Product & Planning

doronkatz Bundle

Estimate market opportunity (TAM, SAM, SOM) using multiple sizing frameworks (top-down, bottom-up, comparable company, analogous market). Triangulates across frameworks, highlights where they converge and diverge as signal, and produces a calibrated range with source-graded confidence labels. Refuses unbounded fabrications; always offers a labeled lower-confidence path when data is thin. Used for investment cases, go/no-go decisions, and stakeholder pitches.

doronkatz Bundle

Creates an opportunity solution tree mapping desired outcomes to opportunities and potential solutions. Use for outcome-driven product discovery, prioritization, or communicating product strategy.

doronkatz Bundle

Produces a private strategic preparation document for the user before a meeting that matters. Captures stakes, stakeholder positions and reads, ranked desired outcomes, key messages, anticipated questions with prepared responses, risks and tensions, specific asks, and success signals. Distinct from meeting-agenda because this artifact is not shared with attendees; it is the user's personal tactical prep for meetings where positioning matters.

doronkatz Bundle

Produces an attendee-facing agenda that sets what will be discussed, who owns each topic, and how time will be spent. Supports ten meeting type variants (standup, planning, review, decision-making, brainstorm, 1-on-1, stakeholder-review, project-kickoff, working-session, exec-briefing). Emits a shareable summary suitable for Slack or email plus a full agenda with time-boxed topics, type tags, owners, attendee prep, and logistics.

doronkatz Bundle

Documents stakeholder needs, concerns, and influence for a project or initiative. Use when starting projects, managing complex stakeholder relationships, or ensuring alignment across organizational boundaries.

doronkatz Bundle

Cross-meeting archaeology skill. Consumes multiple meeting recaps (or raw notes) over a period and surfaces patterns invisible in any single meeting. Shows how decisions evolved, who has been saying what, where threads are stalling, and where contradictions have emerged. Produces a plain-text timeline, themes with confidence markers, stakeholder position tracking, consolidated decision list, contradiction flags, open items, narrative summary, and prioritized follow-ups.

doronkatz Bundle

Produces async communication to stakeholders, primarily non-attendees and secondarily some attendees who want a reference. Translates meeting outcomes into what-it-means language for readers, with channel variants (slack, teams, email, notion, exec-memo) and audience variants (engineering, design, leadership, customer-facing, mixed). Surfaces a primary CTA up front, flags technical-to-business translations for user verification, and detects thread continuation from prior updates.

doronkatz Skill

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes. Full CLI command reference. For vault discovery and automation workflows, also see `steipete-obsidian`.

hybridaione Skill

Plan sprints, milestones, roadmaps, risks, dependencies, and stakeholder updates for team delivery.

harsh817 Bundle

Ask question-first prompts to capture known knowns before software work. Use for any domain when establishing the outcome, existing facts, decisions, constraints, project state, references, and user context before planning, designing, debugging, building, or auditing.

harsh817 Bundle

Ask question-first prompts to uncover unknown unknowns before or during software work. Use for any domain when hidden assumptions, missing failure modes, unseen dependencies, security risks, data risks, edge cases, or expert concerns could change the plan.

harsh817 Bundle

Orchestrate the Unknowns Toolkit question-first skills for any software work, including frontend, backend, debugging, database design, agent frameworks, docs, deployments, and audits. Use to create or update UNKNOWNS.md, ask focused user questions, classify unknowns, and recommend the next workflow phase without implementing the work.

harsh817 Bundle

Create, update, and maintain the canonical FEATURE_MAP.md from outcome, users, journeys, actions, rules, failures, groups, priorities, and vertical slices. Use when the feature discovery flow needs a comprehensive document that coding agents read before implementation and update whenever feature decisions change.

harsh817 Bundle

Ask question-first prompts to expose known unknowns before software work. Use for any domain when open decisions, ambiguities, missing requirements, uncertain architecture, debugging hypotheses, data choices, UX flows, or risky assumptions could change the next step.

harsh817 Bundle

Discover failure cases, edge cases, invalid states, and recoverable errors for planned features. Use when designing resilient workflows, reducing hidden unknowns, or deciding which errors can be defined out of existence.

harsh817 Bundle

Prioritize features by outcome value, learning value, dependency order, risk, and complexity. Use when turning a feature map into a build order or reviewing whether a backlog is tactical and too feature-first.

harsh817 Bundle

Ask question-first prompts to turn tacit preferences and unknown knowns into examples, references, criteria, prototypes, or reaction loops. Use for frontend design, architecture taste, developer experience, agent frameworks, workflows, documentation quality, and any work where the user knows what good looks like when they see it.

harsh817 Bundle

Discover business rules, invariants, policies, limits, and decisions hidden inside outcomes, journeys, actions, or existing code. Use when feature maps need domain rules before implementation or when rules appear duplicated across a project.

harsh817 Bundle

Convert actions into small buildable features with clear boundaries. Use when turning workflow actions into backlog items, reviewing feature size, or separating user-facing behavior from internal implementation tasks.

ryankolean Bundle

Full-discovery planning skill that analyzes a GitHub repo, designs a complete implementation plan, and produces a structured markdown execution file for Claude Dispatch. Chains after interrogate. Activates when the user says "architect this", "plan for dispatch", "architect-plan-for-dispatch", "design this for dispatch", or when a large body of work needs thorough planning before handing off to Dispatch workers. Covers greenfield builds, refactors, migrations, infrastructure, documentation, and any complex multi-task project.

yogsoth-ai Bundle

---

yogsoth-ai Skill

IPC/CPC hierarchy drill-down and lateral expansion for patent discovery

jorinyang Skill

干系人分析——Power×Interest矩阵定位、四象限沟通策略、冲突识别。当需要管理干系人、筹备项目启动、对齐跨职能团队、规划沟通策略时触发。

jorinyang Skill

构建机会方案树——将期望结果映射为机会→方案→实验的四层发现结构。基于Teresa Torres的Continuous Discovery Habits。当需要结构化产品发现、梳理机会空间、避免跳入方案陷阱时触发。

jorinyang Bundle

多轮需求对齐差异分析。将PRD及多轮会议对齐结果以需求项为核心逐项对比，标注原有/差异/新增/待确定状态。适用于系统开发中与客户进行多次信息同步后产出差异分析文档。触发：需求对齐差异分析/PRD对比/需求变更分析/需求项追踪/需求对齐结果对比。

jorinyang Bundle

产出技术文档套件（PRD、ER图、架构图、流程图）并进行系统化校验。 适用于需从会议纪要/调研材料中提取需求、产出多份关联文档并交叉校验的场景。 触发条件：用户要求产出PRD+数据关系图+架构图+业务流程图，或要求多文档交叉校验。

harsh817 Skill

Define or audit a project's goal, users, success boundary, and explicit out-of-scope work. Use when starting a project, writing a PRD, clarifying scope, rejecting feature creep, or checking whether a proposed change increases complexity without serving the core purpose.

jorcan Bundle

Context Discovery

steph-dove Skill

Use when the user wants to plan and implement a non-trivial task in this repo. Runs a multi-phase flow — discovery, parallel exploration, clarifying questions, parallel architectures, approval gate, implementation, parallel review, summary.

steph-dove Skill

Use when the user wants to plan and implement a non-trivial task in this repo. Runs a multi-phase flow — discovery, parallel exploration, clarifying questions, parallel architectures, approval gate, implementation, parallel review, summary.

steph-dove Skill

Use when the user wants to plan and implement a non-trivial task in this repo. Runs a multi-phase flow — discovery, parallel exploration, clarifying questions, parallel architectures, approval gate, implementation, parallel review, summary.

steph-dove Skill

Use when the user wants to plan and implement a non-trivial task in this repo. Runs a multi-phase flow — discovery, parallel exploration, clarifying questions, parallel architectures, approval gate, implementation, parallel review, summary.

steph-dove Skill

Use when the user wants to plan and implement a non-trivial task in this repo. Runs a multi-phase flow — discovery, parallel exploration, clarifying questions, parallel architectures, approval gate, implementation, parallel review, summary.

steph-dove Skill

Use when the user wants to plan and implement a non-trivial task in this repo. Runs a multi-phase flow — discovery, parallel exploration, clarifying questions, parallel architectures, approval gate, implementation, parallel review, summary.

steph-dove Skill

Use when the user wants to plan and implement a non-trivial task in this repo. Runs a multi-phase flow — discovery, parallel exploration, clarifying questions, parallel architectures, approval gate, implementation, parallel review, summary.

orcaqubits Skill

Implement the UCP Catalog capability (`dev.ucp.shopping.catalog`) — free-text product Search and identifier-based Lookup, the Product/Variant data model, media, ratings, and quantity units. Use when exposing product discovery to agents or consuming a business catalog before cart and checkout.