Product & Planning

abhillashjadhav Skill

Build-stage skill: models a feature's per-user token cost at three scale points — every number derived from stated assumptions, arithmetic fully reproducible. Use when inference cost needs stress-testing before commitment — 'what does this cost per user at 1k/50k/1M users', 'will inference eat our margin at scale', 'run the unit economics on this feature' — or when /pm routes such a request here. If token counts or prices are missing it asks for them or proposes labeled assumptions — it never silently invents them. Do NOT use for portfolio-level roadmap economics (roadmap-reality-check), pricing-structure design (pricing-tradeoff), bare per-MTok price lookups, or general infra cost reduction.

bage2014 Skill

提供项目文档创建和维护的指导，包括PRD、技术规范和用户指南。在处理文档相关任务或需要文档结构建议时调用。

pramoddutta Bundle

Draft an as-of QA status brief from approved execution, defect, plan, and risk snapshots. Use for daily or weekly testing updates, standups, sprint reports, stakeholder summaries, and comparisons with a prior status snapshot. Reports sourced progress, changes, blockers, risks, and next actions without logging test outcomes, filling missing metrics, closing a cycle, or making a release decision.

jh941213 Skill

Codex용 PRD/SPEC 작성 스킬. 아이디어를 CPS, PRD, 시장/사용자/기능/위험/SPEC 문서로 구조화한다. 트리거: "$prd", "PRD 작성", "제품 기획", "아이디어 정리", "요구사항 문서", "CPS" 안티-트리거: 이미 확정된 작은 코드 변경, 단순 버그 수정

jh941213 Skill

Azure FinOps and resource review workflow. Use when Azure resources, infrastructure specs, cost estimates, budgets, quotas, scaling, monitoring, or cloud operations are involved. Defaults to read-only Azure CLI discovery.

luongnv89 Bundle

Generate Product Requirements Documents from `idea.md` and `validate.md` files. Use when asked to create or update a PRD. Don't use for TAD, sprint tasks, or raw idea validation.

luongnv89 Bundle

Generate a Technical Architecture Document (TAD) from a PRD. Use when asked to design system architecture or define how a product is built. Updates tad.md and reports GitHub links. Don't use for PRD authoring, sprint tasks, or code implementation.

luongnv89 Bundle

Run Herdr loops for one open GitHub issue (resolve→review→fix) or an existing PR (review→lazy fixer) until CLEAN. Don't use for plain resolution without review, review-only/no-fix requests, backlog automation, or merging.

luongnv89 Bundle

Generate sprint-based development tasks from a PRD. Use when asked to create tasks or break down requirements. Don't use for PRD/TAD authoring or task execution.

luongnv89 Bundle

Audit a stale, inherited, or messy codebase — deps, bugs, security, tests, CI, docs, UI/UX — then emit a phased, testable modernization plan. Read-only: plans upgrades, never applies them. Not for single-PR review, PRD-to-tasks, or UX-only audits.

luongnv89 Bundle

Generate an approval-gated improvement PRD from a report and baseline, with evidence-backed what/why/value changes and measurable targets. Use for rebuild proposals. Don't use for task breakdown, coding, implementation, or unapproved persistence.

luongnv89 Bundle

Generate phased tasks.md from an approved website PRD, with landing page first, measurable tasks, and collect/create asset tracking. Use for implementation planning. Don't use for coding, design review, unapproved PRDs, or direct deployment.

mrzhangguoguo Skill

Deprecated. Do not invoke. Use ralph directly after PRD/test-spec planning is complete.

lukedj78 Bundle

Orchestrate an end-to-end product-development workflow built on atomic skills. Reads `.workflow/meta.json` in a project directory, works out which phase the user is in (idea → PRD → tasks → design → scaffolded → pages → modules → tests → pre-deploy gates → deployed), and delegates to whichever specialist skill owns the next move — across the web, mobile, monorepo and eve-agent families. Use when the user wants to "start a new project end-to-end", "advance my project to the next stage", "what should I do next on this project", or pastes a brand-new product idea / Figma URL / inspiration images with a request to "build the app". Not for: deeply-specialized work inside one stage (invoke that specialist skill directly).

lukedj78 Bundle

Review a diff on the two axes a dev-flow project can check that a generic reviewer cannot: the **spec** it was built from (`.workflow/PRD.md` + `tasks.md`) and the **contract** it was built under (golden rules, `meta.json#stack`). Two parallel sub-agents, reported side by side and never merged, with a Fowler smell baseline as the floor. Use when the user says "review this branch", "spec review", "review since <ref>", "does this match the PRD?", "controlla il diff contro la spec", or dev-flow proposes it after a feature lands. Requires `.workflow/`; without one use the built-in `/code-review`. Records `meta.json#spec_review`; no phase bump. Not for: generic review with no spec (built-in `/code-review`), UI quality (`shadscan`), legal (`compliance-audit`), Vercel cost (`vercel-doctor`), or running tests (`write-tests`).

lukedj78 Bundle

Take a dev-flow project into Linear and run it with agile scrum: creates or links the Linear Project, pushes `.workflow/tasks.md` into estimated, labelled issues, sets up 2-week cycles, then keeps **Linear as the source of truth** — syncing new tasks up, status and velocity down, planning each sprint to the velocity target. Triggers: "porta il progetto in Linear", "crea le issue in Linear", "setup scrum", "pianifica lo sprint", "report di velocity", "adotta questo progetto in Linear", or dev-flow routing from `prd_drafted`/`tasks_split`. Modes: Setup, Adopt, Sync. Not for: writing or estimating the tasks themselves (use `prd-to-tasks`), building the app or agent (design-md-to-app / eve-agent), or the headless server loop (docs/loop-engineering.md).

lukedj78 Bundle

Break down a PRD.md into a concrete, executable `tasks.md` checklist that a developer or an AI agent can pick up and ship. Reads `.workflow/PRD.md` (and `.workflow/PROJECT.md` for context), produces `.workflow/tasks.md` with one task per checkable bullet, grouped by user story or epic, sized to ~2–8 hours each. Output is compatible with beads, GitHub Issues import, `linear-scrum` (via Linear MCP), and ralph-tui task sources. Use when the user says "split this into tasks", "make the issues", "ticket the PRD", "task breakdown", "create the issues from the PRD", or the orchestrator routes here from phase `prd_drafted`. Not for: writing code or implementing the tasks (those run later).

lukedj78 Bundle

Scaffold a new Expo + React Native app from a PROJECT.md + PRD.md + DESIGN.md using the opinionated stack (Expo Router, TypeScript, NativeWind v4, Zustand, TanStack Query, Reanimated, expo-image, FlashList). Reads .workflow/meta.json with stack.framework="expo-rn" and phase in {prd_drafted, design_extracted}. Produces a running Expo app at the project root, sets phase to "scaffolded". Always idempotent: re-running detects existing files and skips. Use when dev-flow routes here from prd_drafted+expo-rn, or the user says "scaffolda app expo from PRD", "create RN app from this PRD/DESIGN", "bootstrap expo app". Not for: adding screens (rn-add-screen, Wave 2), modules (rn-module-add, Wave 3), Next.js scaffolding (design-md-to-app — different stack).

lukedj78 Bundle

Turn a raw product idea — a paragraph, a Notion dump, a half-formed thought, or a brief that arrived as a **file** (`.docx`, `.pdf`, `.pptx`, `.xlsx`: an RFP, a client deck, a Word spec — converted to Markdown first with `anydoc`) — into a structured PROJECT.md (high-level brief) and PRD.md (product requirements document) inside a project's `.workflow/` folder, following the dev-flow contract. Use when the user pastes a product idea and says "let's plan this", "draft a PRD", "what would this look like as a project", "fammi il PRD da questo PDF", "PRD da questo documento/RFP", or starts a new project from scratch. Also use when a `.workflow/` exists at phase `empty` or `idea_captured` and the orchestrator routes here. Not for: writing code, designing UI, or producing task lists (those are downstream skills).

lukedj78 Bundle

Run a GDPR + EU AI Act compliance audit on an existing dev-flow project (web / mobile / eve agent) and remediate what it finds. Two modes: Audit (scan the codebase and `meta.json#stack` against a 10-point risk register — DSAR, consent/cookies, EU data residency, retention and PII-scrubbing, AI-transparency Art.50, high-risk Annex III, sub-processors — into a report with severity, evidence and article mapping) and Remediate (apply the safe mechanical mitigations, flag the ones needing a legal decision, never deciding legal basis or high-risk for the user). A pre-deploy gate; run it any time. Triggers: "audit GDPR", "compliance check", "AI Act", "siamo conformi?", "DSAR / cancellazione account / cookie consent / data residency". Not for: legal advice or DPIA sign-off (a DPO confirms), building features, or writing the PRD (use prd-from-idea).

lukedj78 Bundle

Generate or customize a frontend app from a DESIGN.md (Google design.md spec): reads its tokens and produces a working React app pre-styled to match. Next.js 16 + App Router only; pre-16 refused. Four UI libraries — shadcn/ui, Base UI, MUI, Coss/UI (via `coss-ui`) — and TanStack Form + Zod (default) or react-hook-form. Bumps phase to `scaffolded`. Use when the user has a DESIGN.md and wants to scaffold an app, set up a theme, or customize shadcn / Base UI / MUI from its tokens: "use this DESIGN.md to start an app", "DESIGN.md → app", "scaffold from design.md", "applica il DESIGN.md a shadcn / Base UI / MUI", "crea l'app dal DESIGN.md", "init shadcn con questo DESIGN.md". Not for: mobile apps (use rn-bootstrap), writing PRDs (use prd-from-idea), or generating pages after the scaffold exists (use screenshot-to-page).

lukedj78 Bundle

Scaffold a turborepo monorepo on pnpm workspaces, with shared packages (types, design tokens or shared UI, backend client). Three topologies, asked in Step 1: web+mobile (Next.js app AND an Expo + RN app — the classic case), web+agent (Next.js app + an eve agent in apps/agent, no mobile), or web-only (just the turborepo and shared-package tooling around one web app). Reads `.workflow/meta.json` with `stack.framework="monorepo"` and phase in {prd_drafted, design_extracted}. Always idempotent. Use when dev-flow routes here, or the user says "scaffolda il monorepo", "create a turborepo with web + mobile", "bootstrap il monorepo da PRD + DESIGN.md", "scaffolda un turborepo per web + agent eve". Not for: scaffolding only web with no monorepo tooling (use design-md-to-app), scaffolding only mobile (use rn-bootstrap), or adding modules after the scaffold (use module-add or rn-module-add).

qa-aman Bundle

Write a Product Requirements Document (PRD). Use when the user says "write a PRD", "document this feature", "product requirements for X", "write requirements", "I need a PRD", "pitch this feature", or wants to formalize a feature or product idea into a structured doc - even if they don't explicitly say "PRD".

qa-aman Skill

Write OKRs (Objectives and Key Results). Use when the user says "write OKRs", "help me set goals", "create objectives and key results", "quarterly goals", "team OKRs", "I need to define success for this quarter", "Doerr method", or wants to translate a strategic direction into measurable targets - even if they don't explicitly say "OKRs".

qa-aman Bundle

Design and review UI/UX, and deliver it as a clickable self-contained HTML mockup (default) or as a Figma file, so it can be judged before any development starts. Use whenever the user wants to design a screen, flow, page, dashboard, form, onboarding, empty state, or app, wants to see what a feature would look like, or wants existing UI critiqued or improved. Trigger on "design this screen", "what should this look like", "make a mockup", "wireframe this", "build a prototype of", "UI for this feature", "design the UX", "improve this screen", "review this UI", "why does this page feel confusing", "make this look better", "audit this interface", "turn this PRD into screens", and on any request to visualise a feature before engineering builds it. Also use when someone pastes a URL, screenshot, or component file and asks what is wrong with it, or when a spec is written and the natural next question is "how does it look". Prefer this skill over hand-rolling UI, and use it even when the user does not say "UX".

qa-aman Skill

Synthesize pilot observations into structured debrief reports and spec updates. Use this skill when: - A pilot has completed and you have observation notes, tickets, or feedback transcripts - You need to turn messy pilot data into actionable spec changes - You want to generate edge case user stories from field observations - You need negative acceptance criteria from pilot bugs - You want a structured debrief report for stakeholder communication

qa-aman Skill

Quality gate for product specifications before stakeholder review. Use this skill when: - A spec draft is ready and you want to validate it before sending to Engineering, Design, and QA - You want to check a spec against your template's completeness rules - You need to catch vague language, missing sections, or gaps before review - You want a pass/fail scorecard with specific fix suggestions

qa-aman Skill

Prioritize a feature backlog or list of ideas. Use when the user says "help me prioritize", "prioritize this backlog", "RICE score these", "MoSCoW", "opportunity solution tree", "what should we build first", "rank these features", or has a list of items and needs to decide order - even if they don't explicitly say "prioritization".

qa-aman Bundle

Run structured product thinking exercises before writing a spec. Use this skill when: - You need to think through a feature idea before writing a PRD - You want to run the 11-star experience exercise for a feature - You need a positioning statement using Geoffrey Moore's framework - You want to define product principles and success vision for a new feature - You have a raw feature idea and need to turn it into a structured brief

qa-aman Skill

Audit a roadmap or backlog to distinguish outcomes from outputs. Use when the user says "outcome vs output", "escaping the build trap", "are we building the right things", "roadmap review", "feature factory", "output-driven team", "we keep shipping but nothing changes", or wants to shift focus from shipping features to delivering value - even if they don't explicitly say "outcome vs output".

qa-aman Skill

Run product discovery to identify what to build. Use when the user says "product discovery", "how do I know what to build", "validate this idea", "talk to customers", "are we building the right thing", "discovery process", or wants to reduce the risk of building something users don't want - even if they don't say "discovery".

qa-aman Skill

Generate structured weekly or fortnightly status updates for leadership and stakeholders. Use this skill when: - You need to prepare a weekly or fortnightly status report - You want to summarize recent progress across git commits, tickets, and spec changes - You need a formatted update ready for Slack, email, or a stakeholder meeting - You want multi-project updates in one report

qa-aman Bundle

Run pre-build user interviews to validate whether a planned feature actually solves a real problem before engineering invests. Use when the user says "validate this feature", "should we build this", "interview users about [feature]", "test this feature idea", "pre-build validation", "is this feature worth building", "talk to users first", or has a feature idea and wants to pressure-test it with real users before writing a PRD or kicking off engineering. Also trigger when the user wants to avoid building something users will not adopt, when they say "what would users actually think of this", or when they have a hypothesis and need a structured interview plan. Combines Mom Test question discipline, Lean Customer Development hypothesis structure, JTBD Forces of Progress, and Opportunity Solution Tree synthesis into one workflow that ends with a clear build / iterate / kill recommendation.

qa-aman Skill

Generate user research interview scripts using Mom Test principles. Use this skill when: - You are preparing for user interviews or pilot observation sessions - You need a question bank organized by behavior, context, pain points, and workflow - You want interview guides that avoid leading questions and hypotheticals - You need per-persona interview guides - You are preparing for field visits or pilot debriefs

qa-aman Bundle

Categorize free-text support tickets into a 3-tier taxonomy and produce a month-on-month management report, an interactive dashboard, and a shareable PowerPoint. Use this skill whenever someone has a batch of tickets, requests, incidents, or cases and wants to know what categories they fall into, how the volumes are trending month on month, or what management should act on. Trigger on ServiceNow, Jira Service Management, Freshservice, Zendesk, or any helpdesk export; on phrases like "categorize these tickets", "tag these requests", "what are people raising", "monthly ticket report", "ticket volume trends", "which category is growing", "what should we automate", "service desk analysis", "bucket these descriptions", "how many tickets per category"; and whenever someone describes manually reading ticket descriptions to sort them into buckets, which is the exact pain this removes. Also use it when there is no ticket data yet and a realistic sample plus a working report is needed to show a stakeholder what the out

qa-aman Skill

Build Opportunity Solution Trees using Teresa Torres' framework for structured product discovery. Use this skill when: - You need to map a desired outcome to opportunities, solutions, and experiments - You want to decide WHAT to build next based on user research and discovery data - You have workshop findings, pilot feedback, or user research to structure into actionable options - You need a visual tree diagram showing the path from outcome to testable experiments