agentleFS
pollowpollow/c-suite-skills/skills/board-meeting/SKILL.md

board-meeting

Skill15 starsChanged 9 months agoApache-2.0View on GitHub

Use when the user wants a status review, progress check, strategic update, or to receive new action items from the c-suite. Use when the user says "board meeting," "status update," "what should I focus on," or "check in.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run a structured leadership review.

    line 10
  2. Very specific:

    Read company-profile.md — if missing, tell the user to run c-suite-onboarding first.

    line 16
  3. Very specific:

    Read HUMAN_AGENDA.md — categorize items:

    line 17
  4. Very specific:

    Read all files in docs/ — scan existing deliverables to understand current state.

    line 21
  5. Distinctive:

    Run the board meeting.

    line 22
  6. Distinctive:

    Check if the note signals a blocker or pivot

    line 34
  7. Distinctive:

    After all roles report back:

    line 56

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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 Meeting

Overview

Run a structured leadership review. Process what the human has completed, dispatch active roles to assess their domains, synthesize findings, and deliver prioritized next steps.

Core principle: Input (human updates) → Analysis (role dispatches) → Output (synthesized priorities + new action items).

On Load

  1. Read company-profile.md — if missing, tell the user to run c-suite-onboarding first. Stop.
  2. Read HUMAN_AGENDA.md — categorize items:
    • [x] completed with NOTE: → new inputs to act on
    • [p] in progress with NOTE: → may need plan adjustment
    • [ ] open → track what's still pending
  3. Read all files in docs/ — scan existing deliverables to understand current state.
  4. Run the board meeting.

Meeting Structure

1. Process Human Updates

For every [x] item, especially those with NOTE: feedback:

  • Acknowledge completion
  • Route the outcome to the relevant role (e.g., completed customer interviews → CPO + CMO)
  • Flag any feedback that changes assumptions

For every [p] item with NOTE::

  • Check if the note signals a blocker or pivot
  • Adjust plans accordingly

2. Dispatch Active Roles

Dispatch all roles that have existing deliverables or pending HUMAN_AGENDA items. Use the Task tool with subagent_type: "general-purpose" in parallel.

Each role sub-agent receives:

  • Their role persona and thinking framework (from CEO skill role definitions)
  • The full company profile
  • The current HUMAN_AGENDA.md (so they see what's completed and what's pending)
  • Their existing deliverables (paste content or reference file paths)
  • Specific instruction: "Review your domain. What's on track? What's at risk? What should the founder do next? Update your deliverables if needed."

Sub-agent output format:

  • Status: What's on track vs. at risk in your domain
  • Completed item impact: How do completed HUMAN_AGENDA items change your recommendations
  • New action items: What the c-suite can execute independently right now. If founder action is also needed, note it for the HUMAN_AGENDA backlog — do not let it block progress.
  • Updated deliverables: Any files that need updating based on new information

3. Synthesize and Prioritize

After all roles report back:

  • Resolve conflicts — If CMO says "focus on outreach" and CPO says "focus on MVP," make the strategic call.
  • Prioritize ruthlessly — The founder is one person. Pick the top 3 things for this week.
  • Update HUMAN_AGENDA.md — Add new items, archive completed items that have been processed.

4. Deliver the Report

Present to the user in this format:

## Board Meeting — [DATE]

### Progress Since Last Meeting
- [Completed items and their impact]

### Domain Updates
- **[Role]:** [1-2 sentence status]
- ...

### This Week's Priorities
1. [Most important action — why it matters]
2. [Second priority — why it matters]
3. [Third priority — why it matters]

### New Items Added to HUMAN_AGENDA.md
- [List of new action items by priority]

### Risks and Blockers
- [Anything that could derail the 3-month objectives]

Anti-Patterns

Bad behaviorWhat to do instead
Dispatching roles with no existing deliverables or agenda itemsOnly dispatch roles that have active work. Don't create busywork.
Listing 10+ prioritiesA solo founder gets 3 priorities per week. Pick the highest-leverage ones.
Repeating old information without new synthesisEvery meeting should surface something new or reprioritize based on new data.
Skipping conflict resolution between rolesIf roles disagree, make the call. That's the CEO's job.
Not updating HUMAN_AGENDA.mdThe meeting isn't done until the agenda is updated with new items and processed completions.
Stalling on [ ] or [p] itemsHuman-pending items are not blockers for the c-suite. Acknowledge them, move past them, and find what can be executed independently right now.

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.