Explorar skills

Design a product value proposition using the Value Proposition Canvas (jobs, pains, gains, pain relievers, gain creators) and the Kano model. Use when the user asks to write a value proposition, map pains and gains to product features, apply VPC, distinguish basic/performance/delighter features (Kano), or articulate why a product matters to a specific customer. NOT for marketing copy or microcopy

React-specific development patterns including hooks (useState, useEffect, useReducer, useContext), component architecture, state management, shadcn/ui integration, JSX/TSX, React testing, and Bulletproof React auditing. NOT for Next.js routing, SSR, or server components (use nextjs-development). NOT for CSS design systems, Tailwind utilities, or accessibility patterns (use frontend-design).

Use when the user asks to set up tracks, pick instruments, scaffold an arrangement, build a project template, or describe a track they want to make in Ableton Live. Examples - "make me a 4-bar lo-fi loop", "set up a film score template", "I want to start a hip-hop beat in C minor".

Generates production-ready docker-compose.yml files for any application stack.

口播稿转录屏脚本（CLI+浏览器），自动生成ffmpeg录制脚本并输出MP4。Use when 用户说"录屏""录制教程""录视频""录一段""screen record""补录""口播稿转录屏""浏览器录屏""录网页"或提到录制Claude Code画面或浏览器操作。

Rewrite AI-generated content to evade AI content detectors by increasing perplexity, burstiness, and lexical entropy. Use when asked to make content pass GPTZero, Originality.ai, Turnitin AI detection, Copyleaks, or any AI content detector; when asked to make writing "undetectable"; or when existing deslop passes fail detection checks. Trigger phrases: "pass AI detector", "evade AI detection", "ma

Diagnostic-loop workflow for improving an underperforming AI agent. Starts with baseline measurement using rubrics and LLM-as-judge scoring (agent-evaluation), then diagnoses architectural problems like task-model mismatch and pipeline bottlenecks (agent-project-development), redesigns the agent topology — supervisor, swarm, or specialized agents (multi-agent-patterns), adds the right memory frame

Use when the user is finishing a track and wants to check it's ready to send to a mastering engineer or for self-mastering. Audits headroom, peak levels, mono compatibility, frequency balance, LUFS. Examples - "is this ready to master?", "audit my mix before export", "check my levels".

Use when a website experienced a sudden visibility/ranking drop that correlates with a published Google Core Update — symptoms include broad ranking loss across many keywords in a short window (1–6 weeks), Sistrix VI dropping 30 %+ from peak, sales/leads falling despite no technical changes, the owner saying "we used to rank, now we don''t" but pages still load and index normally. Distinguishes Co

Use when the user needs help choosing, evaluating, fixing, extending, or operationalizing colors for any interface. Trigger on requests about palettes, color grading, themes, semantic roles, contrast, tokens, visual tone, muddy or washed-out UI, dark mode, light mode, state colors, or making colors feel right. Use this skill to teach flexible color judgment and, when useful, support that judgment

Orchestration logic for running a parallel persona-swarm brainstorm — when to invoke, which subset of the 12 canonical personas to spawn (PM, Engineer, Designer, Skeptic, User Advocate, Pre-Mortem Specialist, Junior, Veteran, First-Principles Thinker, Constraint-Setter, Optimist, Operator), how to spawn them in parallel via the Task() tool with persona-specific subagent types, how to handle their

Use when the user needs a monthly work summary, time-tracking report, or commit-based activity recap.