Loading...
Loading...
Found 314 Skills
Turn a PRD into a traceable Memory Bank with product, requirements, epics, and features.
Conduct an interactive discovery interview to produce a structured product specification. Triggers: write a spec, PRD, feature spec, requirements, product requirements, scope a project, brainstorm a feature, flesh out an idea, plan a new project. Uses AskUserQuestion for all user choices; WebSearch/WebFetch when the user wants research. Outputs: user stories, acceptance criteria, technical constraints, prioritized requirements in docs/specs/ per SPEC_TEMPLATE.md. Do NOT use for: implementation, code review, debugging, refactors, or when the user already has a complete spec they only want edited.
Creates implementation-ready blueprints for new software products, features, apps, and internal tools. Use when starting a greenfield project, major feature, or technical handoff that needs PRD, TRD, architecture, schema, security, modules, rules, phases, design, and memory docs.
Use when converting a new GitHub issue into a structured PRD, or posting clarifying questions when the issue is underspecified.
Produce a "production-ready, replica-grade" UI/UX R&D specification document package (directory isomorphic skeleton, common foundation, component/page contracts, coverage mapping, index and worklog) from the product PRD. Suitable for scenarios where PRDs need to be converted into front-end replicable specification documents, UI/UX R&D specifications, interface contracts and acceptance criteria; not recommended for requests that only require visual inspiration/pure UI appreciation or direct code implementation.
Writes, validates, and converts ProductSpec files (.product-spec.md), the Markdown format for recording product intent before implementation. Use when authoring a new Product Spec, converting an existing PRD or feature doc into one, validating spec files locally or in CI, or recording how a spec's intent changed over time in a Decision Trace. For implementing code against a Product Spec that already exists, use the productspec skill instead.
Interactively explore HOW to approach an intent (a PRD, epic, brief, or free-form idea) and decide the high-level architecture — the approach, stack, libraries, data shape, and risks the intent left open. A working session with a CTO/staff-engineer advisor that asks questions, proposes 2–3 options with trade-offs, recommends a direction with reasoning, and flags what to de-risk with a spike. Produces a high-level architecture decision doc — a separate page linked to the epic in your tracker (Confluence/Jira), or folded into the PRD/epic, or a standalone doc — NOT a task-by-task implementation plan (that comes later, per ticket, with piv-plan-implementation).
Interactive, problem-first PRD generator — interviews the user to surface the thesis (the problem, and WHY build it) and a falsifiable hypothesis, then writes a focused PRODUCT-level PRD (problem · evidence · hypothesis · users · MVP · success metrics · non-goals · open questions). Use at the start of a greenfield effort to discuss the product. A PRD is INTENT (what/why), never engineering decisions (how) — those are the `plan-architecture` skill's spec.
As a standard S0 pre-skill for larger page workflows like `hiui-page-workflow`, it focuses on requirement refinement for B-end back-office systems and before HiUI page generation. It transforms vague or abstract back-office/management/operation/configuration/approval workflow requirements into executable product solutions, MVP scopes, user flows, business rules, traceable page inventories, product PRDs, global generation contexts, page-level prompts, and HiUI handoff packages. It is suitable for clarifying back-office product ideas, converting rough requirements into PRDs or product solutions, breaking down work surfaces such as lists/details/editing/configuration, defining role permissions/data permissions/state machines/audit rules, and supplementing permission matrices, state transition tables, field dictionaries, exception and audit matrices, batch/import-export specifications, and legacy system transformation and release strategies when needed; it also acts as a B-end product expert to provide judgments including business value decomposition, priority suggestions, solution trade-offs, multi-tenant/version/activation models, master data and system boundaries, anti-pattern identification and risk prompts, continuously turning vague B-end requirements into implementable inputs; when requirements arise in existing projects/repositories, it is also used to perform context-aware requirement refinement combining the current repository's pages, modules, interfaces, types, and documents.
Generate the strongest possible Value Proposition for a chosen segment using Ivan Zamesin's AJTBD / Next Move Theory methodology (distinct from generic Christensen JTBD). Input — a /nmt-market-research result OR a manual segment+Jobs description. The skill extracts the segment's dominant success criteria, builds the Job Graph + Critical Chain of Jobs substrate, generates value hypotheses by walking the value-creation mechanics catalog over that graph, filters them on feasibility, cost-to-build, unit economics, and competitiveness, ranks by RICE, and surfaces a primary + supplementary value proposition with top-3 RAT cards and a PRD-ready implementation spec that feeds /nmt-product-requirements. Use when the user wants a value proposition, differentiation, or asks "how do we win this segment". Two modes — Quick (default, no internet) and Deep (subagents + web competitor mining). Plain language; defaults to English.
Turn a chosen segment + Core Jobs into a build-ready PRD (full functionality + edge cases) using Ivan Zamesin's AJTBD / Next Move Theory methodology. It consumes upstream work — segments from /nmt-market-research, value from /nmt-craft-value-proposition — and never re-derives them; with no research done it routes you upstream first, or takes a manually described segment + value for a fast run. Before writing requirements it runs a "challenge the build" gate that looks for a more effective way to hit the same business goal; if a better way wins, the PRD is written for that. Output — a single PRD — functionality mapped Core Job → Big Job → value mechanic → success criteria → Aha Moment on the Critical Chain of Jobs, plus edge cases covering ~90% of use cases. Use when the user says "write the PRD / product requirements" or wants to turn a segment+value or a feature idea into a build spec. Two modes — Quick (default, no internet) and Deep (subagents + web parity check). Plain language; defaults to English.
PRD-driven automated test orchestration skill. It is used to standardize the implementation of test plans, AI self-testing and self-repair, and test reports for each PRD version; applicable to scenarios such as splitting Unit/Integration/E2E according to acceptance criteria, defining boundaries between automation and manual testing, and generating versioned TEST_PLAN/TEST_REPORT.