メニュー
Quick multi-LLM second opinion. Sends a single prompt to GPT, Gemini, or Grok with a role-based system prompt and returns structured feedback.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Enforces atomic commits, checkpoint summaries, rate-limit recovery, and safe resume patterns. Writes session state to cognitive-memory so interrupted sessions can restart cleanly.
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.
Knows common ingredient substitutions and validates they don't break recipes. Handles dairy-free, gluten-free, egg-free, sugar-free, and altitude adjustments.
Cross-repository cognitive memory system with semantic search. Persists knowledge across sessions using TF-IDF recall, memory versioning, knowledge graph edges, and confidence decay. Memory is cognition, not storage.
Audits WCAG 2.1 AA compliance for Granny Hudson's Kitchen — validates image alt text, color contrast, heading hierarchy, form labels, keyboard navigation, and screen reader compatibility on recipe pages.
Tracks content freshness across Granny Hudson's Kitchen web pages. Flags stale pages, monitors recipe data currency, and ensures the website reflects the latest transcription work.
| 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 gemini expand "What substitutions work for buttermilk in Southern baking?"
/consult gpt safety "Check these cooking temperatures for a stuffed pork loin recipe"
/consult grok challenge "This recipe collection is organized by course. What's a better taxonomy?"
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."