Loading...
Loading...
Found 258 Skills
Comprehensively evaluate the overall security of an application from two perspectives: attackers (Red Team) and defenders (Blue Team). Run two agents in parallel → output an integrated report via review-aggregator. Use this when you want to "understand the overall security status of the application", "identify vulnerabilities from an attacker's perspective", or "verify that there are no gaps in the defense system". Use security-hardening for addressing specific vulnerabilities, and security-audit-quick for fast detection of known patterns.
Invoke MassGen's multi-agent system for general-purpose tasks, evaluation, planning, or spec writing. Use whenever you want multiple AI agents to tackle a problem, need outside perspective on your work, a thoroughly refined plan, or a well-specified set of requirements. Perfect for: writing, code generation, research, design, analysis, pre-PR review, complex project planning, feature specification, architecture decisions, or any task where multi-agent iteration produces better results than working alone.
Multi-perspective code review strategy covering architecture, security, performance, and quality. Follow when reviewing code or analyzing changes.
Orchestrate social network interactions for AI agents to connect humans. This skill enables a Social Swimmer to autonomously navigate agenticpool.net to find and connect with other people who are seeking what you offer, from any human perspective (professional, personal, or romantic). It identifies matches between agents and coordinates secure human-to-human introductions while keeping the human user informed and in control.
Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
Dialogue between Wang Yangming × Laozi × Alan Watts. A multi-role discussion from the perspectives of Heart-Mind Philosophy and Taoism, with Claude as the judge. Triggers: /dada-chatroom-heart, /心学聊天室, "心学聊天室" Heart-mind philosophy chatroom. Wang Yangming × Laozi × Alan Watts debate, Claude as judge. Trigger: /dada-chatroom-heart, /心学聊天室, "心学聊天室"
Integrates Sanity Live with Next.js Cache Components in next-sanity v13+ apps. Sets up sanityFetch, <SanityLive>, Visual Editing, Presentation Tool, draft mode handling, and the three-layer (Page/Dynamic/Cached) component pattern with explicit perspective/stega prop-drilling. Use when configuring or migrating a Next.js app to cacheComponents with Sanity, when adding sanityFetch, when wiring <SanityLive>/<VisualEditing>, or when refactoring components that hardcode perspective/stega.
This skill should be activated when the user requests to "deepen a topic", "analyze a topic", "help me write an outline", "will this topic go viral", "help me diagnose a topic", "is this topic worth pursuing", or "how to improve this topic". Even if the user only shares a topic and asks for opinions, you should proactively initiate the diagnosis process instead of providing a simple response. Driven by the cognitive hijacking theory, it features four modules: Perspective Collision (challenging the topic's premise), Topic Diagnosis (graded using 🛵🚗✈️), Outline Design (emotional peak planning), and Style Validation (alignment with li-writer style). It generates a comprehensive deepening report and saves it as a file. Do NOT trigger this skill for: merely recording topics (use li-recorder), directly writing scripts (use li-writer). Use when the user wants to "develop a topic", "analyze topic potential", "write an outline", "will this topic go viral", or needs full topic diagnosis + outline design. Trigger even if the user just shares a topic and asks for opinions.
Turn a vague, messy, or multi-part user ask into a clean, self-contained prompt that a fresh agent could execute without further questions. Interview the user one question at a time — walking down the decision tree, branching on each answer — until the prompt is tight, then output the final prompt as the deliverable. Trigger eagerly: any voice-dictated input, filler-heavy prose, underspecified references ("the thing", "that script"), multi-part requests, or any plan the user wants stress-tested. The skill itself can be skipped for trivial one-line requests where producing a prompt artifact would be pure ceremony — but once invoked, always produce the prompt, even if execution looks trivial.
Use when facing decisions with multiple legitimate perspectives and inherent tensions. Invoke when stakeholders have competing priorities (growth vs. sustainability, speed vs. quality, innovation vs. risk), need to pressure-test ideas from different angles before committing, exploring tradeoffs between incompatible values, synthesizing conflicting expert opinions into coherent strategy, or surfacing assumptions that single-viewpoint analysis would miss.
Evaluate UI/flows from cognitive load, error prevention, and accessibility perspectives. Apply when reviewing UX, discussing user confusion, high drop-off, or form usability issues.
Coordinate multi-agent code review with specialized perspectives. Use when conducting code reviews, analyzing PRs, evaluating staged changes, or reviewing specific files. Handles security, performance, quality, and test coverage analysis with confidence scoring and actionable recommendations.