skills$openclaw/council
emasoudy4.6k

by emasoudy

council – OpenClaw Skill

council is an OpenClaw Skills integration for data analytics workflows. Council Chamber orchestration with Memory Bridge. Single session, multiple personas, structured deliberation.

4.6k stars4.4k forksSecurity L1
Updated Feb 7, 2026Created Feb 7, 2026data analytics

Skill Snapshot

namecouncil
descriptionCouncil Chamber orchestration with Memory Bridge. Single session, multiple personas, structured deliberation. OpenClaw Skills integration.
owneremasoudy
repositoryemasoudy/council
languageMarkdown
licenseMIT
topics
securityL1
installopenclaw add @emasoudy/council
last updatedFeb 7, 2026

Maintainer

emasoudy

emasoudy

Maintains council in the OpenClaw Skills directory.

View GitHub profile
File Explorer
9 files
.
references
chamber-orchestrator.sh
1.3 KB
env-check.sh
354 B
graphiti-bridge.sh
804 B
_meta.json
268 B
init-db.sh
1.9 KB
manifest.json
1.1 KB
README.md
774 B
SKILL.md
3.1 KB
SKILL.md

name: council description: Council Chamber orchestration with Memory Bridge. Single session, multiple personas, structured deliberation. metadata: {"clawdbot":{"emoji":"🏛️","requires":{"bins":["sqlite3"]},"features":{"memory_bridge":true,"chamber_pattern":true}}}

Council - Chamber Orchestration Pattern

Instead of spawning separate agent silos, create a Council Chamber where multiple expert personas deliberate in a single session with cross-pollination and unified transcript.

Prerequisites

  • SQLite3 (member database)
  • Graphiti service (Memory Bridge)
  • Clawdbot gateway (sessions_spawn)

Setup

Initialize council database:

bash command:"{baseDir}/init-db.sh"

🏛️ The Chamber Pattern

Traditional Approach (Silos):

  • Spawn 3 separate agents
  • Each analyzes independently
  • No cross-pollination
  • Fragmented output

Chamber Approach (Meeting Room):

  • Single agent session
  • Moderates multiple personas
  • Structured turn-taking
  • Unified deliberation transcript

Tools

council_chamber

Start a Council Chamber session (recommended).

Usage:

bash command:"
TOPIC='YOUR_TOPIC'
MEMBERS='architect,analyst,security'

{baseDir}/references/chamber-orchestrator.sh \"\$TOPIC\" \"\$MEMBERS\"
"

What it does:

  1. Fetches Graphiti context (Memory Bridge)
  2. Loads member personas from database
  3. Constructs chamber task with turn structure
  4. Creates session record
  5. Outputs task for sessions_spawn

council_list_members

List all registered members.

Usage:

bash command:"sqlite3 -header -column ~/.clawdbot/council.db 'SELECT id, name, role FROM council_members'"

council_add_member

Register new member.

Usage:

bash command:"
sqlite3 ~/.clawdbot/council.db \"
INSERT INTO council_members (id, name, role, system_message, expertise)
VALUES ('MEMBER_ID', 'NAME', 'ROLE', 'SYSTEM_MESSAGE', 'EXPERTISE');
\""

Chamber Session Structure

3-Turn Deliberation:

  1. Turn 1: Initial Analysis

    • Each persona provides their perspective
    • Distinct voices maintained
  2. Turn 2: Cross-Pollination

    • Members critique each other's points
    • Real-time responses
    • Healthy debate
  3. Turn 3: Synthesis

    • Find common ground
    • Resolve disagreements
    • Executive Summary for user

Default Members

IDNameRole
architectSystem ArchitectTechnical Design
analystTechnical AnalystResearch & Analysis
securitySecurity OfficerRisk Assessment
designerUX DesignerUser Experience
strategistBusiness StrategistROI & Strategy

Example

# User: "Start council on Salesforce integration"
council_chamber topic:"Salesforce Integration" members:"architect,strategist"

# Output:
# 🏛️ Convening Council Chamber...
# 🧠 Memory Bridge: [Retrieved 10 facts about Salesforce]
# 👥 Loaded 2 personas
# ✅ Chamber Task ready for sessions_spawn

Benefits:

  • ✅ Cross-pollination (members respond to each other)
  • ✅ Single transcript (one .jsonl file)
  • ✅ Shared context (Memory Bridge loaded once)
  • ✅ Structured output (3-turn deliberation)
README.md

Council - Multi-Agent Deliberation

Council Chamber pattern for structured debate with Memory Bridge integration.

Installation

clawdhub install council

Or manual:

git clone https://github.com/emasoudy/clawdbot-skills.git
cp -r clawdbot-skills/council ~/.clawdbot/skills/
~/.clawdbot/skills/council/init-db.sh

Usage

Start a council chamber:

council_chamber topic:"Your Topic" members:"architect,strategist"

Chamber Pattern: Single session with multiple personas debating, rather than separate agents.

Default Members

  • architect - System Architect
  • analyst - Technical Analyst
  • security - Security Officer
  • designer - UX Designer
  • strategist - Business Strategist

License

MIT - See LICENSE file

Permissions & Security

Security level L1: Low-risk skills with minimal permissions. Review inputs and outputs before running in production.

Requirements

- SQLite3 (member database) - Graphiti service (Memory Bridge) - Clawdbot gateway (sessions_spawn)

FAQ

How do I install council?

Run openclaw add @emasoudy/council in your terminal. This installs council into your OpenClaw Skills catalog.

Does this skill run locally or in the cloud?

OpenClaw Skills execute locally by default. Review the SKILL.md and permissions before running any skill.

Where can I verify the source code?

The source repository is available at https://github.com/openclaw/skills/tree/main/skills/emasoudy/council. Review commits and README documentation before installing.