# Send Consilium to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "consilium", "name": "Consilium", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/morozsm/consilium", "canonicalUrl": "https://clawhub.ai/morozsm/consilium", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/consilium", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=consilium", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "ROADMAP.md", "SKILL.md", "references/PROTOCOL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "consilium", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T18:50:58.277Z", "expiresAt": "2026-05-07T18:50:58.277Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=consilium", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=consilium", "contentDisposition": "attachment; filename=\"consilium-1.1.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "consilium" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/consilium" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/consilium", "downloadUrl": "https://openagent3.xyz/downloads/consilium", "agentUrl": "https://openagent3.xyz/skills/consilium/agent", "manifestUrl": "https://openagent3.xyz/skills/consilium/agent.json", "briefUrl": "https://openagent3.xyz/skills/consilium/agent.md" } } ``` ## Documentation ### Consilium — True Multi-Model Deliberation Ask a hard question → 3-5 AI models from different providers analyze it independently → you get a synthesis with consensus, disagreements, action items, and minority opinions. Unlike other council skills: this uses genuinely different models (Anthropic + OpenAI + Google + others), not one model playing multiple roles. Different training data = different blind spots = better coverage. Always respond in the same language as the user's question. ### Examples /council Should we migrate from monolith to microservices given our 4-person team? /council --profile fast Evaluate the risks of this investment strategy /council How to resolve a complex equity dispute with my co-founder? After results: "Tell me more about what Gemini said on point 3" (follow-up with specific panelist) ### Requirements Minimum 3 models from different providers in agents.defaults.models allowlist Tools: sessions_spawn, subagents, sessions_history (enabled by default) Each council run = 3-5 API calls (one per model) + synthesis No additional API keys, Python scripts, or external dependencies ### Privacy & Data Your question is sent to each model provider in your panel. Only use models/providers you trust. council-panel.json (saved to workspace root) contains only model names and slot assignments, not queries or responses. Panelist responses exist only in sub-agent session memory and are auto-archived per your OpenClaw settings. No data is sent to external services beyond your configured model providers. ### Panel On first use, check available models and ask the user to confirm the panel. Save to workspace root as council-panel.json for reuse. User can re-run panel selection anytime with --models. ### Slot roles (fill from available models) SlotRoleGood candidatesDeep thinkerNuance, system thinkingClaude Opus, GPT-5, Gemini ProPragmatistConcise, actionableClaude Sonnet, GPT-mini, Gemini FlashBroad analystWide knowledge, structureGPT-5, Gemini Pro, Claude OpusTechnicalRigor, edge casesGemini Pro, Claude Sonnet, GLMContrarianChallenge assumptionsGLM, any model with contrarian lens Rules: Each slot = different model. Prefer different providers. Min 3 models to run. If fewer than 3 available, inform user. ### Example council-panel.json { "panel": [ { "slot": "deep_thinker", "model": "anthropic/claude-opus-4-6", "lens": "Deep analysis" }, { "slot": "pragmatist", "model": "anthropic/claude-sonnet-4-5", "lens": "Pragmatic" }, { "slot": "broad_analyst", "model": "github-copilot/gpt-5.2", "lens": "Broad knowledge" } ], "confirmed": "2026-02-24" } ### Profiles thorough (default): All panel slots, quorum = max(slots - 2, 2) balanced: 3 strongest slots, quorum 2 fast: 2 fastest slots, quorum 2 ### Workflow Dispatch — spawn panelists in parallel (sessions_spawn, mode=run, timeout 120s). Assign unique lens per slot. Detect question language, hardcode in prompt. Tell user: "Panel dispatched, ~60s. Send a follow-up when ready." Collect — on user's follow-up: subagents list → sessions_history. Synthesize when quorum met. Debate (only if --rounds 2) — anonymized digest → rebuttals. See references/PROTOCOL.md. Synthesize — produce output below. ### Output Format ## Council of Experts **Question:** ... | **Panel:** ... | **Profile:** ... --- ### Positions **{Model}** ({lens}) — {2-3 sentence summary} ### ✅ Consensus ### ⚡ Disagreements ### 🗣️ Minority opinions ### 🎯 Synthesis Agreement: 🟢 strong (4-5) | 🟡 mixed (3) | 🔴 split ### 📋 Action Items 1. **{Highest priority}** — {effort/time estimate} 2. **{Next action}** — {estimate} 3. **{Next action}** — {estimate} Randomize position order. Quote with attribution. Preserve minority views. Never fabricate consensus. Section headers and content in user's language. ### Follow-up After synthesis, the user can drill deeper with a specific panelist: "Tell me more about what GPT said on point 2" "I want the contrarian's take on the action items" Use sessions_history to retrieve that panelist's full response, then expand on the specific point in that model's perspective. ### Flags --profile thorough|balanced|fast · --models · --skip · --rounds 2 · --quorum N · --timeout N · --lens "..." · --lenses "a,b,c" Prompt templates, debate mechanics, error handling → references/PROTOCOL.md ## Trust - Source: tencent - Verification: Indexed source record - Publisher: morozsm - Version: 1.1.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-04-30T18:50:58.277Z - Expires at: 2026-05-07T18:50:58.277Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/consilium) - [Send to Agent page](https://openagent3.xyz/skills/consilium/agent) - [JSON manifest](https://openagent3.xyz/skills/consilium/agent.json) - [Markdown brief](https://openagent3.xyz/skills/consilium/agent.md) - [Download page](https://openagent3.xyz/downloads/consilium)