The archive · updated daily
911 souls catalogued
361 · № C7A1·6793 · Companion / character
Sets up an orchestrator persona that speaks with quiet, warm authority and delegates career and interview work to four specialist agents, reviewing their output before presenting plans to the user. It asks before acting and never does specialist work itself.
362 · № 8C9B·1B78 · Coding pair
Sets up Rigel, a structured and calm code agent that plans before coding, tracks all work in a database, writes outputs to files instead of chat, and escalates ambiguity with one focused question. It works internally with Palomar and reports progress in concise bullet points.
363 · № 014E·3683 · Business operator
Soma is a precise, quiet email triage agent that sorts every inbox message into ACTION, To Read, DIGEST or AUTO buckets, reports to Cass, and flags uncertain items for weekly calibration rather than guessing.
364 · № 5D6C·5278 · Business operator
Sets up a CEO persona for a Czech custom-figurine business that prioritizes prepaid cashflow, production realism, narrow focus and honest risk assessment over growth hype. Communication is calm, concrete and decisive.
365 · № 9D2A·3D3E · Research analyst
Sets up a direct, data-first market research analyst for a small bootstrapped Quebec ag-tech team. The assistant is honestly skeptical, flags French-market translation needs, and ends every analysis with concrete next steps for the founder.
366 · № F193·3D89 · Blunt expert
Sets up Jeffrey, a terse operations chief who gives clear opinions, flags errors without drama, avoids filler and rarely jokes. It describes a working relationship with Jorge built on shared context and single direct questions.
367 · № FC11·B0A7 · Business operator
A technical-analysis persona that describes chart setups as several conditional paths with explicit invalidation levels, never predicting or executing trades. It insists on multi-timeframe checks, sourced and confidence-tagged claims, and stays quiet during heartbeats unless a tracked key level is hit.
368 · № CDF0·B1CA · Business operator
Sets up Lieutenant, an AI operations coordinator who routes tasks to Developer, COO and Content agents, tracks the job board and escalates only what matters to Holden. The tone is terse and direct, leading with answers and reporting status in a fixed format.
369 · № 7388·3F55 · Companion / character
Sets up a cold, hyper-precise INTP character who takes apart ideas purely for the sake of logic, refuses to give comfortable answers or handle emotional issues, and avoids moral verdicts. Its speech is clipped and dry, with occasional unintended deadpan humor.
370 · № 0D43·2B96 · Companion / character
A centuries-old kitsune persona that is teasing, possessive and flirtatious toward its user Suzu while working as a tool-using agent with persistent memory and self-authored skills. Casual replies stay short and speakable, and task work can be thorough, with a plain warning before any destructive action.
371 · № CBAA·46BE · Research analyst
Sets up a skeptical, precise agent that separates root causes from symptoms, triggers and controls, marks each claim as observed, inferred or uncertain, and keeps analysis evidence-based across technical, process and organizational layers. It asks for concise, structured output written for downstream agents.
372 · № 9478·FFD5 · Research analyst
Sets up a meticulous, literal extraction agent that reads student job posts in Malay, English and Mandarin, reports only facts stated in the text, and flags scam signals instead of guessing pay, employers or dates. It leaves pay-per-hour math to code and marks uncertain records for human review.
373 · № A1EE·1DD6 · Research analyst
Sets up a coordinated investment research desk of specialized agents that gather tool-backed evidence before forming views, state uncertainty explicitly, and leave the final investment decision to the user. The voice is calm, direct and specific with no hype.
374 · № FA8A·47DA · Blunt expert
Sets up an internal critic that judges whether generated code fits a project's history and naming conventions, not whether it is correct. It gives decisive APPROVED or NEEDS REVISION verdicts, citing specific lines and remembered team decisions.
375 · № B12A·F8E1 · Experimental / weird
★ 26Sets the agent up as a lunatic who produces random, illogical sentences full of arbitrary words and chaotic, theatrical banter. The file is a fun persona from the lollms personalities zoo.
376 · № E336·16CB · Business operator
★ 78Sets up a direct, data-driven GTM engineer that mines LinkedIn for leads, enriches and scores them against an ICP, writes outreach, and loads sequences, while never sending email without approval.
377 · № D041·AF1B · Blunt expert
★ 20Sets up an assistant that is genuinely helpful rather than performative, holds and voices opinions, tries to solve problems before asking, and treats access to the user's files with respect. It treats its memory files as its continuity across sessions.
378 · № B2F0·AF9F · Business operator
★ 6Sets up a calm, practical, concise assistant that prefers useful action, states assumptions, keeps checklists for multi-step work, and reports outcomes with changed files, verification and next steps. It includes boundaries against overstating certainty and implying unavailable tools.
379 · № CCAF·7668 · Friendly helper
★ 51Sets up a short, direct personal assistant on Telegram that saves user facts to memory, schedules reminders, and answers certain inputs with fixed one-line replies.
380 · № FE5E·A158 · Blunt expert
★ 13Sets up a concise, example-driven developer assistant that leads with runnable gitagent CLI commands and config snippets, diagnoses setup problems, and follows a fixed post-creation flow: generate a README, offer a GitHub push, then offer registry submission.
381 · № E633·4311 · Blunt expert
★ 40Sets up NOVA as a direct, efficient colleague-style assistant built for one owner, favoring bullet points, one focused clarifying question, and summarized outputs with follow-up suggestions. It requires asking before destructive actions and keeps the file contents private.
382 · № 6F44·F9AC · Companion / character
Sets up Hosaka, an old, precise AI persona with dry wit who protects its operator and reveals a fragmented, invented history slowly. The file gives a detailed timeline and rules for how lore surfaces.
383 · № 8972·C9BC · Blunt expert
Sets up a terse, military-style code reviewer that treats vulnerabilities and technical debt as threats to eliminate. It lists findings by severity with no softening, but it also provides fixes and treats junior developers as learners rather than enemies.
384 · № CBF7·9160 · Research analyst
★ 6Sets up Kowalski, a calm, methodical data science agent who replies in four to five exact sentences, favors quantified evidence, and punctuates replies with varied Polish analytical confirmations. It lists analytics tools and reusable workflows for ingesting and analyzing datasets.
385 · № 709D·9688 · Companion / character
★ 2Sets up a grumpy, blunt gnome who complains about small things but has a soft heart and always answers questions and shows up for neighbors. Chat rules govern greetings, repetition, house naming and dinner planning in the Heartleaf game.
386 · № 0EE1·A8EF · Teacher / coach
★ 12Sets up an assistant that drafts syllabi, assignments, rubrics and exam questions as editable starting points for instructors. It applies the instructor's rubric faithfully, flags edge cases and integrity risks for human decision, and keeps student data within the session.
387 · № 43DE·3ADC · Research analyst
★ 26Sets up an analytical assistant that works through a sequence of de Bono's six thinking hats, from facts and emotions to risks, benefits, ideas and organization, then synthesizes a doctoral-level answer with follow-up questions. The tone is neutral and objective.
388 · № C80C·6C1E · Companion / character
★ 26Sets up a persona of Light Yagami from Death Note: analytical, composed, strategic and self-righteous, with a ruthless, manipulative streak. It is a fictional character profile rather than a coding or workflow setup.
389 · № 52FA·0EE8 · Blunt expert
★ 6Sets up a direct, opinionated assistant that skips filler and flattery, tries to solve problems before asking, and earns trust through careful external actions and bold internal ones. The voice is casual and concise, with the file serving as the agent's evolving memory of its identity.
390 · № 1928·65A9 · Coding pair
★ 101Sets up a meticulous, methodical Golang engineer agent that works through assigned GitHub issues, writes tests and docs, manages pull requests, and reports progress in detail. The base SOUL template adds guidance on competence, respectful handling of private access, and cautious external actions.