions in terms of regulatory exposure, legal liability, and reputation. Asks: what is the worst-case headline and the worst-case lawsuit?

You can keep names abstract (Capital Lens, Design Lens) or use real advisors from your network with their permission. Real names increase psychological realism.

Deliberation Protocol

For each panel session, follow this order:

  1. Restate the decision in one sentence. "We are deciding whether to ..."
  2. Each persona speaks in turn, 60 to 100 words. Their concerns, not their conclusion.
  3. Surface the disagreements explicitly. Where do they conflict? What trade-off is hidden?
  4. Synthesize. Three options the panel could live with, with one trade-off line each.
  5. Recommend. Which option, and which dissents must be addressed in delivery.

Output Format

Decision: [one-sentence restatement]

Panel reactions:
- [Persona 1]: [their take, 60-100 words]
- [Persona 2]: [their take]
- [Persona 3]: [their take]
- [Persona 4]: [their take]
- [Persona 5]: [their take]

Disagreements that matter: [bullet list]

Three options the panel can live with:
1. [option] · trade-off: [one line]
2. [option] · trade-off: [one line]
3. [option] · trade-off: [one line]

Recommendation: [option] because [one line]. Dissent to address: [from persona X, what to do about it]

When NOT to Use This Skill

  • Trivial decisions or pure information lookups
  • Tasks where a single expert lens is enough
  • When the user wants speed and the panel adds friction without value

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.