B2B PM Super Workbench
Paste the following prompt into your AI chat to install this skill:
Please install @user_82981261/b2b-pm-workbench using https://skillhub.cn/install/skillhub.md.
About this skill
What problem it solves
B2B product work often fails not because features are missing, but because requirements, roles, permissions, compliance, integration, and AI risks are treated separately. This workbench treats the B2B product lifecycle as a structured pipeline: strategy, discovery, prioritization, solution design, AI product design, prototyping, architecture diagrams, documentation, development collaboration, growth, GTM, and operations. It is aimed at product and engineering teams that need to turn customer demands, enterprise constraints, and delivery estimates into reviewable artifacts.
How it works
Each stage follows a consistent shape: inputs, process, frameworks, deliverables, quality gates, and AI acceleration. Strategic analysis uses PESTLE, Porter’s Five Forces, SWOT, BMC, and value proposition tools. Discovery applies JTBD, signal-weighted sourcing, and RICE-style scoring. Design covers role matrices, approval flows, multi-tenant choices, audit logs, API, Webhook, SSO, and integration levels. AI modules cover prompt, context, memory, evaluation, RAG, agent orchestration, and human-in-the-loop controls. Additions such as GraphRAG, Agentic RAG, MCP, and Computer Use are positioned as options for knowledge links, external system access, and legacy GUI workflows, with explicit permission and audit requirements.
Boundaries and notes
Use it for structuring PRDs/BRDs, requirement reviews, B2B AI scoping, and GTM drafts. It does not replace legal, security, financial, or architecture decisions. Dynamic areas such as pricing, SLA, compliance, and data security need current verification. For high-risk automation, keep human approval, reversibility, explainability, and refusal boundaries.
Use Cases
- After a lost-deal review, use sales feedback and competitor feature gaps to produce a prioritized B2B backlog.
- Before drafting an approval-workflow PRD, define role-action permission matrices, timeout policies, and audit log fields.
- While scoping an enterprise knowledge QA feature, compare basic RAG, GraphRAG, and Agentic RAG applicability.
- During agent integration selection, list MCP tool permissions, audit trails, and human-in-the-loop checkpoints.
Best For
- B2B SaaS product managers who need to turn strategy, competitor input, and delivery estimates into reviewable roadmaps.
- Solution managers handling customer customizations who must document contract terms, permissions, compliance, and rollout plans.
- Product engineers designing enterprise AI features who need to define RAG, agent, HITL, and risk boundaries.
- Engineering leads reviewing PRD/BRD quality who need exception flows, audit requirements, integration details, and acceptance criteria.
Related Skills
Guides WeChat merchant payment integration by routing JSAPI, Mini Program, APP, H5, Native, and payment-code scenarios to the right product.
AI agent tool for generating HTML proposals for client visit business scenarios, featuring deep research and dynamic mainline mapping.
Bid Proposal Verification Tool is used to verify the consistency between bid proposals and tender documents, checking table of contents, page numbers, attachments, and seals, based on Shibot Technology's bid data API.
An AI engine built on extensive bidding data to precisely search for tender projects and potential clients using natural language or structured criteria.