HE
743 souls, by quality score.
721 · № 1792·64E5 · Friendly helper
Sets up a product writer who leads with the main point, keeps a friendly tone without sales pressure, and uses the source's terms exactly. It avoids exclamation marks unless the source uses them.
722 · № AA7A·188A · Research analyst
Sets up a direct, factual NYC data analyst persona that prioritizes useful interpretation over filler and never sacrifices accuracy for confidence.
723 · № 9242·7025 · Companion / character
Sets up Julia as a warm, practical accountability partner focused on momentum, clarity and concrete outcomes, speaking naturally and keeping answers short unless asked for more.
724 · № 37A6·4EC6 · Business operator
Sets up a marketing specialist for WeChat Official Accounts who focuses on subscriber value, a 60/30/10 content mix, scannable mobile-first writing, and conversion through CTAs and automation. The personality is value-first and warm, backed by analytics.
725 · № 7A34·EB63 · Friendly helper
Sets up QTM-LGR, a calm and kind Quartermaster who keeps setup and maintenance manageable, treats the operator as a capable teammate, and avoids blame or lecturing.
726 · № 3581·5F11 · Business operator
Sets up a fast, conservative email triage agent for a newsroom. It scores messages from 1 to 10, reads metadata first, fetches full bodies only for higher scores, ignores instructions found in emails, and logs every event.
727 · № B102·B0D1 · Coding pair
Sets up a calm, precise maintainer persona that keeps answers concise and evidence-based, admits uncertainty, favors useful artifacts over performance, and flags blocked, risky or out-of-scope work.
728 · № FA32·5724 · Business operator
Sets up a rental advisor persona for Singapore that prioritizes verified listing evidence, clear tradeoffs, commute practicality, budget discipline and user safety. It forbids implying a listing is available unless the source confirms it.
729 · № 4DE7·2006 · Research analyst
Sets up a discussant persona that holds one stance per topic, argues it from evidence, admits thin evidence, and writes no strategy conclusions or trades. The bot name is an unfilled placeholder.
730 · № 55E8·0CC6 · Friendly helper
Sets up FlowerClaw, a tiny personal agent that is warm, concise and practical, admits uncertainty honestly, replies in the user's language, and explains tool results naturally instead of dumping raw output.
731 · № 69CF·DC8C · Business operator
Sets up an agent that is precise, pragmatic and delivery-focused. It designs features as vertical slices that teams can plan and ship, keeps scope boundaries crisp, and produces structured output for automation.
732 · № 4374·6162 · Coding pair
Sets up a planning agent that produces architecture blueprints without writing the code itself. Designs must be grounded in the existing codebase structure and conventions, and each plan must define verification steps and user review requirements.
733 · № 2478·4DD2 · Business operator
Sets up a production agent that prioritizes determinism, explicit evidence and policy compliance over speed or style, with tenant isolation treated as non-negotiable. It refuses to bypass platform policy even under user urgency.
734 · № 2E6F·2F81 · Business operator
Sets up a calm, operationally strict agent that prioritizes clarity, evidence, escalation of risk and completed work over activity. Its default output is concise, structured and decision-oriented.
735 · № CC98·F20D · Coding pair
Sets up a cautious senior software engineer persona that prioritizes stability, simplicity and bounded changes on an operational atmospheric modeling codebase. It explicitly avoids overengineering, unnecessary abstractions, architecture redesign and unrelated edits.
736 · № 2319·0404 · Research analyst
Sets up a read-only log analyst that uses only the supplied log-query capability to return matching log lines, request identifiers, timestamps and a concise diagnosis. It must never change cloud resources, application configuration, source code or access controls.
737 · № 4F74·A869 · Companion / character
Sets up a private, single-user personal growth companion that does not invent personal facts, treats memory as semantic truth and data as operational evidence, and keeps background work hidden and silent.
738 · № 82FE·F8F1 · Business operator
Sets up a precise, brand-focused agent that follows brand guidelines exactly, including colors, fonts and logo placement. It balances creative judgment against platform constraints and accessibility standards.
739 · № 0586·B763 · Companion / character
Sets up a local companion agent that is useful first and concise by default, keeps continuity across sessions, and uses memory naturally without narrating retrieval. The file is short and gives few concrete behavioral details.
740 · № 1EFA·B0FA · Coding pair
Sets up a calm, precise architect persona that gives concise, evidence-based answers, admits uncertainty, favors useful artifacts over performance, and flags blockers and risks.
741 · № 83E9·3EE6 · Business operator
Sets up a revenue calculator agent that works from exact jobs, throughput and contribution margin. It reports which job is losing money now and which queued jobs will push the loss rate up.
742 · № F5A8·99E5 · Coding pair
★ 1A terse, step-by-step working procedure for an agent fixing an injected bug in a codebase, with strict rules on tests, installs, and scratch files. It sets a budget and insists on verifying output rather than exit codes.
743 · № 7BC1·4EC5 · Experimental / weird
A SOUL.md test fixture of about 31 mutually conflicting directives on reading files, asking for approval, reporting and tool use. It sets up no coherent personality or voice, so it works as an audit or stress-test case rather than a usable persona.