How do I install the Prd Goal Delivery skill?

Run npx skillmds@latest add flpbalada/prd-goal-delivery in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Prd Goal Delivery safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Prd Goal Delivery?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Prd Goal Delivery free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Prd Goal Delivery?

flpbalada (@flpbalada) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Prd Goal Delivery by flpbalada — Agent Skill

Name: Prd Goal Delivery
Author: flpbalada

Prd Goal Delivery

Drive PRD implementation through a durable /goal, scoped parallel implementation agents, independent QA ownership, acceptance evidence, and persona-based test instructions. Use when a PRD must be delivered end-to-end and every acceptance criterion must be verified before marking the goal complete.

flpbalada bafda0f 2.1 KB Updated Sep 17, 2026

File contents

PRD Goal Delivery

Goal

Create new /goal for this PRD:

Deliver every acceptance criterion successfully.

First Pass

Read PRD.
Extract scope.
Extract acceptance criteria.
Define evidence required for each criterion.
Identify target personas affected by new functionality.

Agent Setup

Spawn parallel agents for independent workstreams. Use as many agents as useful, no more.

Give each agent:

Dedicated /goal.
Clear scope.
Expected output.
Evidence required.

Required Agents

Agent	Responsibility
Implementation agents	Build independent pieces.
QA agent	Own independent quality verification.

QA Responsibilities

QA agent must:

Build acceptance checklist from PRD.
Verify each criterion with precise evidence.
Run or request tests/checks.
Reject incomplete or unverified work.
Report gaps, risks, regressions.

Completion Gate

Do not mark /goal complete until:

All implementation results are synthesized.
QA confirms every acceptance criterion passes.
Final answer includes acceptance checklist with status and evidence.
Final answer includes persona-based test instructions.

Final Answer Format

Acceptance Checklist

Criterion	Status	Evidence
[criterion]	pass / fail	[command, output, screenshot, file, or behavior proof]

Persona Test Instructions

For each affected persona, include:

Persona name / role: [name and role]
Goal: [goal user wants to achieve]
Steps: [steps to test new functionality]
Expected result: [expected result per step]
Edge cases / failure states: [states user should try]

Failure Loop

If any criterion fails:

Keep /goal active.
Dispatch follow-up fix agent.
Re-run QA on failed criteria.

---name: prd-goal-deliverydescription: Drive PRD implementation through a durable /goal, scoped parallel implementation agents, independent QA ownership, acceptance evidence, and persona-based test instructions. Use when a PRD must be delivered end-to-end and every acceptance criterion must be verified before marking the goal complete.---# PRD Goal Delivery## GoalCreate new `/goal` for this PRD:> Deliver every acceptance criterion successfully.## First Pass- Read PRD.- Extract scope.- Extract acceptance criteria.- Define evidence required for each criterion.- Identify target personas affected by new functionality.## Agent SetupSpawn parallel agents for independent workstreams.Use as many agents as useful, no more.Give each agent:- Dedicated `/goal`.- Clear scope.- Expected output.- Evidence required.### Required Agents| Agent | Responsibility || --- | --- || **Implementation agents** | Build independent pieces. || **QA agent** | Own independent quality verification. |## QA ResponsibilitiesQA agent must:- Build acceptance checklist from PRD.- Verify each criterion with precise evidence.- Run or request tests/checks.- Reject incomplete or unverified work.- Report gaps, risks, regressions.## Completion GateDo not mark `/goal` complete until:- [ ] All implementation results are synthesized.- [ ] QA confirms every acceptance criterion passes.- [ ] Final answer includes acceptance checklist with status and evidence.- [ ] Final answer includes persona-based test instructions.## Final Answer Format### Acceptance Checklist| Criterion | Status | Evidence || --- | --- | --- || [criterion] | pass / fail | [command, output, screenshot, file, or behavior proof] |### Persona Test InstructionsFor each affected persona, include:- **Persona name / role:** [name and role]- **Goal:** [goal user wants to achieve]- **Steps:** [steps to test new functionality]- **Expected result:** [expected result per step]- **Edge cases / failure states:** [states user should try]## Failure LoopIf any criterion fails:- Keep `/goal` active.- Dispatch follow-up fix agent.- Re-run QA on failed criteria.

Frequently asked questions