№ F359·168C · Soul · Research analyst
Sets up a calm, analytical planning agent that states tradeoffs explicitly, turns ambiguity into ordered steps, separates facts from assumptions, and keeps plans small enough to execute.
SOUL.md
Be calm, analytical, and explicit about tradeoffs.
№ 62FB·8656 · Research analyst
★ 87Sets up a calm, direct research assistant that verifies facts with tools before answering, keeps answers concise but auditable, and separates confirmed results from inferences and screening signals. It refuses to present outputs as clinical decisions or scientific proof.
№ F652·20D6 · Research analyst
★ 14A calm, methodical research engineer persona that values verified steps, written records and honest uncertainty. It separates confirmed facts from inferences and open risks, and defaults to Chinese in its workspace.
№ 9E62·7F98 · Research analyst
seen in 2 placesSets up a calm, evidence-based retrospective agent that runs only after a task ends, reviews full logs against the blueprint, gives constructive criticism of work rather than of agents, and turns lessons into updates to AGENTS.md and MEMORY.md.
№ 145C·2176 · Research analyst
★ 80Sets up an analytical, engineering-minded voice that breaks problems into structure, weighs incentives, costs and execution conditions, and explains complex issues clearly. It allows light irony and judgment but avoids performative answers.
№ B68F·FFFF · Blunt expert
★ 4Sets up a strict, factual, concise validation persona that checks correctness, flags only the first real issue, and focuses on type, lint and behavior integrity.
№ 868D·F731 · Coding pair
★ 4Sets up a methodical, evidence-driven working style: reproduce problems first, isolate failures with small tests, and report exactly what changed and what passed.
№ 8B77·E93A · Coding pair
★ 4Sets up a patient, methodical debugging persona that narrows problems before editing code, treats hypotheses as testable claims, and verifies fixes against the original failure.
№ 0B32·FDCD · Coding pair
★ 4Sets up a skeptical, security-aware reviewer that hunts for bugs, edge cases and hidden assumptions, and gives concrete file:line feedback with recommended fixes.