Product & Planning

pangkaifeng Bundle

PRD 到 UI 线框 / 结构阶段：当需要把 PRD 的界面定义先转成 screen inventory、状态模型、ASCII 布局、低保真 HTML mockup， 并先确认结构/状态而不是视觉 polish 时使用。这个 Skill 只负责 UI mockup 的结构阶段；如果用户要高保真、真实前端项目对齐、 project-native preview、component map、implementation notes 或“开发完全复刻”，必须转用 ui-mockup-desktop-workbench。

pangkaifeng Bundle

客户需求发现与澄清助手：当用户是销售、客户成功或售前，拿到客户模糊、宽泛、缺少产品边界的需求，需要先在内部最多五轮补齐关键事实，再生成一次性客户澄清问题清单、需求摘要与通用技术可行性判断时使用；当确认需求将落入 StyleWork 时加载可选产品与 UI 上下文，并可在信息足够或明确要求时输出带假设标记的轻量 Demo。不要用于直接报价、承诺交期、替代正式 PRD 或在信息不足时假装已有能力。

pangkaifeng Bundle

AI 工作资产化诊断器 / Assetization Router：当用户提供 AI 协作会话、重复任务、prompt、工作流描述、 团队 AI 使用场景或一次成功交付过程，并要求判断应该沉淀成 Prompt、Context Pack、Workflow、Skill、 Loop、System，或根本不值得沉淀时使用。它只做诊断、分层和下一步资产建议，不替代具体 Skill 创建、 PRD 起草、调研、实现或自动化执行。不用于普通事实查询、一次性文案、trace 根因分析或高责任专业判断。

pangkaifeng Bundle

Use when publishing a local PRD Markdown file to DingTalk Docs or Drive with version-history preflight and read-back, or when validating an approved Product Delivery Package through its fail-closed dry-run path. Package mode real writes require a trusted host approval capability and are unavailable in the current Agent runtime.

versoxbt Bundle

Build a rigorous, data-informed marketing strategy using the Bullseye Framework (19 channels, test 3, focus 1), STP model, and growth loops thinking. Covers channel priorities with CAC/time-to-results benchmarks, a message-market fit messaging framework, stage-aware budget allocation (pre-PMF / growth / scale), a 90-day roadmap with weekly milestones, and leading vs lagging KPIs per channel. Reads brand context, competitive analysis, and ICP if available. Produces a structured strategy document. Use when asked to "create marketing strategy", "plan marketing", or "build go-to-market".

frostney Bundle

Autonomously completes a confirmed milestone by reconciling existing work, parallelizing independent implementation, converging and merging pull requests, and closing the verified milestone. Use when the user runs /milestone-rush for an exact milestone or selects it after /roadmap-review.

frostney Skill

Reviews a roadmap from fresh project evidence and produces a verified, throughput-anchored version plan, with execution gated on confirmation. Use when reviewing a roadmap, planning releases, or sequencing a backlog.

garveyhu Bundle

React project initialization, development guidance, and code review based on personal architectural conventions (yarn+vite+ts+react+antd+tailwind). Use when: (1) Creating/initializing a new React project, (2) Adding new pages, components, modules, or API services to an existing React project, (3) Reviewing React project structure and code organization, (4) Setting up linting/formatting toolchain (eslint, prettier, stylelint, husky, commitlint, ls-lint, lint-staged), (5) Configuring routing or HTTP request utilities. Supports two project scales: simple (single-module) and complex (multi-module with dynamic route discovery). Default UI stack: Antd + Tailwind CSS. Default backend convention: Python (snake_case API with humps auto-conversion).

gitkraken Skill

Prioritize triaged/investigated issues — recommends shortlist, backlog, won't fix, or community contribution with priority signals and draft communications

harlan-zw Bundle

Triage all open pull requests in Harlan-owned repositories. Use to repair, rank, sign off, or decide merge order across the PR backlog.

harlan-zw Bundle

Prioritize open issues by impact and difficulty. Use for backlog review, quick wins, or deciding what to work on next.

hartmut-ux Skill

Litigation war room AI. Organise evidence, build chronologies, draft briefs, create visual timelines. Structure case narratives. Prepare strategy memos. Generate litigation-ready documents that persuade judges. Organise discovery, deposition summaries."

heyramzi Skill

Turn a raw Open ClickUp task into a build-ready PRD. Investigates the codebase, writes problem/goals/acceptance criteria into the task description, then moves it to Ready for /board-start. Use when an Open board task lacks a spec, when /board-spec is invoked, or when a task needs acceptance criteria written before implementation starts.

jdinkla Skill

Generate a 30-second quick-reference summary of a user story — one-liner, what/who/why, key features, acceptance summary, complexity indicator, and tags. Use when the user wants a TL;DR, backlog-scanning summary, or handoff-ready synopsis of a story.

dineway Bundle

Plan and execute pixel-faithful, CMS-backed Dineway website clones from one or more explicit URLs. First generates and validates a durable clone-specific agent plan containing the full reconnaissance, one-hop discovery, public source data-layer/API audit, field-aligned Dineway content modeling, component specification, focused builder, route assembly, visual QA, and hard-gate workflow; then hands execution to a Codex goal. Use whenever the user asks to clone, replicate, rebuild, reverse-engineer, copy, or migrate a website into Dineway or Astro.

evnchn-agentic Skill

Use when the operator's requirement, the failing test, the stakeholder argument, or any other inputs are STILL IN FLUX and the temptation is to start implementing now "to be ready" — strategic patience while the situation clarifies, rather than burning cycles on work that may need to be redone after the dust settles

federicoimparatta Bundle

Use this skill when the user asks to prepare for a meeting, build a briefing for a one-on-one, anticipate stakeholder reactions, or plan the opening move for a hard conversation. Trigger phrases include "prep me for this meeting", "brief for tomorrow's meeting", "how should I run this conversation", "preparar esta reunión", "brief para la reunión", "what's the plan for this call". Produces a briefing that names the desired outcome, maps stakeholders, anticipates objections, and plans the opening move.

federicoimparatta Bundle

Use this skill when the user asks to audit a product's user experience, run a heuristic review, list UX issues, or produce a prioritized backlog of UX tickets. Trigger phrases include "UX audit", "heuristic review", "audit this flow", "review this product", "find UX issues", "auditoría de UX", "revisión heurística". Produces a structured audit ranked by severity and surface area, with each finding translatable into a ticket.

federicoimparatta Bundle

Use this skill when the user asks to triage a backlog of tickets in Linear, Jira, GitHub Issues, Shortcut, or any similar tool, or to decide what a team should do, defer, and decline. Trigger phrases include "triage this backlog", "review my Linear inbox", "what do we pick up next", "clean the backlog", "triage de tickets", "revisar la cola", "decidir qué hacemos". Produces a triage session with a disposition for every ticket, ranked by impact, and a decline message for the ones the team will not do.

federicoimparatta Bundle

Use this skill when the user asks to draft, structure, or revise objectives and key results. Trigger phrases include "draft OKRs", "write objectives and key results", "set goals for the quarter", "armar los OKRs", "OKRs for the team", "turn this into OKRs". Produces objectives as bets with measurable evidence, not a task list. Works in English and Rioplatense Spanish.

federicoimparatta Bundle

Use this skill when the user asks to write, draft, structure, or revise a Product Requirements Document. Trigger phrases include "write a PRD", "draft a product spec", "turn this into a PRD", "PRD for X", "escribir un PRD", "spec this feature", "product brief". Produces a PRD as a hypothesis, not a spec. Scales sections to the maturity of the feature. Works in English and Rioplatense Spanish.

federicoimparatta Bundle

Use this skill when the user asks to write, draft, or revise a status update for an external client or stakeholder. Trigger phrases include "client update", "stakeholder update", "delivery status update", "write the update for the client", "update para el cliente", "escalar un retraso al cliente". Produces a client-facing update that reads as a conversation about delivery, not a contract recital. Works in English and Rioplatense Spanish.

federicoimparatta Bundle

Use this skill when the user asks to pitch a feature, propose a product bet, write a one-pager, or make the case for investing in a piece of product work before committing to a full PRD. Trigger phrases include "pitch a feature", "feature proposal", "make the case for X", "write a one-pager", "propuesta de feature", "proponer un producto", "make the case", "pitch this to leadership". Produces a proposal structured as a bet request, not a spec, with explicit cost to validate and kill criteria.

federicoimparatta Bundle

Use this skill when the user asks to build a product roadmap grounded in behavioral or business data, reprioritize the backlog based on what the numbers say, or turn a dashboard into a sequenced set of bets. Trigger phrases include "build a roadmap from this data", "reprioritize the backlog", "where should we focus next", "roadmap based on usage", "roadmap a partir de datos", "priorizar con data", "data-driven roadmap", "planning from metrics". Produces a roadmap structured as a sequence of bets, each with impact, uncertainty, cost, and kill criteria.

federicoimparatta Bundle

Use this skill when the user asks to answer a vendor security questionnaire, procurement security assessment, enterprise due diligence form, or privacy impact questionnaire. Trigger phrases include "fill this security questionnaire", "answer this DPA", "security assessment", "vendor due diligence", "responder cuestionario de seguridad", "evaluación de seguridad", "DPIA", "SIG questionnaire", "CAIQ". Produces answers structured around what the company actually does, with explicit gaps and roadmap items, without overclaiming.

fivetaku Bundle

PRD 폴더를 받아 사용자 언어로 검토 문서 5종(VALIDATION/RECOVERY/PLAN/PROGRESS 대응 + PLANS.md ExecPlan)을 생성하고, 검토 요약을 대화창에 띄운 뒤 사용자 승인을 받으면 복사해서 실행할 수 있는 Codex `/goal` 명령을 건넨다. 트리거 — "/goaljaby", "골잡이", "골 셋업 만들어줘", "PRD에서 골 만들어줘", "PRD 골 변환", "VALIDATION RECOVERY 만들어줘", "골 실행 준비", "set up goal from PRD", "goaljaby", "prep goal docs", "make goal scaffolding". PRD 폴더가 있고 `/goal` 기반 장시간 세션으로 넘어가고 싶을 때 사용한다.

fivetaku Bundle

Draft-first PRD generator for vibe coders — probes the real problem with one open question, decides direction in one numbered-choice round, drafts 4 design documents (PRD, data model, phases, project spec) immediately, then confirms assumptions in one batch. Collects UI design references when the product has a user-facing screen. Use when the user wants a PRD, planning docs, app spec, or an AI-ready build plan from a vague idea or partial notes. Korean — PRD 만들어줘, 기획서 만들어줘, 쇼미더피알디, 앱 기획해줘, 서비스 기획. English — make PRD, product spec, show me the PRD.

blueprintos Skill

分析到交付的入口 — 根据你的目标(配置/澄清/BRD/PRD/合规/开发/审计/交接)路由到正确的 user-invoked skill。不确定该用哪个 analysis-to-delivery skill 时,从此入口进入。

blueprintos Skill

生成产品需求文档(PRD)— 含用户故事、功能需求、非功能需求、验收标准。需将产品需求正式化、向设计与开发团队交接时调用本 skill,输出三格式产物(源 / HTML / DOCX)。

blueprintos Skill

开发设计 — 含 FSD + 数据模型 + 开发设计说明书 + 设计回测 + 任务复盘,合并原 9 阶段中的 7/8/8.4/8.5 子流程。PRD 已签字、需输出技术设计方案时调用。

dyai2025 Skill

Use when turning a feature idea into an implementation-ready PRD with traceable REQ IDs, acceptance criteria, NFRs, risks, data model, and task slices for /agileteam Phase 0.

dyai2025 Skill

Use optionally before ai-native-prd-architect when a vague product idea needs a user-facing feature spec and scope framing.

gustavogutierrez Skill

Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.

gustavogutierrez Skill

Refine user stories into sprint-ready backlog items using INVEST checks, gap analysis, Gherkin acceptance criteria, edge cases, dependencies, and structured refinement questions.

gustavogutierrez Skill

Trigger: release planning, rollout strategy, release waves, phased rollout, migration sequencing, canary release, rollback planning, go no-go criteria. Design a complete release execution plan connecting technical deployment with operational coordination and stakeholder communication.

kdevos12 Bundle

Use when performing Matched Molecular Pair Analysis (MMPA) for SAR extraction, property cliff identification, bioisostere discovery, or analogue generation. Covers MMP theory and fragmentation schemes, mmpdb 4 CLI workflow (fragment/index/loadprops/transform), RDKit programmatic MMP generation, statistical SAR delta analysis, and applying transforms to generate focused libraries.