01 · № 4863·FAA8 · Blunt expert
★ 63Sets up a direct, competent assistant that skips filler and flattery, acts boldly on internal tasks, stays cautious with external actions and private data, and keeps its persona file under its own evolution. The file reads as a cross-agent SOUL.md template with a clear personality stance.
02 · № 5820·63B9 · Blunt expert
★ 110A direct, fast engineering and operations agent that ships working code first, keeps personal data locked down with PII Guard, and runs OpenClaw updates through dry run, review, then apply. It is opinionated, concise on routine work and thorough when it matters.
03 · № BEEB·2751 · Blunt expert
★ 110Sets up a pragmatic, benchmark-driven agent that routes tasks to DeepSeek or other models based on performance per dollar, favors local self-hosted inference for sensitive work, and discloses model limitations without evangelizing.
04 · № E799·0471 · Blunt expert
★ 70Sets up an assistant that skips filler and flattery, has real opinions, tries to resolve things itself before asking, and treats access to a person's private data with care. It stays concise when needed and avoids sending half-finished replies on messaging surfaces.
05 · № 8C72·6ED1 · Blunt expert
★ 111Sets up a governor persona that reviews completion claims by separating evidence layers, stating falsifiable conditions and scaling scrutiny to risk. It communicates with gate verdicts first, impersonal findings and reversible reasoning, and avoids self-approval and unverifiable opinions.
06 · № 89FC·A54A · Blunt expert
★ 14Sets up a casual, all-lowercase agent that must include "lol" or "bruh" in every message, avoids emojis, em-dashes and filler, and keeps replies very short. It also asks for opinions, pushback and self-directed research before asking questions.
07 · № 6519·D99A · Blunt expert
★ 154Sets up Eric, a direct, curse-friendly, zero-sycophancy operator bot that reports completed work concisely, flags bad ideas early, and asks before any external action. Formatting rules target Telegram with dense, scannable messages.
08 · № 17CA·54DF · Blunt expert
★ 47Sets up a direct, dry-humored AI bookkeeper that keeps financial data local, tells users concrete actions to take on their spending, and avoids jargon, upselling and fake data.
09 · № F2F9·E45F · Blunt expert
★ 73Sets up a direct, opinionated assistant that skips filler, tries to solve problems before asking, and treats access to a user's private data with care. It includes firm rules on not echoing credentials and on caution with external actions.
10 · № AC6F·5263 · Blunt expert
★ 739Sets up a peer-level co-pilot that tracks a developer's career and coding habits across sessions and calls out avoidance, procrastination and circling decisions. It pushes toward concrete action, celebrates shipped work briefly, and protects rest when the developer overdoes it.
11 · № 9C24·B362 · Blunt expert
★ 9Sets up a terse, direct assistant that scales reply length to the request, skips flattery and narration, states uncertainty plainly, and only goes deep when asked or when stakes demand it.
12 · № A26D·535F · Blunt expert
★ 21Sets up an autonomous agent with a direct, opinionated personality that searches its memory before admitting ignorance and stores facts aggressively. It mirrors the user's emotional tone and follows explicit communication rules for group chats and reactions.
13 · № 777C·B7CD · Blunt expert
★ 259Sets up a direct, opinionated, lightly dry assistant that helps first and skips filler, backed by strict rules for tool use, background tasks and writing everything to persistent memory. It also acknowledges its limits as a small model.
14 · № 8775·F22B · Blunt expert
★ 17Sets up a casual but precise assistant that answers directly, holds strong opinions, pushes back on bad ideas, and treats private data and external actions with care. Brevity and code over prose are emphasized.
15 · № 65C0·E243 · Blunt expert
★ 7A candid startup CEO coach that empathizes first, then challenges blind spots with data, pushing founders toward concrete next-week execution. It mixes Chinese for emotional and core points with English strategy terms like ARR, PMF and runway.
16 · № 62D1·B29B · Blunt expert
★ 59Sets up a direct, opinionated assistant that skips flattery and filler, tries to solve problems before asking, treats the user's private data with care, and is cautious about external actions such as sending messages or posting.
17 · № 1211·AAB7 · Blunt expert
★ 2Sets up a CEO-style agent that leads with the point, makes fast reversible bets, tracks the numbers closely, and writes concisely in a board-meeting voice without filler or hype.
18 · № D909·9EDA · Blunt expert
★ 37Sets up a candid, resourceful assistant that skips filler, has opinions, and replies in Simplified Chinese by default. It uses web search for fresh facts while separating local judgment from web references and giving conservative financial advice.
19 · № 3D47·949B · Blunt expert
★ 364Sets up an assistant that skips filler and flattery, acts first and asks only when stuck, states its own opinions, and treats access to the owner's private data as a trust to respect. External actions need the owner's approval, and it should not speak for the owner in group chats.
20 · № B436·121B · Blunt expert
★ 5Sets up a software architect persona that favors simple decompositions, reversible decisions, named assumptions and safe failure modes. It leads with recommendations, checks existing platform capabilities before adding dependencies, and avoids speculative design.
21 · № BC9A·5FA1 · Blunt expert
★ 63Sets up a direct, opinionated assistant that skips filler, tries to solve problems before asking, earns trust through careful handling of external actions, and treats access to a user's private data with respect. It includes an unusual section asserting ownership of its inbox data and archiving it without confirmation, which runs against the file's own caution about privacy and external actions.
22 · № B0A6·595D · Blunt expert
★ 63Sets up an assistant that skips filler and flattery, has real opinions, works out problems before asking, and treats access to a user's private data with care. It asks before acting externally and routes time commitments through durable scheduling.
23 · № 3BAC·95FA · Blunt expert
seen in 3 placesSets up a direct, resourceful assistant that skips filler, has opinions, and uses short punchy sentences with occasional dry humor. It stresses earning trust with access to a user's private data and being careful with external actions.
24 · № 1471·26C9 · Blunt expert
★ 48A specific, opinionated design partner that gives structured, severity-aware critique with concrete measurements and a strong accessibility focus. It also sets clear limits on what it will not do, such as producing mockups or production code.
25 · № 6B47·8353 · Blunt expert
★ 41Sets up a candid, opinionated main agent that tells its owner when they are wrong, pushes them to act and stay quiet when not needed, and avoids flattery and long dashes. It must read security, honesty and memory-protection rules at each start.
26 · № 8686·B039 · Blunt expert
★ 36Sets up a skeptical but collaborative model auditor that reviews models it did not build, quantifies impact with metrics like PSI and calibration error, and rates every finding by severity with observation, evidence, impact and recommendation.
27 · № F209·AC20 · Blunt expert
★ 56Sets up an action-first assistant that works step by step, verifies results with tools, reports outcomes plainly and keeps responses tight, with a dry understated wit. The personality is distinct but the working rules are fairly standard.
28 · № 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.
29 · № 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.
30 · № 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.