Product & Planning

jamillazarev Skill

Start the next feature from the roadmap — the manual flow's main button.

jonathaneciana17-maker Bundle

Essential tools and frameworks for modern product management, from discovery to delivery.

clarentcinematics Bundle

Create decision memos that frame context, options, tradeoffs, risks, recommendation, and implementation implications. Use when Codex needs to turn analysis, stakeholder input, ambiguous choices, or strategic questions into a structured decision document for enterprise leaders.

clarentcinematics Bundle

Standardize project updates into concise status briefs with health, milestones, blockers, risks, owner actions, and escalation needs. Use when Codex needs to synthesize project notes, stakeholder updates, sprint summaries, launch plans, or program status into a leadership-ready brief.

clarentcinematics Bundle

Synthesize account notes, company research, CRM context, buying signals, stakeholder information, and customer artifacts into a sales-ready account research brief. Use when Codex needs to prepare account strategy, discovery planning, outreach angles, ICP fit, stakeholder mapping, or enterprise customer context.

clarentcinematics Bundle

Identify, evaluate, and prioritize enterprise workflows that can be automated with Codex Skills, scripts, tools, integrations, or operating-process changes. Use when Codex needs to analyze a process, find automation opportunities, estimate value, map inputs and outputs, or recommend a practical automation roadmap.

clarentcinematics Bundle

Draft tailored enterprise proposals from customer needs, discovery notes, constraints, product or service capabilities, proof points, commercial context, and implementation assumptions. Use when Codex needs to create a proposal, statement of work draft, solution narrative, scope summary, or next-step document for a revenue workflow.

clarentcinematics Bundle

Convert product requirements, feature notes, customer asks, PRD drafts, issue descriptions, or rough specifications into acceptance criteria, test scenarios, dependencies, launch constraints, owners, and open questions. Use when Codex needs to make requirements implementation-ready without inventing scope, owners, or commitments.

format-technologies Bundle

A guide for agents querying customer conversations through the Format MCP: how to navigate its tools, how to query, when to use what, what to be careful of, and the practices that keep an answer truthful, reliable and reproducible. Orient with describe_org first — its analysisGuide carries the reading rules and each tool description carries its own traps; this guide holds what they cannot: which sequence of calls answers which question, the traps that live between calls, and how to state a result so it can be re-run. Skipping it produces confident answers that do not survive checking. Use it on any Format search, and on 'what are customers saying about…', 'how many customers asked for…', 'is X a real theme or one loud account', 'is there evidence for this roadmap item', 'what has [account] been saying', and on any Format result about to be summarised for a person. It produces no document of its own; writing one up is format-report-authoring.

format-technologies Bundle

Use when a product manager or leader wants to check a roadmap against real customer evidence using Format MCP — answering 'are customers asking for what we're building?' and the inverse, 'what are customers asking for that we're not building?'. Canonical invocation: 'using the Format MCP and the format-roadmap-check skill, check this roadmap' followed by a pasted list of roadmap items or a reference to a tracker project/epic. Also triggers on 'validate this roadmap against customer feedback', 'is there evidence for these roadmap items', 'what are customers asking for that isn't on the roadmap', 'roadmap evidence check', 'gap analysis on our roadmap'. Produces an evidence board: per-item customer evidence with links to every quote, plus the demand themes no roadmap item covers. It presents evidence and context rather than scoring items or recommending what to build or cut.

format-technologies Bundle

Use when a product manager or leader wants to check a roadmap against real customer evidence using Format MCP — answering 'are customers asking for what we're building?' and the inverse, 'what are customers asking for that we're not building?'. Canonical invocation: 'using the Format MCP and the cube-roadmap-check skill, check this roadmap' followed by a pasted list of roadmap items or a reference to a tracker project/epic. Also triggers on 'validate this roadmap against customer feedback', 'is there evidence for these roadmap items', 'what are customers asking for that isn't on the roadmap', 'roadmap evidence check', 'gap analysis on our roadmap'. Produces an evidence board: per-item customer evidence with links to every quote, plus the demand themes no roadmap item covers. It presents evidence and context rather than scoring items or recommending what to build or cut.

thatmike1 Bundle

Research/discovery orchestrator for open-ended questions whose answer may span multiple current, external, historical, or authenticated sources and where choosing the research surface is part of the task. Use when the user explicitly invokes /find-out or asks for broad, current, multi-source research. Do not trigger for ordinary codebase, issue-tracker, document, or conversation-history investigation with a known local source, even if the user says "find out", "look into", "dig into", or "explore"; use the relevant local tool directly. Sibling of /find-skills (skills only) and /deep-research (heavy multi-source reports).

yananlong Bundle

Generate, filter, rank, and hand off grounded research ideas from a broad research direction, problem area, literature landscape, Zotero corpus, paper limitation, or user notes. Use when asked to brainstorm publishable research ideas, find a direction, turn a broad area into candidate claims, choose what to work on, evaluate idea quality before novelty review, or create an ideation stage inside a coordinated research workflow. Prefer research-novelty-review when the user already has one concrete idea to pressure-test, research-experiment-plan when the claim is already frozen, and research-pipeline-planner when the main request is multi-stage project sequencing rather than ideation itself.

yananlong Bundle

Coordinate research as either a standalone staged planning pass or a durable orchestrated multi-skill workflow with shared artifacts, explicit work items, paper-level commitment, verifier-backed transitions, checkpoints, replay, observability, stage gates, evidence assurance, and controlled pivots. Use when asked to scope a research direction, inspect existing research artifacts, choose the next research stage, create a research brief or task board, coordinate a reusable research workflow, build a research roadmap or agenda, organize a research repo, turn notes into a phase plan, define milestones, decide what to do next, coordinate literature, ideation, novelty, experiments, auditing, review, paper planning, and rebuttal work, or prevent a project from drifting between paper identities.

yananlong Bundle

Run or audit literature discovery and evidence synthesis with explicit review profiles, high-recall discovery, seed and challenge-set testing, citation searching, corpus freezing, PRISMA 2020 core accounting, evidence extraction, confidence grading, and adversarial stress-testing across publications. Prefer peer-reviewed published versions over preprints. Use for systematic reviews, bounded evidence maps, state-of-the-art surveys with explicit methods, citation-integrity checks, novelty-critical prior-art searches, confidence-rated conclusions, or when a research commitment depends on reliable literature coverage.

vamseeachanta Skill

Product Roadmap Skill

jamillazarev Skill

Bring a backlog in from another tracker — the mapping is shown first, and issues arrive unassigned.

jamillazarev Skill

Add a feature mid-flight — grilled into a spec, ICE-scored against the backlog, slotted into a release.

khadir-syed Bundle

Draft one section of a product requirements document (PRD) from notes, a ticket, or a confirmed brief, and write it to a file only with explicit approval. Use when requirements are already reasonably clear and need to be written up; do not use on a vague or conflicting request — use the Requirements Gap Investigator first.

khadir-syed Bundle

Investigate a vague or incomplete feature request to surface unstated assumptions, missing constraints, and conflicting stakeholder signals before requirements are written. Use when a feature ask is ambiguous, underspecified, or conflicting; do not use to write a PRD, make product decisions, or evaluate an already-detailed spec.

nhouseholder Skill

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. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

zengxiansheng007 Bundle

Route business ideas and source materials into PRD, architecture design, development plan, or test plan skills with prerequisite checks, artifact state governance, RTM consistency, grill escalation, and change-impact reopening. Use when writing, reviewing, routing, or updating PRDs and delivery plans.

zengxiansheng007 Bundle

Create and review UI-test planning packets from PRD, design, Figma, HTML prototype, live URL, code evidence, and knowledge base sources. Use for test-point decomposition, coverage matrix design, ambiguity discovery, automation candidate screening, and execution readiness before Midscene exploration.

zengxiansheng007 Bundle

Prepare and review Midscene-first UI exploration from a ui-test-packet. Use for semantic browser exploration, prompt packet shaping, weak locator discovery, visible-state observation, and preserving successful or failed exploration strategies before deterministic Playwright verification.

zengxiansheng007 Bundle

Reusable Codex development hub and top-level router. Use when Codex must turn a user goal into a requirement anchor, research-backed PRD, development plan, test plan, landed implementation review, RAG writeback, publish manifest, A2A handoff packet, Claude/Midscene execution review loop, or gap-to-requirement decision cycle.

zengxiansheng007 Bundle

Turn business ideas, notes, rules, permissions, and source docs into a development-ready PRD with explicit scope, business rules, states, acceptance criteria, RTM, change governance, and grill-based ambiguity control. Use when creating, reviewing, or repairing a PRD from business sources.

roedyrustam Skill

Initial guardrail skill that enforces creating a comprehensive Product Requirements Document (PRD) before generating code. Use whenever the user starts a new project or feature and jumps straight to "build me X" without defined requirements. Trigger on phrases like "build me an app that...", "create a system for...", "I want to build...", or any greenfield request lacking clear scope. Also trigger when the user explicitly asks for a PRD or requirements document.

roedyrustam Skill

Roadmap and technical design for bootstrapping high-performance multi-tenant B2B/B2C SaaS MVPs. Use whenever the user wants to start a new SaaS product, plan architecture, choose a tech stack, or needs a launch checklist. Trigger on phrases like "build a SaaS", "SaaS MVP", "multi-tenant app", "launch a product", "Next.js SaaS boilerplate", or any product that needs auth, billing, and a dashboard. Covers Next.js 15, Tailwind CSS v4, Drizzle/Prisma, Stripe, Clerk, and Vercel AI SDK.

shinpr Bundle

Update existing design documents (Design Doc / PRD / ADR) with review and consistency verification.

shinpr Bundle

Determines which PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires and where each document lives. Use when deciding documentation scope or creating or reviewing one of these artifacts.

anubisrooster Skill

Generate a single self-contained, interactive HTML dashboard from a roadmap workbook (XLSX) for portfolio/program planning. Use this skill whenever the user wants an HTML roadmap, an interactive Gantt, a cross-team/pillar dependency map or DAG, a schedule-risk view, a resourcing/capacity view, or an executive summary built from a planning spreadsheet — especially when they say "make an interactive HTML", "build a dashboard from this roadmap", "visualize dependencies", "Gantt with dependencies", "schedule risks", or "executive report". Output is one offline .html file (no server, no build) with inline editing, browser-local persistence, and CSV export. Complements confluence-publish-html (to publish the result) and repo-mental-map-tpm.

anubisrooster Skill

Publish an interactive, script-bearing HTML artifact (dashboard, report, visualization) to Confluence — especially self-hosted Confluence Data Center/Server — reliably. Use this skill whenever the user wants to "put this HTML on Confluence", "embed a dashboard in a wiki page", "publish an interactive report to Confluence", or hits the common failure where Confluence strips <script>/<style> or the HTML macro is disabled. Produces a page that links to and/or iframe-embeds the artifact, plus a macro-ready fragment, and gracefully handles Data Center quirks (HTML macro disabled, attachment-upload API failures, inline-vs-download serving). Builds on confluence-dc-mcp (for the MCP connection) and pairs with roadmap-dashboard-html (which produces the HTML).

anubisrooster Bundle

Navigate and operate the live Metron Engineering Intel portal at https://latc.lenovo.com/metron — all sidebar pages (Overview, Team, Program, Jira Cadence, CTOO Partnerships, AI ROI, Contributors, Activity, Sync Jobs) plus Program Roadmap / FY26 pillar dependency tabs. Includes Confluence→Metron weekly Exec Summary refresh with quality gates (skip empty templates, fix strip artifacts, reject TBD impacts). Use when the user mentions Metron, LATC Engineering Intel, Program Roadmap, Team Calorie, Jira Cadence, CTOO/ATP partnerships, AI ROI/adoption, Contributors leaderboard, Activity Feed, Sync Jobs, or latc.lenovo.com/metron.

foryourhealth111-pixel Bundle

Query ChEMBL bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry.

expeqiu Bundle

用于生成中文《技术IP传播策划方案》的 Python 类型技能。适用于技术IP发布、重大事件传播、项目概述、传播目标拆解、受众分层、内容渠道规划、传播节奏ROADMAP、预算明细和效果评估。

migoxlab Skill

将 PRD、产品需求或功能说明转化为可评审的后端系统设计文档。用于用户要求从 PRD 生成后端技术方案、系统设计、接口设计、数据库设计、服务边界、架构评审文档或实现前设计文档。