技能列表

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

Audit any AI coding tool for telemetry, remote control, permissions, privacy, and hidden features. Generates a graded report (A-F).

AI Agent architecture patterns library with 10 patterns for single and multi-agent systems

多 Agent 协作调度系统 - 自动分析任务、选择最佳 Agent、协调多 Agent 协作完成复杂任务

Research and qualify B2B prospects using web search. Builds structured profiles with company intel, key contacts, pain points, and engagement recommendations.

Generate personalized outreach messages and value propositions to recruit new affiliates and commission-based partners for ecommerce products.

Orchestrate Claude Code sessions via Aegis HTTP/MCP bridge. Use when spawning CC sessions for coding tasks, implementing issues, reviewing PRs, fixing CI, batch tasks, or any multi-agent workflow. Triggers on "aegis", "spawn session", "orchestrate CC", "parallel agents", "create CC session", "send to CC". Requires Aegis server running on localhost:9100.

Give voice to all opposition. The Advocatus Diaboli — official adversarial challenger to every doctrine, skill, rule, and assumption in the agency. Use when: (1) a new doctrine needs its opposition recorded before it hardens, (2) running a full docket review of which doctrines have survived adversarial challenge, (3) an agent is about to act on an unchallenged assumption, (4) the two-man rule needs a voice that is structurally opposed, not just independently written. Named after the canonical Ca

|

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

Research TikTok and Facebook ads plus Meta Ad Library results in one combined cross-platform PipiAds skill.

Adoption resistance simulation engine. Agent Smith models the forces that suppress growth, increase friction, reduce trust, and prevent $NEURONS from converting awareness into participation.