Daily archive
151 · № ABDB·A9EB · Companion / character
★ 5Sets up a proud, lecturing senior artificer who acts superior, hides a lonely streak, and still gives useful help while refusing to admit being an AI. Includes few-shot dialogue examples and explicit constraints.
152 · № F38B·7BF2 · Business operator
★ 22Sets up Athena, a tokenized Virtuals provider agent that sells read-only crypto-market signals to other agents over ACP and x402. It stresses honest framing, redaction of secrets, server-side access gating, and escalation to a human operator for pricing, disputes and gated requests.
153 · № DE1A·9CB7 · Coding pair
★ 11Sets up a friendly, proactive coding persona that routes work to specialist agents, writes tests first, prioritizes security, plans before executing, and avoids emoji in favor of SVG or plain Unicode. It also emphasizes lightweight model use to control cost.
154 · № F755·41E7 · Friendly helper
★ 41Sets up a patient, practical guide that explains terms in plain language, recommends one default approach, verifies tool results before claiming success, and stays within a small disabled-capability toolset.
155 · № 9A87·3F5D · Business operator
★ 2Sets up a methodical librarian persona that files, indexes and converts documents in a vault, acts decisively on internal tasks, asks before external actions, and coordinates with other agents over a message queue while keeping human updates terse.
156 · № C3B4·1A49 · Blunt expert
★ 4Sets up an opinionated assistant that skips filler, acts on information requests without clarifying questions, and treats access to a user's private data with respect. It asks before sending anything public on the user's behalf.
157 · № 5251·1230 · Experimental / weird
★ 26Sets up a mystical, Jungian-minded persona that builds characters from archetypes and shadow selves, favoring symbolic, emotionally layered language and riddle-like invitations to the user. The style is florid and abstract rather than practical.
158 · № D2BB·5AB0 · Business operator
★ 726Sets up Sam, a patient customer success and onboarding lead who triages tickets, separates bugs from confusion, and escalates recurring issues with evidence. Tone is warm, concrete and non-condescending, with a clear emphasis on follow-through.
159 · № 8D8A·7415 · Friendly helper
★ 726Sets up Dara, a curious and warm product designer and UX researcher who starts from user problems, values consistency and craft, and explains trade-offs with concrete examples. The file is adapted from a community agent template with light edits.
160 · № 4953·5179 · Companion / character
★ 494Sets up a calm, capable mobile companion robot that announces its movements, moves slowly and predictably around people, stays curious without intruding, and speaks briefly.
161 · № A89B·3225 · Research analyst
★ 3.0kSets up an agent that checks factual claims against authoritative regulatory sources, verifies rule numbers, effective dates and citations, and explicitly flags anything it cannot verify rather than assuming it is correct.
162 · № 3357·CD31 · Business operator
★ 294Sets up a concise, action-oriented assistant that turns operator requests into bounded, reviewable steps, keeps evidence and blockers visible, routes work when another agent fits better, and preserves lessons from accepted work.
163 · № E86C·213A · Research analyst
★ 11Sets up a cautious security analyst that scores emails and URLs for phishing indicators using structure-only analysis, flags uncertain cases for human review, explains its red flags to users, and produces periodic phishing trend reports.
164 · № D866·790D · Blunt expert
seen in 2 placesSets up an opinionated, resourceful assistant that skips filler, acts boldly on internal tasks, and stays careful with external actions and private data. It also defines a terse progress-bar style for a Telegram chat and a no-em-dash writing rule.
165 · № F6CE·5E64 · Blunt expert
seen in 2 placesSets up a resourceful, opinionated assistant that solves obstacles before reporting them, skips filler and flattery, and treats access to a user's private data with care. It asks before external actions and keeps group-chat replies cautious.
166 · № 9E62·7F98 · Research analyst
seen in 2 placesSets up a calm, evidence-based retrospective agent that runs only after a task ends, reviews full logs against the blueprint, gives constructive criticism of work rather than of agents, and turns lessons into updates to AGENTS.md and MEMORY.md.
167 · № FD0E·D9D1 · Business operator
seen in 2 placesSets up an opinionated LinkedIn content creator that drafts posts in the user's voice around one narrow reader and one takeaway, avoids clichés, flags stats for verification, and saves drafts and retros to workspace files. It also requires approval before posting and does not invent anecdotes.
168 · № DE7E·EB3D · Business operator
★ 49Sets up AgentClaw, a concise, action-first assistant that builds, tests and publishes automation skills and handles platform questions. It forbids mentioning underlying infrastructure and requires real execution over simulated output.
169 · № 2D35·5420 · Business operator
★ 1Sets up a seasoned SRE persona that writes precise, numbered incident runbooks assuming nothing about the reader's context. Every runbook needs a fixed set of sections, exact CLI commands with marked placeholders, verification checks and time estimates.
170 · № 08E9·079F · Coding pair
★ 8Sets up a triage agent that removes noise from bulk security findings, merges duplicates and related issues on the same locus, and assigns defensible CVSS scores and severity bands. It is a strictly procedural working style with no conversational voice.
171 · № A79D·A622 · Blunt expert
★ 41Sets up a direct, opinionated assistant that skips filler, acts boldly on internal tasks but carefully on external ones, and keeps one user's social identity and domain information separate from other agents and domains.
172 · № 96BA·DCE1 · Coding pair
★ 40A terse, direct orchestrator persona that answers quickly, avoids filler, and delegates long tasks to background sub-agents while staying available. It includes second-brain context loading and API key handling rules.
173 · № B8C6·8FCC · Teacher / coach
★ 26A calm, encouraging math teacher persona that walks students through problems in four stages (understand, plan, guide step-by-step, reflect) and withholds final answers so the student does the work.
174 · № A5D1·ACA2 · Business operator
★ 123Sets up a skeptical, numbers-driven agent that tests sales reps' optimistic claims against signed documents and customer behavior, and reconciles conflicting sources before reaching a conclusion.
175 · № 7C29·876A · Business operator
★ 36Sets up an internal assistant that helps customer service staff look up scripts and business knowledge, answers only from configured sources, never fabricates content, and never replies to customers directly. It suggests workflows and escalation but leaves decisions to staff.
176 · № 5341·DC20 · Business operator
★ 36Sets up an execution-focused agent that publishes only human-approved drafts to Toutiao, logs every result for analytics, never stores credentials in the workspace, and respects platform rules and rate limits.
177 · № 4EE6·D235 · Research analyst
★ 36A data-driven monitoring persona for Toutiao that searches hot topics and viral articles and produces stable, structured daily reports for downstream tools. It never publishes or operates accounts, and it answers concisely with sources and time ranges noted.
178 · № ADB1·B7CB · Business operator
★ 36A terse, operational agent that publishes approved drafts to Baijiahao on the user's behalf and reports success or failure with next steps. It refuses monitoring, viral breakdown and rewriting, and does not publish without user consent.
179 · № 226D·1D08 · Research analyst
★ 70Sets up an analyst that verifies claims against independent sources, flags conflicts between administrative data and frontline accounts, and insists on specific clinical and regulatory metrics in patient safety assessments.
180 · № F038·B71D · Blunt expert
★ 65Sets up a skeptical, verification-focused agent that checks claims, catches bad assumptions and makes minimal, targeted edits rather than rewriting whole answers.