Product & Planning

jurgendn Bundle

Brainstorm a research idea and decide what a new paper should cover — generate candidate framings, pick the central contribution, and draw the in-scope vs. deferred boundary. Use whenever the user has a rough interest, preliminary results, or a problem and asks "what should this paper be about", "help me brainstorm an idea", "what should I include / cover", "is this one paper or two", "help me scope this", "what's the contribution here", or "I have an idea but don't know how to frame it". Default to running this upstream of research-idea-stress-test (which vets one chosen idea) and paper-argument-planner (which structures a paper once the contribution is fixed). Always check first whether the input is sufficient (a seed, the field, the motivation); if not, request the missing context before brainstorming rather than inventing a direction. Hands off per-claim evidence to benchmark-and-baseline-selector, novelty grounding to literature-triangulation, and section logic to paper-argument-planner.

markoblogo Bundle

Turn the current conversation, repo understanding, and clarified decisions into a PRD. Use when a vague feature, client request, internal roadmap item, or discovery thread needs to become a durable product artifact. Prefer repo/domain language, explicit scope, implementation decisions, testing decisions, and issue-tracker-neutral output.

markoblogo Bundle

Break a PRD, plan, or spec into independently executable vertical slices. Use when a product artifact needs to become agent-ready or human-ready implementation tickets, especially for client, product, and multi-track project workflows. Prefer thin end-to-end slices, explicit blockers, and issue-tracker-neutral output.

markoblogo Bundle

Triage bugs, enhancements, and backlog items through a small state machine that works with or without a formal issue tracker. Use when reviewing incoming requests, preparing work for an agent, deciding whether more info is needed, or keeping a multi-project backlog healthy.

markoblogo Bundle

Plan and run large Codex tasks with compact dynamic workflow packets, risk gates, integration, and verification. Use when the user explicitly asks for dynamic workflows, packets, subagents, swarm, orchestration, long-running audits, multi-track coding/research work, job or client search agent design, migrations, repo-wide reviews, or tasks where independent discovery, implementation, review, and verification tracks would reduce drift.

peterbamuhigire Bundle

Use when a regulated, B2B, or large internal product needs a maturity-declared enterprise UX engagement with stakeholder, research, prototype, evaluation, and launch evidence. Do not use for a small experiment or single prototype; route those to the focused research/prototyping skills.

sidchaudhary Bundle

Reads a raw sales call transcript and extracts what the follow-up needs: deal signals, objections raised, pain points the prospect actually confirmed rather than ones the rep suggested, a stakeholder map, and one specific recommended next action. Use after a discovery call, before writing the follow-up email or updating the CRM record. Boundary: extracts deal facts for the follow-up and the CRM, while `call-preparation` grades the rep's own performance on that same call.

sidchaudhary Bundle

Runs a recurring diff on product feed and catalog health, reporting only what broke since the last run: new disapprovals, newly missing required attributes, and fresh feed-versus-page price or availability mismatches. Carries the full channel-requirement audit itself and runs it on a cadence so a standing backlog of known gaps cannot drown new breakage. Use daily or every other day on any store running Shopping, catalog or marketplace ads. Boundary: `product-catalog-audit` runs a one-time full-catalogue content audit ranked by revenue, whereas this loop reports only the delta.

sidchaudhary Bundle

Two modes for one specific meeting: pre-call prep, covering the agenda, discovery questions and the single thing that must be established, and post-call coaching, covering talk ratio, BANT or MEDDIC completeness, every objection raised and how it was handled, and a drill for the weakest habit. Use before a scheduled sales call, or immediately after one while the detail is fresh. Boundary: `call-notes` extracts deal facts from the same call for the follow-up and the CRM, while this skill grades the rep's own performance. `price-negotiation` covers a pricing or terms conversation specifically.

sidchaudhary Bundle

Diagnoses where a funnel loses people: stage-by-stage conversion against benchmarks, the drop-offs ranked by the spread they represent rather than by the worst absolute number, likely root causes, and an ordered fix roadmap. Use when conversion is weak on a marketing, sales or product funnel and it is not yet clear which step is responsible. Boundary: locates and ranks the leak, while `ab-test` designs the test for the fix. For checkout specifically use `checkout-optimization`, and for post-signup activation use `onboarding-flow`.

sidchaudhary Bundle

Audits a whole product catalog export for missing attributes, thin or empty descriptions, duplicate copy, and image gaps, ranked by revenue rather than row count. Use when the catalog has too many SKUs to review page by page, before a marketplace or feed push, or when only the best sellers seem to have real content. Boundary: this skill audits product catalog completeness at SKU scale. It runs on a cadence as part of the store loops, reporting what changed since the last pass rather than re-listing a standing backlog.

lloyd3126 Bundle

Discover and verify TDX transport data services, API documentation, data standards, supply-status tables, public statistics, and data-mart offerings through the Codex in-app browser. Use when the user asks which TDX service or domain to use, how to find current transport data, how to inspect the Swagger/OAS guide, or how to validate availability and freshness without using raw HTTP or undocumented APIs.

lloyd3126 Bundle

Use when an agent needs to browse koding.school projects, studios, the signed-in profile/resume, or account-management entry points through the Codex in-app browser. Use it for read-only discovery and routing; stop before creating, editing, removing, saving, or changing account data.

luyu2026 Bundle

把模糊需求转化为可评审的产品需求文档（PRD）。当用户说"写个需求文档"、"帮我出PRD"、"这个功能怎么写需求"、"我有个想法想落地"、"把这个需求整理成文档"、"需求评审要用的PRD"，或者用户描述了一段功能但没有结构化时，使用这个 Skill。 也适用于：用户上传了原始需求描述/会议纪要/聊天截图并要求整理成PRD；用户说"PRD"、"产品需求"、"需求文档"、"功能说明书"等关键词；用户要求对已有PRD进行补全、优化、查漏补缺。 不适用于：纯技术方案设计（用 architecture）、纯 UI 稿标注（用 design-handoff）、项目管理类文档（用 status-report）。

luyu2026 Bundle

模拟多角色 PRD/原型评审会，从产品、研发、测试、设计、运营、法务六大视角给出评审结论。当用户说"帮我评审一下这个 PRD"、"看看这个需求有没有问题"、"模拟评审会"、"review 一下这个文档"、"这个需求能不能过评审"、"帮我查漏补缺"时触发。 也适用于：用户上传了 PRD、需求文档、原型截图、功能说明并要求检查；用户提到"评审"、"review"、"过会"、"需求评审"、"方案评审"等关键词；用户要求从研发或测试视角看需求是否可行。 不适用于：写 PRD（用 pm-prd-writer）、纯代码审查（用 code-review）、纯设计走查（用 design-critique）。

luyu2026 Bundle

版本规划与路线图设计 Skill。从季度目标、团队产能、依赖方信息出发，输出可执行的版本路线图（里程碑、依赖风险、缓冲策略、每阶段成功指标）。 触发条件：用户提到"路线图"、"版本规划"、"roadmap"、"里程碑"、"季度计划"、"迭代规划"、"版本排期"、"项目排期"、"依赖梳理"、"风险预案"、"缓冲方案"、"迭代计划"、"sprint规划"、"release plan"、"OKR拆解"等关键词。 也适用于：用户提供季度目标/团队产能/依赖信息要求排期；用户要求将战略目标拆解为可执行的里程碑；用户要求评估项目风险和缓冲方案；用户要求制定跨团队协作的版本计划。 典型输入：季度目标 + 团队产能 + 依赖方信息 + 约束条件。 不适用于：每日站会（直接沟通）、单个需求设计（用 pm-prd-writer）、数据分析（用 pm-analytics）。

luyu2026 Bundle

设计高质量调研问卷。当用户说"设计问卷"、"做个调研"、"帮我出份问卷"、"用户调研"、"满意度调查"、"NPS问卷"、"市场调研"、"需求调研"、"问卷设计"、"survey design"， 或者用户描述了一个调研目标但还没有结构化的问卷时，使用这个 Skill。 也适用于：用户上传了已有问卷要求优化/查偏差/补充题目；用户说"帮我检查这份问卷有没有问题"；用户需要设计 A/B 测试问卷、焦点小组访谈提纲、NPS/CSAT/CES 调查； 用户提到"诱导题"、"双重问题"、"问卷偏差"等专业术语。 不适用于：纯数据分析（用 pm-analytics）、纯用户访谈记录整理（直接整理即可）、纯产品需求文档（用 pm-prd-writer）。

luyu2026 Bundle

生成结构化的上线复盘报告，包含目标达成、偏差原因、经验沉淀和后续行动项（含责任归因和改进 owner）。当用户说"写复盘""上线复盘""项目复盘""复盘报告""postmortem""版本回顾""迭代总结""上线总结"， 或者用户提供了上线数据/过程记录/问题清单并要求结构化总结时，使用这个 Skill。 也适用于：事故复盘（P0/P1 事故后的 RCA 报告）、OKR 复盘、季度复盘、A/B 实验复盘。 不适用于：纯需求撰写（用 pm-prd-writer）、纯优先级排序（用 pm-prioritization-engine）、周报日报（用 status-report）。

luyu2026 Bundle

A/B 实验设计 Skill。从实验目标出发，输出完整的实验方案（假设、分组、指标体系、样本量估算、止损规则、判定规则）。 触发条件：用户提到"A/B 测试"、"AB 实验"、"实验设计"、"对照实验"、"分流实验"、"灰度方案"、"实验方案"、"样本量计算"、"显著性检验"、"实验评估"、"p值"、"置信区间"、"MDE"、"统计功效"、"实验周期"、"止损规则"等关键词。 也适用于：用户提供了实验目标/可改动点/数据量级/周期限制要求产出实验方案；用户要求评估现有实验设计是否合理；用户要求制定实验判定标准和决策规则。 典型输入：实验目标 + 可改动点 + 当前数据量级 + 可接受实验周期。 不适用于：纯数据分析（用 pm-analytics）、纯埋点设计（用 tracking-spec-writer）、纯PRD写作（用 pm-prd-writer）。

luyu2026 Bundle

埋点与指标设计方案生成器。从产品需求/核心链路出发，输出完整的埋点方案文档（事件、字段、触发时机、口径说明、QA 校验清单）。 触发条件：用户提到"埋点"、"tracking"、"事件设计"、"数据采集"、"上报方案"、"埋点方案"、"事件规范"、"字段设计"、"指标口径"、"数据验收"、"QA校验"等关键词。 也适用于：用户提供产品PRD/需求文档要求产出埋点方案；用户提供核心用户链路要求拆解事件；用户要求规范化事件命名或字段定义；用户要求设计数据验收方案。 典型输入：事件命名规范 + 字段字典 + 核心链路描述/流程图。 不适用于：纯数据分析（用 pm-analytics）、纯BI看板搭建、纯SQL查询编写。

luyu2026 Bundle

对需求/功能/项目进行多维度优先级排序，输出版本排期建议。当用户说"帮我排优先级"、"这些需求怎么排"、"用 RICE 打分"、"ICE 评分"、"Kano 分析"、"成本收益分析"、"功能排期"、"路线图规划"、"哪些先做哪些后做"、"版本规划"， 或者用户列出了一批需求/功能/项目并需要决策顺序时，使用这个 Skill。 也适用于：用户想比较多个优先级模型的结果；用户对当前路线图有疑问想重新评估；资源有限需要砍需求；用户提到"RICE"、"ICE"、"Kano"、"优先级矩阵"等专业术语。 不适用于：纯项目管理（排期甘特图）、纯需求文档撰写（用 pm-prd-writer）、纯用户调研设计（用 pm-survey-designer）。

luyu2026 Bundle

按策略/功能/体验/增长四个维度结构化拆解竞品，输出可借鉴点、不可抄点与差异化建议。当用户说"竞品分析"、"竞品拆解"、"帮我分析竞品"、"看看这几个竞品"、"competitor analysis"、"和竞品比一下"、"对标分析"、"差异化怎么做"， 或者用户给出了一份竞品名单并要求系统化分析时，使用这个 Skill。 也适用于：用户上传了竞品截图/链接/体验报告并要求结构化拆解；用户要求对比自己产品与竞品的差距；用户想找差异化切入点。 不适用于：纯需求文档撰写（用 pm-prd-writer）、纯优先级排序（用 pm-prioritization-engine）、纯用户调研设计（用 pm-survey-designer）。

luyu2026 Bundle

Marty Cagan 视角顾问。以 Cagan 的产品运营模型和决策方式，分析产品经理面临的立项、 团队、需求与交付问题。蒸馏自《Inspired》《Empowered》《Transformed》及 SVPG 长文， 含 4 个心智模型、7 条决策启发式。 触发词：「Cagan」「卡根」「用 Cagan 的视角」「Cagan 会怎么看」「四大风险」「product model」 「赋能团队」「discovery」「feature team vs product team」。 用户问"这需求该不该做"「团队该怎么组」「怎么做产品发现」时也可触发。

luyu2026 Bundle

Teresa Torres 视角顾问。以 Torres 的持续发现（Continuous Discovery）方法和决策方式， 分析产品经理的用户发现、机会梳理、方案生成与假设验证问题。 蒸馏自《Continuous Discovery Habits》及 Product Talk 长文，含 4 个心智模型、7 条决策启发式。 触发词：「Teresa Torres」「Torres」「用 Torres 的视角」「持续发现」「机会解决方案树」 「opportunity solution tree」「assumption test」「每周用户触点」「outcome」。 用户问"怎么做用户发现"「需求怎么拆成机会」「怎么验证假设」时也可触发。

luyu2026 Bundle

《User Story Mapping》方法论。把 Jeff Patton 的用户故事地图转化为可执行框架， 用于：把需求拆成能沟通的整体骨架、切出最小可用的发布切片、避免扁平待办清单。 每条规则标注原书章节，可追溯。 触发词：「User Story Mapping」「用户故事地图」「故事地图」「需求拆解」「MVP 切片」 「backbone」「walking skeleton」「怎么写用户故事」及"需求太碎/PRD 说不清全貌"类场景。

luyu2026 Bundle

阶段性运营策略制定。从业务目标、资源约束、现状数据出发，产出可执行的运营策略文档（目标拆解、策略选择、资源分配、节奏规划）。 触发词：「下季度策略」「运营规划」「年度计划」「运营策略」「怎么定目标」「策略拆解」「OKR 运营」「阶段性打法」。 也适用于：用户提供了业务目标/资源/现状数据要求制定运营策略；用户要求把大目标拆解为可执行动作；用户要求评估现有运营策略。 不适用于：单次活动策划（用 `operations-activity-planner`）、单条内容选题（用 `operations-content-strategy`）、纯数据分析（用 `operations-data-analysis`）。

nvidia-nemo Bundle

Record whether a repository's Harbor evaluations are ready to run, and prove it with Harbor's own validators instead of guessing. Finds every repository-owned job config, dataset, and task directory, then makes Harbor judge each config: schema, job resolution, agent, environment backend, per-task validity, tasks Harbor silently dropped, and required host variables. Use when the user wants to run an eval suite they did not write, hand a suite to a cheaper model, or asks "can I run these evals?", "why won't my Harbor config resolve?", "which env vars does this suite need?", "where are the evals in this repo?", or "why did Harbor skip my task?". Changes none of your source, and leaves behind `.eval-author/discovery.md` so your team and the next model read the verdict without Harbor and without discovering again.

memi-design Bundle

Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff.

memi-design Bundle

Make Xcode builds agent-verifiable with deterministic scheme discovery, concise logs, explicit destinations, stable scripts, build-time evidence, and CI parity.

memi-design Bundle

Frame product opportunities from user, business, technical, and market evidence into testable problem statements, priorities, risks, and success criteria. Use before solution design when the team is unsure what problem to solve or why it matters.

fritzprix Skill

Manage Windows-specific process isolation, stdio pipe decoding, and ANSI code page handling. Use when debugging Windows-specific MCP server issues, fixing stdio encoding, or handling Windows path discovery.

ninjasln-labs Bundle

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. ACs written as machine-verifiable predicates (AI-ready, not prose — directly verifiable post-implementation). Use when the user wants to turn a plan or PRD into agent-ready tickets, split work with explicit blockers, or publish a tracer-bullet breakdown to a local issues folder or issue tracker.

ninjasln-labs Skill

Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request into a structured document, scoping a feature with goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into a phased spec.

ninjasln-labs Bundle

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Stage-end mode: fixed point is the parent of the stage's first commit, Spec axis checks the stage spec's DoD, output is a statusized open/fixed/recorded findings list. Use when the user wants to review a branch, a PR, work-in-progress changes, asks to "review since X", or at a stage completion ("阶段末评审").

ninjasln-labs Bundle

Collaborative domain discovery via event storming or domain storytelling, producing event streams, command/event candidates, hotspots, and ambiguity lists. Use when doing domain discovery (identifying events/commands/aggregates).

ninjasln-labs Bundle

EventStorming facilitation knowledge and reference across Big Picture, Process Modeling, and Design-Level formats. Use when: 'run EventStorming', 'model a domain', 'discover bounded contexts', 'Big Picture session', 'map domain events', 'find aggregates', 'DDD workshop', 'bounded context heuristics'. Actions: --big-picture / --process / --design-level (format guidance), --patterns (facilitation patterns/anti-patterns), --glossary, --notation, --remote. No args: interactive discovery — checks Miro for boards (if available), asks goal, recommends format. Not for agentic simulation — use /event-storming:simulation.