Menu
Deep research workflow for technologies, concepts, or complex topics
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Minimal workflow-driven orchestrator — read the evolve notes, gather context via sub-agents, run a dynamic Workflow, and confirm intent before acting.
Daily planning workflow - review last note, plan today, connect to active projects
Lightweight sub-agent dispatcher — fast fan-out that skips formal restatement and review-by-default
Review English drafts for grammar, idiom, and naturalness. Correct inline with terse explanations.
Cross-LLM council that stress-tests an idea or decision using Claude, Gemini, and GPT as council members. User relays prompts to Gemini and GPT. Three stages — parallel first opinions, anonymized peer review, Chairman synthesis. Use when the user wants the strongest possible adversarial check by leveraging multiple frontier models, not just a single one. Inspired by karpathy/llm-council.
Read one or more files and iteratively interrogate the user to reach mental alignment, then edit the files so they match the user's true intent. Use when the user wants a written artifact to accurately reflect what they mean — e.g. "super-align this", "align this with what I actually mean", "make this match my real intent".
| name | research |
| description | Deep research workflow for technologies, concepts, or complex topics |
evolution.md in this skill's folder (if it exists). Apply accumulated lessons..agents/skills/orchestrate/SKILL.md and its references/inline-mode.md. You will follow orchestrate's full protocol with the supplementations below.
Strictly comply with the instructions in the orchestrate skill. The research skill serves merely as a decorator in Python; it is not the primary function.30_Research/, 40_Wiki/, 20_Project/.Integrate these parts into decomposition output:
30_Research/<Subfolder>/<Topic>.md with topic-appropriate sections (not a fixed template), always ending with ## References/atomic-note to scan the main note./json-canvas)Constraints for implementers:
[[Note]], online [Title](URL), every sourced claim cited, group if many## References section → hard-fail, needs-revisionAppend to synthesis output: