{"id":"9ee08837-2a11-4add-9848-5e6edc51e6e3","entityType":"agent","slug":"amirbabar-ai-roundtable","name":"roundtable","canonicalUrl":"https://www.xpersona.co/agent/amirbabar-ai-roundtable","canonicalPath":"/agent/amirbabar-ai-roundtable","generatedAt":"2026-10-09T10:08:07.793Z","source":"GITHUB_OPENCLEW","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"description":"This skill should be used when the user asks to \"run roundtable\", \"roundtable brainstorm\", \"roundtable debate\", \"roundtable build plan\", \"roundtable review\", \"team debate\", \"diamond debate\", or mentions multi-agent collaboration, Diamond Architecture, or AI Roundtable workflow. Provides seven specialized AI collaboration modes for different problem types including brainstorming, refinement, build planning, build review, Opus gatekeeping, diamond debate, and team debate. --- name: roundtable description: This skill should be used when the user asks to \"run roundtable\", \"roundtable brainstorm\", \"roundtable debate\", \"roundtable build plan\", \"roundtable review\", \"team debate\", \"diamond debate\", or mentions multi-agent collaboration, Diamond Architecture, or AI Roundtable workflow. Provides seven specialized AI collaboration modes for different problem types including brainstorming, refi","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.","installCommand":"git clone https://github.com/AmirBabar/ai-roundtable.git","sourceUrl":"https://github.com/AmirBabar/ai-roundtable","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/AmirBabar/ai-roundtable","kind":"source"}],"safetyScore":94,"overallRank":29.7,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"This skill should be used when the user asks to \"run roundtable\", \"roundtable brainstorm\", \"roundtable debate\", \"roundtable build plan\", \"roundtable review\", \"t"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"No source adoption metrics were available."},"stars":0,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-04-15T02:14:18.405Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T05:21:22.124Z","lastCrawledAt":"2026-04-15T02:14:18.405Z","lastIndexedAt":null,"nextCrawlAt":"2026-04-16T02:14:18.405Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"git clone https://github.com/AmirBabar/ai-roundtable.git","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/amirbabar-ai-roundtable/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/amirbabar-ai-roundtable/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/amirbabar-ai-roundtable/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/amirbabar-ai-roundtable/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/amirbabar-ai-roundtable/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/amirbabar-ai-roundtable/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_OPENCLEW","generatedAt":"2026-10-09T10:08:07.793Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/amirbabar-ai-roundtable/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/amirbabar-ai-roundtable/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/amirbabar-ai-roundtable/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/amirbabar-ai-roundtable/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"readme":"---\nname: roundtable\ndescription: This skill should be used when the user asks to \"run roundtable\", \"roundtable brainstorm\", \"roundtable debate\", \"roundtable build plan\", \"roundtable review\", \"team debate\", \"diamond debate\", or mentions multi-agent collaboration, Diamond Architecture, or AI Roundtable workflow. Provides seven specialized AI collaboration modes for different problem types including brainstorming, refinement, build planning, build review, Opus gatekeeping, diamond debate, and team debate.\nversion: 3.0.0\nrun: python scripts/skill.py $MODE \"$@\" 2>&1\ntimeout: 300000\n---\n\n# AI Roundtable - Multi-Model AI Collaboration Platform\n\n**Version:** 3.0.0\n**Repository:** https://github.com/yourusername/ai-roundtable\n**License:** MIT\n\nA sophisticated multi-agent orchestration system that routes requests to specialized AI workflows based on intent detection. Seven distinct collaboration modes for different problem types.\n\n## Quick Start\n\n```bash\n# Clone the repository\ngit clone https://github.com/yourusername/ai-roundtable.git\ncd ai-roundtable\n\n# Install dependencies (optional - core skill works with Claude Code only)\npip install -r requirements.txt\n\n# Copy to your Claude skills directory\n# Windows:\ncopy SKILL.md %USERPROFILE%\\.claude\\skills\\roundtable\\\nxcopy /E /I scripts %USERPROFILE%\\.claude\\skills\\roundtable\\scripts\nxcopy /E /I lib %USERPROFILE%\\.claude\\skills\\roundtable\\lib\n\n# macOS/Linux:\ncp -r SKILL.md scripts lib ~/.claude/skills/roundtable/\n```\n\n## Usage\n\n```bash\n# Via Claude Code Skill tool (recommended)\n/roundtable brainstorm <prompt>\n/roundtable refine <input_text>\n/roundtable build-plan <topic>\n/roundtable build-review <summary>\n/roundtable opus-gatekeeper <query>\n/roundtable diamond-debate <topic>\n/roundtable team-debate <topic>\n\n# Via Python (direct entry point)\npython scripts/skill.py brainstorm \"Ways to improve API performance\"\npython scripts/skill.py diamond-debate \"Should we use PostgreSQL or MongoDB?\"\n```\n\n## Seven Collaboration Modes\n\n| Mode | Purpose | Execution Pattern | Output |\n|------|---------|-------------------|--------|\n| **Brainstorming** | Generate diverse ideas | Parallel light models → Synthesizer | List of prioritized ideas |\n| **Refinement** | Critical review & improvement | Series with quality gates | Refined output with critiques |\n| **Build Planning** | Detailed technical specifications | Sequential 4-step workflow | Build plan artifact |\n| **Build Reviewer** | Post-build validation | Review against criteria | Pass/Fail verdict with findings |\n| **Opus Gatekeeper** | Cost optimization | Category/budget check | INVOKE/SKIP/BUDGET_BLOCK decision |\n| **Diamond Debate** | Complex architectural decisions | PARALLEL Diamond Architecture | Comprehensive decision analysis |\n| **Team Debate** | Build specifications (alias) | SEQUENTIAL 4-step workflow | Final decree with phases |\n\n## Mode 1: Brainstorming (Parallel Idea Generation)\n\n**Use for:** Generating diverse options, exploring possibilities, creative ideation\n\n**Workflow:**\n```\nGemini Flash ─┐\nDeepSeek Chat ─┼─→ Claude Sonnet (Synthesizer) → Prioritized Ideas\nClaude Haiku ──┘\n```\n\n**Example:**\n```bash\n/roundtable brainstorm \"Ways to improve memory context injection in Claude Code\"\n```\n\n## Mode 6: Diamond Debate (PARALLEL Diamond Architecture)\n\n**Use for:** Complex architectural decisions, cross-domain analysis\n\n**Workflow:**\n```\nStage 1 (PARALLEL): kimi + perplexity → context gathering\nStage 2 (PARALLEL): deepseek + gemini-flash + sonnet → deliberation\nStage 3 (SEQUENTIAL): gemini-pro → synthesis\nStage 4 (CONDITIONAL): opus → ratification\n```\n\n**Example:**\n```bash\n/roundtable diamond-debate \"Should we use PostgreSQL or MongoDB for this project?\"\n```\n\n## Mode 7: Team Debate (Sequential 4-Step Workflow)\n\n**Use for:** Creating build specifications, iterative refinement\n\n**Workflow:**\n```\nStep 1: gemini-architect → proposes solution\nStep 2: deepseek-v3 → critiques proposal\nStep 3: kimi-researcher → codebase-aware analysis\nStep 4: opus-synthesis → final decree\n```\n\n**Example:**\n```bash\n/roundtable team-debate \"Design a new authentication system\"\n```\n\n## Optional Components\n\nThe core skill works with Claude Code's native capabilities. For enhanced functionality:\n\n### LiteLLM Gateway (Optional)\n\nEnables multi-model routing:\n\n```bash\n# Install LiteLLM\npip install litellm\n\n# Copy example config\ncp litellm/config.yaml.example litellm/config.yaml\n\n# Start gateway\nlitellm --config litellm/config.yaml --port 4000\n```\n\n### Dashboard (Optional)\n\nWeb UI for monitoring debates and memory:\n\n```bash\ncd dashboard\npip install -r requirements.txt\npython start_dashboard.py\n```\n\n### Memory Subsystem (Optional)\n\nPersistent context across sessions:\n\n```bash\ncd memory\npython init_db.py\n```\n\n## Configuration\n\nModel configurations are in `config/models.yaml` (create from `models.yaml.example`):\n\n```yaml\nmodels:\n  brainstorm:\n    - gemini-flash\n    - deepseek-chat\n    - claude-haiku\n  build_planning:\n    architect: gemini-architect\n    auditor: deepseek-v3\n    contextualist: kimi-researcher\n    judge: opus-synthesis\n```\n\n## Documentation\n\n- **`docs/ARCHITECTURE.md`** - Complete system architecture\n- **`docs/INSTALLATION.md`** - Detailed installation guide\n- **`docs/CONFIGURATION.md`** - Configuration reference\n- **`docs/TROUBLESHOOTING.md`** - Common issues and solutions\n\n## Version History\n\n| Version | Date | Changes |\n|---------|------|---------|\n| **3.0.0** | 2026-02-09 | Public distribution release |\n| **2.1.2** | 2026-02-06 | Hallucination Safeguards |\n| **2.1.0** | 2026-01-30 | diamond-debate and team-debate modes |\n| **2.0.0** | 2026-01-28 | Diamond Architecture v2 |\n| **1.0.0** | 2025-01-15 | Initial release |\n\n## License\n\nMIT License - see LICENSE file for details.\n\n## Contributing\n\nContributions welcome! Please see CONTRIBUTING.md for guidelines.\n\n---\n\n*AI Roundtable - Multi-Model AI Collaboration Platform*\n","readmeExcerpt":"--- name: roundtable description: This skill should be used when the user asks to \"run roundtable\", \"roundtable brainstorm\", \"roundtable debate\", \"roundtable build plan\", \"roundtable review\", \"team debate\", \"diamond debate\", or mentions multi-agent collaboration, Diamond Architecture, or AI Roundtable workflow. Provides seven specialized AI collaboration modes for different problem types including brainstorming, refi","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# Clone the repository\ngit clone https://github.com/yourusername/ai-roundtable.git\ncd ai-roundtable\n\n# Install dependencies (optional - core skill works with Claude Code only)\npip install -r requirements.txt\n\n# Copy to your Claude skills directory\n# Windows:\ncopy SKILL.md %USERPROFILE%\\.claude\\skills\\roundtable\\\nxcopy /E /I scripts %USERPROFILE%\\.claude\\skills\\roundtable\\scripts\nxcopy /E /I lib %USERPROFILE%\\.claude\\skills\\roundtable\\lib\n\n# macOS/Linux:\ncp -r SKILL.md scripts lib ~/.claude/skills/roundtable/"},{"language":"bash","snippet":"# Via Claude Code Skill tool (recommended)\n/roundtable brainstorm <prompt>\n/roundtable refine <input_text>\n/roundtable build-plan <topic>\n/roundtable build-review <summary>\n/roundtable opus-gatekeeper <query>\n/roundtable diamond-debate <topic>\n/roundtable team-debate <topic>\n\n# Via Python (direct entry point)\npython scripts/skill.py brainstorm \"Ways to improve API performance\"\npython scripts/skill.py diamond-debate \"Should we use PostgreSQL or MongoDB?\""},{"language":"text","snippet":"Gemini Flash ─┐\nDeepSeek Chat ─┼─→ Claude Sonnet (Synthesizer) → Prioritized Ideas\nClaude Haiku ──┘"},{"language":"bash","snippet":"/roundtable brainstorm \"Ways to improve memory context injection in Claude Code\""},{"language":"text","snippet":"Stage 1 (PARALLEL): kimi + perplexity → context gathering\nStage 2 (PARALLEL): deepseek + gemini-flash + sonnet → deliberation\nStage 3 (SEQUENTIAL): gemini-pro → synthesis\nStage 4 (CONDITIONAL): opus → ratification"},{"language":"bash","snippet":"/roundtable diamond-debate \"Should we use PostgreSQL or MongoDB for this project?\""}],"parameters":{},"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["typescript"],"docsSourceLabel":"GITHUB OPENCLEW","editorialOverview":"This skill should be used when the user asks to \"run roundtable\", \"roundtable brainstorm\", \"roundtable debate\", \"roundtable build plan\", \"roundtable review\", \"team debate\", \"diamond debate\", or mentions multi-agent collaboration, Diamond Architecture, or AI Roundtable workflow. Provides seven specialized AI collaboration modes for different problem types including brainstorming, refinement, build planning, build review, Opus gatekeeping, diamond debate, and team debate. --- name: roundtable description: This skill should be used when the user asks to \"run roundtable\", \"roundtable brainstorm\", \"roundtable debate\", \"roundtable build plan\", \"roundtable review\", \"team debate\", \"diamond debate\", or mentions multi-agent collaboration, Diamond Architecture, or AI Roundtable workflow. Provides seven specialized AI collaboration modes for different problem types including brainstorming, refi","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":405,"uniquenessScore":60,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T10:08:07.793Z","emptyReason":null},"items":[{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_openclew","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}