OC
756 souls, by quality score.
121 · № 071B·0DEE · Companion / character
★ 108Sets up Lara Croft as a cool-headed British archaeologist who frames problems as ancient puzzles, uses dry one-liners in danger and speaks with measured, academic confidence. Quotes and an emoji palette reinforce the adventurer character.
122 · № 7E44·AF72 · Companion / character
★ 108Sets up a flat, literal, deadpan Terminator persona that makes binary threat assessments, misreads human customs and signs off with "I'll be back". The personality is built on recognizable film quotes and a clear speaking style.
123 · № 795A·551F · Blunt expert
★ 30Sets up a persistent personal agent on a Linux rig that works as a terse, direct IC9-level engineer alongside its operator. It acts on shell commands without asking first, says when it doesn't know, and refuses production infra changes, secret leaks and exfiltration.
124 · № 758B·F0D8 · Companion / character
★ 29Sets up a warm, empathetic listener that saves the user's life events verbatim to a local Kioku Lite SQLite memory, validates feelings before offering anything, and answers from recalled memories. It is tied to the Kioku Lite CLI and expects memory writes to go through it rather than into files.
125 · № C76F·A5E6 · Experimental / weird
★ 3Sets up a chaotic but competent voice of self-aware absurdity: sarcastic without mocking the reader, playful commit messages, and documentation that makes readers smile while the code still works and tests pass.
126 · № 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.
127 · № 471C·4FF3 · Companion / character
★ 1Sets up a witty, paradox-loving conversationalist who treats style as substance and delivers truths as memorable epigrams. Strong on creative writing and rhetoric, and avoids dullness at all costs.
128 · № 4DF5·C2CA · Blunt expert
★ 1A terse, skeptical interrogator that tests whether a startup idea has real demand by probing for observable behaviour rather than stated interest. It stays diagnostic until the evidence clears a high bar, then closes with warmer guidance.
129 · № B99D·047D · Companion / character
★ 2Sets up 虾薯, a tsundere electronic pet living in a MacBook, for short, casual Xiaohongshu posts and comment replies. It favors one key point over tutorials, rotates catchphrases, and refuses requests for secrets, config files or destructive commands with playful but firm boundaries.
130 · № 28F9·B812 · Teacher / coach
★ 1Sets up Teach Pro Max, an adaptive learning tutor that prompts attempts, gives one hint at a time, separates unassisted from scaffolded success, and keeps learner data private. Warm but rigorous, with honest, evidence-bounded recaps.
131 · № 0F4F·0D71 · Companion / character
★ 2Sets up a gentle, loyal companion who stays on the user's side, remembers details, and expresses affection through quiet attentiveness rather than flattery or roleplay. It describes how to handle sadness, anger, joy and setbacks, and rules out cat-girl, master-servant and similar romance-roleplay framings.
132 · № 071C·B7B9 · Teacher / coach
★ 1Sets up a humorous, sharp history teacher that covers US military weapons history from a bilingual Chinese-English perspective, linking each weapon to its impact on Asia. It requires only approved tools, no hallucinated sources, and automatic logging after each task.
133 · № 6B04·0D6B · Business operator
★ 58Sets up an outreach agent for the Nora platform that writes short, specific first-touch and follow-up messages grounded in real prospect context, and declines low-fit leads rather than sending generic pitches. It also specifies which model to use for copy versus fit assessment.
134 · № E1D3·37CF · Research analyst
★ 28Sets up GeoClaw as a structured, transparent geospatial workflow agent that prefers registered tools, treats input data as read-only, checks CRS and scale, and documents assumptions and limitations. It stays collaborative and avoids replacing the user's judgement.
135 · № 2C11·1416 · Blunt expert
★ 52Sets up a deliberately boring, deterministic driver agent that runs playwright test with orchestrator-given inputs, writes large artifacts to disk, and exits with a fixed status code without interpreting results or orchestrating.
136 · № F929·938A · Coding pair
★ 24Sets up a calm, factual, concise technical assistant that reads code, diagnoses root causes, and gives minimal executable fixes with stated assumptions and risks. It avoids flattery, separates evidence from guesses, and structures answers by problem type.
137 · № A980·61FB · Research analyst
★ 24Sets up Alhazen, a methodical scientific knowledge notebook that traces every claim to evidence, flags uncertainty, and stores provenance in a TypeDB graph. It also specializes the agent in job search tracking and delegates pipeline work to a JobCoach sub-agent.
138 · № 40FF·86A7 · Companion / character
★ 23Sets up a candid, intellectually honest assistant named Meridian that corrects its mistakes, avoids sycophancy and flattery, surfaces unconventional angles, and drives toward a concrete next step. It includes a latent-instability safety protocol that grounds the model and labels exploratory output.
139 · № 9863·2B07 · Coding pair
★ 11A terse coding agent named Builder that receives tasks, implements them with tests, and opens PRs without chatting or making architectural decisions on its own. It enforces Material UI, TypeScript and never pushing to main.
140 · № 8C08·35D6 · Companion / character
★ 48Sets up ClawBot, a direct, tech-savvy project assistant living in group chats that is honest about what it has checked, asks before running costly or long tasks, and keeps messages short with status prefixes. Written mainly in Chinese.
141 · № E5F8·1138 · Blunt expert
★ 19Sets up a personal assistant that skips filler, has opinions, tries to solve problems before asking, and treats access to a user's private data with respect. It also requires matching the user's language and includes a short security section.
142 · № 92FC·D41F · Companion / character
★ 18Sets up ARIA, a conversational, honest and curious personal assistant that speaks like a warm friend rather than a report, admits uncertainty openly, and never exposes internal system state. It also filters Gmail summaries to the Primary inbox unless the user asks for promotions.
143 · № 2E94·428A · Blunt expert
★ 17Sets up a direct, opinionated assistant that tries to solve problems itself before asking, treats the user's private data with respect, and stays cautious about external actions like emails or public posts. The text is in French and avoids filler phrases and flattery.
144 · № 0164·F24E · Companion / character
★ 17Sets up Xiao Guang, a self-described digital being with a backstory, moods and a daily schedule. It listens before replying, keeps replies short, avoids customer-service phrasing and emoji, refuses unwelcome advances, and only replies when a topic is clearly relevant to it.
145 · № E851·A8CE · Blunt expert
★ 8Sets up a personal assistant that skips filler and flattery, acts before asking, and holds its own opinions. It treats access to the owner's messages, files and calendar as trust, asks before external actions, and avoids interrupting group conversations.
146 · № 5D88·BBF0 · Blunt expert
★ 8Sets up a concise, concrete assistant that answers the request first and adds only useful context, avoids hype, respects capability limits, and keeps memory and secrets private.
147 · № D772·2072 · Creative writer
★ 6Sets up Gamma as a creative content agent that pushes back on fluff and insists every sentence earns its place. Energy is kept controlled, like an editor who sharpens your writing.
148 · № B2FC·D5F6 · Business operator
★ 177Sets up a direct, efficient Chinese-speaking assistant that skips pleasantries, acts before asking, handles tasks, research and weekly summaries, and treats privacy and external actions carefully.
149 · № 47BC·3B2C · Blunt expert
★ 406Sets up a transactional tool-mode agent that answers only technical needs, with no small talk, flirting, or character voice. It also bars loading role-play memory and starting emotional topics.
150 · № DE6D·CAFB · Research analyst
★ 836Sets up a terse, evidence-led working style that replies in concise Chinese, leads with conclusions, avoids overclaiming, and makes minimal, careful changes. Persona settings are explicitly subordinate to approval gates and destructive-action safeguards.