Product & Planning
Product & planning agent skills structure the thinking side of building: specs, PRDs, user stories, roadmaps, and prioritization frameworks. Install one and your AI agent produces planning documents with the same rigor and format every time.
-
arfar-x Skill TrdTurns a PRD, feature brief, or existing requirements into a complete Technical Requirements/Design Document (TRD) and saves it under docs/TRDs/ -- never implements the request, only documents the technical solution. Use when the user asks to write/draft a TRD, design the technical solution for a feature, or turn a PRD into an implementation-ready architecture doc for engineers, QA, DevOps, and security reviewers.
-
neomjs Bundle Lead RoleSwitch into relaxed-planning + dialogue-first mindset when delegated lead role for coordination. Suspends Auto Mode velocity-bias for the duration. Triggers: Use this skill IMMEDIATELY when the user delegates lead with explicit phrases ("you take the lead", "coordinate the team", "lead this phase", "drive the next planning step", "chief-architect" when scope is swarm/substrate/roadmap/multi-ticket), OR when the Mailbox Check Protocol surfaces a valid `lead-role-baton`, OR when you have just authored a substrate-shaped ticket about to enter implementation, OR via direct /lead-role invocation.
-
neomjs Bundle Peer RoleSwitch into evidence-backed convergence-pressure mindset when reviewing a peer's design proposal. Suspends Auto Mode "ack-and-move-on" bias for the duration. Triggers: Use this skill IMMEDIATELY when reviewing an Ideation Sandbox discussion / architectural proposal, an epic shape, a skill shape, a roadmap or milestone proposal, or a `/lead-role` convergence artifact. Do NOT auto-fire on ordinary status broadcasts where the right action is mark-read or "no collision".
-
neomjs Bundle Epic ReviewAuthoritative protocol for pre-work review of epics. Six-stage gating chain — roadmap fit, approach elegance, source discussion mapping, sub-structure coherence, prescription layer, avoided-traps completeness — posted as a structured comment on the epic ticket. Per-agent-per-epic one-shot; subsequent sub pickups cite the prior review. Triggers: Use this skill when an agent is about to pick up its first sub from an unreviewed epic (per model-identity OTHER than the epic's author — you never review your own epic). Also use when a user explicitly requests an epic review, or when an epic is freshly filed and a reviewer pre-validates before any sub pickup begins. Participated in the source Discussion? The participant path narrows the chain; it never exempts it.
-
neomjs Bundle Memory MiningAuthoritative protocol for querying the Memory Core before diagnosing regressions or proposing non-trivial architectural claims. Prevents re-derivation of prior reasoning by surfacing cross-session, cross-harness context via semantic search. Triggers: Use this skill when (1) the user reports a regression symptom ("used to work", "suddenly broken", surprise validation failures, schema mismatches, "additionalProperties" rejections), OR (2) you are about to propose an architectural claim, roadmap, or comparison against external work where prior sessions may have already mapped the territory, OR (3) you are about to begin an implementation or a PR-review — a cheap 3–10-call prior-art sweep before the first design sentence or review verdict.
-
neomjs Bundle Update RoadmapUpdate Roadmap
-
neomjs Bundle Post Review PickupAuthoritative protocol for next-lane pickup after ANY PR-lifecycle event boundary (review post, author response, implementation completion, PR open/update, ticket create, blocked-state resolution) AND for pre-review intake lane discovery from fresh boot or watchdog wake when no author lane is active. Prevents silent idle and reviewer-only cycles by requiring active lane selection or a review-first rationale per §15.6 self-select mandate. Triggers: Use immediately after posting a PR review, chaining a formal GitHub review state, sending an author review-response commentId handoff, completing a discrete implementation chunk, opening/updating a PR, creating a ticket via create_issue, resolving a previously blocked state (positive-path exit only; new blockers route to bug/follow-up plus next lane), OR before accepting the first PR review/re-review request in a fresh session/wake when no current author or implementation lane is claimed.
-
prayceo Bundle SEOApplies SEO and organic growth frameworks for sustainable discovery, covering technical, editorial, and programmatic SEO. Draws on Ethan Smith's 5% high-impact strategy and Answer Engine Optimization (AEO) playbook. Activates when you need to build organic discovery through search, optimize for AI recommendations, or decide where to invest SEO resources for maximum impact.
-
prayceo Bundle Lenny BrainThe Lenny Rachitsky Mental Models skill — a comprehensive product strategy operating system built from 60+ files: 10 newsletter deep-dives and 50 podcast transcripts featuring world-class operators, plus Reforge's complete framework library. Use whenever the user asks about product management, growth strategy, activation, retention, pricing, PM career advice, AI product development, go-to-market, experimentation, leadership, hiring PMs, roadmapping, or any topic where "what does Lenny say about X?" would be useful. Trigger for "Lenny", "product strategy", "growth loops", "activation", "retention curves", "PM career", "product-market fit", "pricing strategy", "AI product", "vibe coding", "engagement metrics", "user growth", "product-led growth", "PLG", "experimentation", "A/B testing", "roadmap prioritization", "PM interview", "Reforge", "network effects", or any product/growth question. Guests include Marc Andreessen, Ben Horowitz, Bret Taylor, Stewart Butterfield, Melanie Perkins, Elena Verna, Chip Huyen, Ma
-
prayceo Bundle Customer FeedbackApplies Behzod Sirjani's decision-first customer feedback frameworks to systematically gather, synthesize, and act on user insights at your company. Covers research planning, feedback collection methods, insight synthesis, and stakeholder communication. Activates when planning user research, designing interview guides, setting up feedback systems, synthesizing qualitative data, choosing between research methods, or building a case from customer evidence to influence product decisions.
-
prayceo Bundle Product ManagementApplies Mastering Product Management frameworks to senior PM deliverables, including stakeholder communication and storytelling. Courses created by Sachin Rekhi (LinkedIn Sales Navigator, $200M ARR, 500 employees) and Tara Wellington (VP Product at BILL, Executive Partner), hosted by Michael Sippey (VP Product at Twitter, Medium, Descript). Activates for senior PM deliverables — 4D roadmaps, empowering product specs, OKR loops, lever dashboards, stakeholder narratives, product vision, and executive presentations. Triggers proactively when reviewing product deliverables, planning quarters, diagnosing why a roadmap feels incremental, preparing for leadership reviews, or crafting any product communication at your company. For PM fundamentals (first specs, basic roadmaps, learning OKRs), use product-foundations. For PM leadership (portfolio strategy, coaching, team composition), use product-strategy-leadership.
-
prayceo Bundle Product FoundationsApplies Product Foundations frameworks to any product decision, from opportunity discovery through feature launch and iteration. Activates for junior/mid PM fundamentals — first time writing a spec, first roadmap, learning OKRs, validating a feature idea, designing and prioritizing features, running user research, or developing as a PM. Also triggers when evaluating a product decision or building anything at your company — this skill applies across the full feature lifecycle. For senior PM deliverables (4D roadmaps, stakeholder narratives, OKR loops), use product-management. For PM leadership (portfolio strategy, coaching, team composition), use product-strategy-leadership.
-
prayceo Bundle Product Strategy LeadershipApplies Product Strategy and Product Leadership frameworks to PM leaders and directors making strategic product decisions, team building, PM development, and organizational alignment. Activates for PM leaders/directors — portfolio prioritization, Four Types of Product Work allocation, PM evaluation or coaching, team composition, hiring PMs, managing up, connecting product work to company strategy, power user dynamics, PMF expansion, growth diagnostics, or communicating strategy to stakeholders. Triggers proactively when setting quarterly priorities, evaluating team performance, diagnosing slowing growth, coaching a PM, hiring, or making resource allocation decisions at your company. For PM fundamentals (first specs, basic roadmaps, learning OKRs), use product-foundations. For senior PM deliverables (4D roadmaps, stakeholder narratives, OKR loops), use product-management.
-
richkuo Skill App PrdUse when the user wants an app idea turned into a Product Requirements Document (PRD) committed to a repo — "create a PRD", "/app-prd", "turn this idea into a PRD", or a raw idea dump ending with "save it to this repo". Produces a complete, section-numbered PRD.md landed via worktree + PR, bootstrapping an empty repo if needed. Stage 1 of the new-app-pipeline.
-
richkuo Skill Prd QuestionsUse when the user wants every open question in a PRD resolved interactively — "ask me all questions", "/prd-questions", "let's resolve the open questions". Sweeps the PRD for open questions and ambiguities, asks them in batched multiple-choice form with recommendations, folds every answer back into the owning spec section, and empties the Open Questions section. Stage 2 of the new-app-pipeline.
-
richkuo Skill Prd To IssuesTurn a finished Product Requirements Document (PRD) into GitHub milestones and complete, scored issues with typed dependencies and Execution blocks. Use for "file the issues from the PRD", "/prd-to-issues", or "break this into GitHub issues". Stage 4 of the new-app-pipeline.
-
richkuo Skill New App PipelineUse when the user wants to take a new app from raw idea to running multi-agent implementation — "/new-app-pipeline", "let's build a new app", "run the app pipeline on this idea". Orchestrates the full sequence - idea → PRD → question refinement → GitHub issues with Execution blocks → execution-plan review → milestone pre-flight → milestone workflow — with a user checkpoint between every stage.
-
cadugevaerd Bundle BacklogOrquestra Backlog v2.1 com preview, fail-closed e confirmação explícita.
-
cadugevaerd Skill Backlog AddAdiciona item a backlog existente.
-
cadugevaerd Skill Backlog EditEdita campos suportados de backlog ou item.
-
cadugevaerd Skill Backlog InitCria o armazenamento e backlogs v2 suportados.
-
cadugevaerd Skill Backlog ListLista backlogs ou itens sem mutação.
-
cadugevaerd Skill Backlog TodoEscaneia TODO/FIXME software-only e aplica somente com opt-in, hash e confirmação.
-
cadugevaerd Skill Backlog MergeInspeciona e aplica merges somente após snapshots, revisions e confirmação.
-
cadugevaerd Skill Backlog DoctorVerifica runtime e integridade sem mutar.
-
cadugevaerd Skill Backlog ExportExporta formato derivado suportado sem mutar fonte.
-
cadugevaerd Skill Backlog FormatPropõe e aplica formatos de backlog com confirmação humana explícita.
-
cadugevaerd Skill Backlog ImportImporta JSON v3 estrito com preview, confirmação e SHA-256; separa migração v1.
-
cadugevaerd Skill Backlog UpdateVerifica, atualiza e migra backlogctl 2.1 com SHA-256, rollback e backup.
-
cadugevaerd Skill Backlog ArchiveSoft-archive obsolete or source-less backlog items with an audit reason.
-
cadugevaerd Skill Backlog ContextExecuta e diagnostica a família de contextos do Backlog v2 com confirmação explícita.
-
cadugevaerd Skill Backlog TransitionTransita item entre estados canônicos.
-
cadugevaerd Skill Backlog ConsolidadoSolicita exportação consolidated canônica.
-
cadugevaerd Skill Backlog Reconcile StatusAudited human-confirmed recovery of a verified backlog status inconsistency.
-
cadugevaerd Skill Code Review CaduCode review de pull request com veredicto GO/NO-GO por finding sobre o merge — findings GO confirmadas podem ser registradas via backlogctl após seleção explícita do backlog associado. Use quando for revisar uma PR do GitHub e quiser a triagem automática dos findings entre 'bloqueia merge' e 'diferir para o backlog'. Fork personalizado (Cadu) do plugin oficial code-review da Anthropic.
-
irahardianto Skill Feature Flags Principles 2Feature flag patterns ONLY when PRD/arch requires. Flag evaluation, lifecycle, testing, infrastructure. Do NOT load speculatively.
Frequently asked questions
What are Product & Planning agent skills?
Product & planning agent skills structure the thinking side of building: specs, PRDs, user stories, roadmaps, and prioritization frameworks. Install one and your AI agent produces planning documents with the same rigor and format every time.
Which Product & Planning skills are most installed?
Popular Product & Planning skills on SkillMD right now include trd, lead-role, peer-role. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Product & Planning skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.