Futuregerald Claude Plugin

Teach the user a new skill or concept, within this workspace.

Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

any input (code, docs, papers, images) - knowledge graph - clustered communities - HTML + JSON + audit report

Convert raster images (PNG/JPG) into clean SVG vector art. Use whenever the user wants to vectorize an image, do png to svg, raster to vector, convert image to svg, trace an image, turn a mascot/logo/illustration into vectors, or produce scalable SVG from a bitmap. Handles color art (vtracer) and mono/line art (potrace), with optional background removal, svgo optimization, and a verification render.

Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.

When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," or "CTA copy." For email copy, see email-sequence. For popup copy, see popup-cro.

Use when the user asks to review a plan, sanity-check a plan, grill a plan, poke holes in a plan, or do an adversarial review of a plan. Dispatches one fresh staff-engineer reviewer against the plan file. Runs once before implementation - findings are fixed, and the plan is never sent back for a second review.

Retrieve relevant past review situations from a corpus of PR review comments. Use when reviewing code, authoring PRs, writing plans, or investigating what reviewers historically flag. Surfaces the most similar past objections ranked by usefulness — no API tokens, no LLM calls at query time.

Create a PRD through user interview, codebase exploration, and module design, then submit as an issue. Use when user wants to write a PRD, create a product requirements document, or plan a new feature. Supports both GitHub Issues and Jira.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

花叔Design（Huashu-Design）——用HTML做高保真原型、交互Demo、幻灯片、动画、设计变体探索+设计方向顾问+专家评审的一体化设计能力。HTML是工具不是媒介，根据任务embody不同专家（UX设计师/动画师/幻灯片设计师/原型师），避免web design tropes。触发词：做原型、设计Demo、交互原型、HTML演示、动画Demo、设计变体、hi-fi设计、UI mockup、prototype、设计探索、做个HTML页面、做个可视化、app原型、iOS原型、移动应用mockup、导出MP4、导出GIF、60fps视频、设计风格、设计方向、设计哲学、配色方案、视觉风格、推荐风格、选个风格、做个好看的、评审、好不好看、review this design。**主干能力**：Junior Designer工作流（先给假设+reasoning+placeholder再迭代）、反AI slop清单、React+Babel最佳实践、Tweaks变体切换、Speaker Notes演示、Starter Components（幻灯片外壳/变体画布/动画引擎/设备边框）、App原型专属守则（默认从Wikimedia/Met/Unsplash取真图、每台iPhone包AppPhone状态管理器可交互、交付前跑Playwright点击测试）、Playwright验证、HTML动画→MP4/GIF视频导出（25fps基础 + 60fps插帧 + palette优化GIF + 6首场景化BGM + 自动fade）。**需求模糊时的Fallback**：设计方向顾问模式——从5流派×20种设计哲学（Pentagram信息建筑/Field.io运动诗学/Kenya Hara东方极简/Sagmeister实验先锋等）推荐3个差异化方向，展示24个预制showcase（8场景×3风格），并行生成3个视觉Demo让用户选。**交付后可选**：专家级5维度评审（哲学一致性/视觉层级/细节执行/功能性/创新性各打10分+修复清单）。

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use when you have a spec or requirements for a multi-step task, before touching code

Review skills for quality, size, progressive disclosure, and effectiveness. Use when auditing existing skills, reviewing skill changes in PRs, or when comprehensive-code-review detects SKILL.md files in a diff.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Deep strategic analysis of meetings from Krisp transcripts. Acts as a second brain — surfaces insights, subtext, commitments, risks, and recommendations the user might miss. Use when: user asks to debrief a meeting, analyze a call, review a conversation, pull insights from a meeting, wants meeting notes or analysis, says 'debrief', 'second brain', 'what did I miss', 'meeting insights', or references a recent call they want analyzed. Works with any meeting type: 1:1s, group syncs, strategy sessions, standups, skip-levels.

Verifies that shipped work actually meets a ticket's acceptance criteria, by both reading the code and running it. Every finding is confirmed twice — traced in the source and reproduced against a running app — then checked against the tracker and git history so existing tickets are linked rather than re-filed. Requires a runnable local environment; asks the user rather than falling back to a code-only review. Produces a QA report written for a product manager and posts it to the ticket. Use when asked to QA a ticket, test whether acceptance criteria were met, verify an epic or story was really delivered, or check whether shipped work matches what was asked for.

Investigate and groom tickets by dispatching sub-agents for codebase research, history, root cause analysis, and risk assessment. Posts structured Triaging Notes as a comment. Default is short-form (TLDR, key findings, risks, estimation, approach) with full investigation collapsed. Use --full for the complete report. Works with Jira, GitHub Issues, or any ticketing system.

Use when writing epics, stories, initiatives, or spike tickets. Also use when asked to rewrite, improve, or clarify an existing ticket. Recommend after ticket-grooming identifies gaps. Covers new ticket creation and rewrites of existing tickets.

Structure Go API and service codebases — package layout, interface-driven dependency direction, and the HTTP edge. Use when starting a Go service, adding a feature or endpoint, deciding which package a file or type belongs in, resolving an import cycle, reviewing Go layout in a PR, or asking "how should I structure my Go project". Also before writing Go that touches a database, HTTP client, cache, queue, or clock, so it lands behind a consumer-declared interface. Covers routing, handlers, middleware placement and order, panic recovery, decoding and validating a JSON body, rejecting oversized input, where wire DTOs live, structured logging with slog, liveness versus readiness health checks; context deadlines, cancellation, ctx-first, WithValue keys; config loading; testing — where tests belong, functional tests, fakes, synctest, race and goroutine-leak detection; and concurrency — worker pools, job queues, bounding concurrency, backpressure, graceful shutdown.

Model routing rules for codebase search. Delegates search/exploration to cheaper models (Haiku/Sonnet) while keeping Opus as the orchestrator. Invoke this skill before any codebase search or exploration task.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' or 'consumer behavior.' This skill provides 70+ mental models organized for marketing application.

Use when encountering any bug, test failure, performance regression, or unexpected behavior, before proposing fixes

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when creating a pull request, writing a PR description, or preparing changes for code review. Ensures PR descriptions include structured summary, background context, test plan, and rollback plan.

Use when performing code review on a PR, reviewing code changes before merge, or when a GitHub code review is requested or received - orchestrates parallel sub-agents for correctness and safety review

Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Comprehensive JavaScript/TypeScript testing patterns for Jest, Vitest, and AdonisJS/Japa. Use when writing tests, reviewing test code, or debugging test failures.

Use when executing implementation plans with independent tasks in the current session

Write and maintain Architecture Decision Records (ADRs) following best practices for technical decision documentation. Use when documenting significant technical decisions, reviewing past architectural choices, or establishing decision processes.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.