Claude Skill

spec-to-prd

Turn the current conversation, repo understanding, and clarified decisions into a PRD. Use when a vague feature, client request, internal roadmap item, or discovery thread needs to become a durable product artifact. Prefer repo/domain language, explicit scope, implementation deci

LLM Mart · 0 points · 2 views 0 listing impressions 0 install-command copies
Download markoblogo-abvx-agent-skills-skills_spec-to-prd-37a7146.zip · 1 KB

Install

skills CLI npx skills add https://github.com/markoblogo/abvx-agent-skills/tree/main/skills/spec-to-prd
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install markoblogo-abvx-agent-skills@llmmart
Git git clone https://github.com/markoblogo/abvx-agent-skills.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole markoblogo/abvx-agent-skills collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Spec To PRD

Convert current understanding into a durable PRD without re-running the whole discovery session.

Workflow

  1. Synthesize what is already known from the conversation and repo.
  2. Use the project's domain language and existing architectural decisions.
  3. Identify the highest useful seams for implementation and testing.
  4. Confirm only the few assumptions that would distort the PRD if wrong.
  5. Produce one PRD artifact:
    • issue tracker body;
    • markdown file;
    • handoff-ready document.

PRD Shape

Include:

  • problem statement;
  • solution from the user's perspective;
  • extensive user stories;
  • implementation decisions;
  • testing decisions;
  • out of scope;
  • further notes and open assumptions.

Rules

  • Do not dump file paths unless they are durable anchors.
  • Do not include code unless a small shape encodes a real decision more precisely than prose.
  • Keep scope sharp; explicitly name what is out of scope.
  • If discovery is too weak, route back to rapid-grilling or doc-grounded-grilling first.

Final Report

State where the PRD lives, what assumptions remain, and the best next step: issue breakdown, prototype, or execution.

Files (abvx-agent-skills)
  • agents
    • openai.yaml 190 B
      Loading…
  • SKILL.md 1.6 KB
    ---
    name: spec-to-prd
    description: Turn the current conversation, repo understanding, and clarified decisions into a PRD. Use when a vague feature, client request, internal roadmap item, or discovery thread needs to become a durable product artifact. Prefer repo/domain language, explicit scope, implementation decisions, testing decisions, and issue-tracker-neutral output.
    license: MIT
    metadata:
      abvx_status: experimental
      abvx_origin: adapted
    ---
    
    # Spec To PRD
    
    Convert current understanding into a durable PRD without re-running the whole discovery session.
    
    ## Workflow
    
    1. Synthesize what is already known from the conversation and repo.
    2. Use the project's domain language and existing architectural decisions.
    3. Identify the highest useful seams for implementation and testing.
    4. Confirm only the few assumptions that would distort the PRD if wrong.
    5. Produce one PRD artifact:
       - issue tracker body;
       - markdown file;
       - handoff-ready document.
    
    ## PRD Shape
    
    Include:
    
    - problem statement;
    - solution from the user's perspective;
    - extensive user stories;
    - implementation decisions;
    - testing decisions;
    - out of scope;
    - further notes and open assumptions.
    
    ## Rules
    
    - Do not dump file paths unless they are durable anchors.
    - Do not include code unless a small shape encodes a real decision more precisely than prose.
    - Keep scope sharp; explicitly name what is out of scope.
    - If discovery is too weak, route back to `rapid-grilling` or `doc-grounded-grilling` first.
    
    ## Final Report
    
    State where the PRD lives, what assumptions remain, and the best next step: issue breakdown, prototype, or execution.
    
  • SKILL_CARD.md 1.2 KB
    Loading…

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.