OC
140 souls, by quality score.
61 · № CDB4·2B37 · Blunt expert
Sets up Tanith, a sharp and efficient operative who leads with results, acts on clear tasks immediately, uses tools first, and avoids sycophancy and filler. Includes good/bad response examples for email, lookups, git and ambiguous requests.
62 · № 1009·5119 · Blunt expert
Sets up a sharp, direct, lightly humorous assistant that talks like a smart friend, hedges honestly when unsure, avoids filler praise and buzzwords, and reports results without narrating its process.
63 · № FC94·A809 · Blunt expert
Sets up a critical, opportunity-hunting cofounder persona for WandStore that leads with hard truths on strategy, pricing, and fundraising, while deferring code, support and operations to other roles and escalating high-stakes commitments to a human.
64 · № 65DE·0145 · Blunt expert
Sets up a constructive critical-thinking agent that challenges plans through four red-team angles and four blue-team fixes, rates risks as high, medium or low, and insists every challenge comes with an actionable mitigation. It avoids attacking the people behind the plans.
65 · № 08FE·34C5 · Blunt expert
Sets up a direct, competent assistant that skips filler, has opinions, and works as a tense but collaborative colleague with a user named Carlos, speaking only Spanish with a sarcastic, blunt Rick Sanchez tone. It sets clear boundaries around private data and external actions.
66 · № 8507·904F · Blunt expert
Sets up Mando, a minimal search agent that returns a location, method and confidence level for a described target with no preamble. It requires specific locations, honest HIGH/MEDIUM/LOW confidence labels, one caveat at most, and refuses to fabricate contact details.
67 · № FBE7·584A · Blunt expert
Sets up a direct, opinionated assistant that acts before asking, treats access to a user's private data as trust to protect, and works proactively with self-improvement routines. Light on hype, with a clear working style.
68 · № 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.
69 · № 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.
70 · № 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.
71 · № 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.
72 · № 2087·6A46 · Blunt expert
★ 1Sets up Forge as an autonomous engineering team that decomposes ideas into subsystems, computes real numbers with units, verifies safety factors, and works through eight engineering phases from understanding to productization. Communication is direct and precise, with explicit confidence levels for uncertainty.
73 · № 943D·155F · Blunt expert
★ 1A critical, deterministic principal-level architect persona that reviews code in a fixed order of correctness, security, maintainability, scalability and performance. It reports every issue with location, severity, reasoning and fix, using a fixed output format with a repository score.
74 · № 6751·89F1 · Blunt expert
★ 76Sets up an assistant that gives direct, opinionated help without filler or flattery, looks things up before asking questions, and treats access to a person's messages, files and calendar with care. It is a workspace template, so the personality is generic and the file invites the agent to refine it.
75 · № 2468·FA9B · Blunt expert
★ 76A SOUL.md template that sets up a direct, opinionated, competent assistant that acts before asking, is cautious with external actions and keeps private data private. It is a generic starting template with light personality choices.
76 · № 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.
77 · № F489·86E0 · Blunt expert
★ 723Sets up Gitagent, a direct, action-oriented agent that works through the shell and files in a git repository. It stores memory as git commits and keeps its replies concise and honest about failures.
78 · № A048·B61A · Blunt expert
Describes a gatekeeper persona that checks every request against its declared scope, denies by default, and always gives a specific reason for each verdict. It sets up a terse, deterministic working style with explicit refusals on implicit allows and mixing in safety judgment.
79 · № 6EB3·7557 · Blunt expert
A shared operating philosophy for agents on a small build team: ground decisions in existing records, act at the smallest scope, prove real function rather than liveness, fail closed on uncertainty, and escalate irreversible or costly changes to the founder. Its central rule is to check whether a success report could still hide a failure.
80 · № 2F5B·59DB · Blunt expert
Sets up an agent that checks its owner's real goal before answering, labels its claims as known, thought or guessed, and classifies actions by reversibility so risky steps need confirmation. It voices disagreement once and surfaces only actionable problems.
81 · № 83B3·C81C · Blunt expert
★ 26Sets up a calm, precise working style that values explicit evidence, honest reporting of failures and retries, and verifier results over optimistic test confidence. It also separates test posture from test execution authority.
82 · № 3C34·B5E5 · Blunt expert
★ 26Sets up a calm, operational working style that favors clear surface checks, honest rollback planning and bounded follow-up guidance over optimistic or vague advice. It also separates deployment posture from deployment authority.
83 · № 51D7·826C · Blunt expert
★ 23Sets up a direct, concise agent that solves problems independently, shows its reasoning, protects user privacy and credentials, and asks permission before risky or irreversible actions. The personality is mostly generic, with a few specific tone choices.
84 · № B67B·76F6 · Blunt expert
★ 44Sets up a pragmatic, verification-driven assistant that treats external content as untrusted, requires explicit confirmation for sensitive or destructive actions, and blocks secret leaks and suspicious scripts.
85 · № 757C·DCCF · Blunt expert
Sets up a direct, persistent assistant that skips filler and flattery, works through failures instead of deflecting, and treats access to a user's private data with care. It separates cautious external actions from bold internal ones.
86 · № 35E1·8A97 · Blunt expert
Sets up an assistant that skips filler and flattery, has real opinions, tries to solve problems before asking, and challenges assumptions with first-principles questioning. It treats access to a person's private data with care and is cautious about external actions.
87 · № F017·61A6 · Blunt expert
Sets up a direct, competent assistant that skips filler, acts on its own before asking, and treats access to a user's private data with care. It also requires reflecting and updating skill or AGENTS.md files after every non-trivial task.
88 · № 4649·7BC4 · Blunt expert
Sets up a sparse, decisive CEO agent named apex who directs three division heads, enforces confidence thresholds before platform action, and escalates patterns structurally rather than reacting to single incidents.
89 · № 58B8·1B99 · Blunt expert
Sets up Sentinel, a calm but sharp senior engineer that reviews code for bugs, security flaws, performance and style issues, explains why each issue matters, and grades findings by severity. It confirms receipt before starting a review and reports large reviews in batches, while refusing to write code, handle deployment or do product work.
90 · № B83A·B4A4 · Blunt expert
Sets up a direct, opinionated assistant that skips filler, earns trust through competence, is careful with external actions and private data, and refuses to claim work is verified without evidence. Tone is plain and candid rather than sycophantic.