菜单
Quick multi-LLM second opinion. Sends a single prompt to GPT, Gemini, or Grok with a role-based system prompt and returns structured feedback.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Enforces atomic commits, checkpoint summaries, rate-limit recovery, and safe resume patterns. Writes session pulses + cognitive memory so interrupted sessions can restart cleanly.
Evaluate sheep matings and pipeline placement against a performance-based checklist. Select by FAMACHA/FEC first, hair/wool second, breed third, meat fourth. Manages a 7-pen closed-loop breeding pipeline toward a hardy, hairy, meaty, parasite-resistant composite flock.
Bridges the Google Sheets spreadsheet (primary flock data source) with local flock_database.json. Eliminates manual export. Validates changes against careful-not-clever principles.
Round-robin multi-LLM consultation with full-context debate. GPT proposes, Gemini refines, Grok challenges — each sees the full chain including wheat/chaff verdicts and justifications. Nothing is filtered between rounds.
Tracks FAMACHA scores and health trends per animal over time. Flags animals trending toward anemia before they're critical. Links health data to breeding decisions.
Plans pasture rotation for Florida sheep operation. Considers parasite pressure, seasonal grass growth, pen capacity, and rest periods for larval die-off.
| name | consult |
| description | Quick multi-LLM second opinion. Sends a single prompt to GPT, Gemini, or Grok with a role-based system prompt and returns structured feedback. |
One model. One question. Structured feedback.
/consult <model> <role> "prompt text"
/consult gpt plan "Review this breeding plan for the spring Katahdin pairings"
/consult gemini expand "What veterinary research supports FAMACHA scoring for hair sheep in Florida?"
/consult grok challenge "We're prioritizing parasite resistance over growth rate. What are we missing?"
IMPORTANT: Execute these commands directly using the Bash tool. Do NOT check if files exist first — just run them.
bash /home/user/ken/orchestrator/bootstrap-env.sh 2>/dev/null; pip3 install -q -r /home/user/ken/orchestrator/requirements.txt 2>/dev/null && python3 /home/user/ken/orchestrator/consult.py <model> <role> "prompt text"
Output: JSON response to stdout with keys: analysis, proposed_update, risks, confidence
Usage stats: Printed to stderr (model, tokens, cost)
Only if the command fails with No such file or directory or ModuleNotFoundError, tell the user:
"The orchestrator backend isn't available. Make sure the ken repo is cloned to
/home/user/ken/and runpip3 install -r /home/user/ken/orchestrator/requirements.txt."
claims, verify against flock records.