pm-agent_skill
- TypeScript
181
GitHub Stars
1
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill first-fluke/fullstack-starter --skill pm-agent- SKILL.md1.9 KB
Overview
This skill is a virtual product manager that decomposes feature requirements into actionable tasks with clear priorities, dependencies, and acceptance criteria. It emphasizes API-first design, testable tasks, and minimal coupling to maximize parallel work. The output is a structured plan suitable for orchestration and handoff to implementation agents.
How this skill works
The agent analyzes high-level requirements and translates them into a task board with individual tasks assigned to agents, each including title, acceptance criteria, priority, and dependencies. It enforces an API-first approach, includes security and testing considerations in every task, and minimizes inter-task dependencies to enable parallel execution. The agent produces both machine-readable plans and human-friendly summaries for sprint planning.
When to use it
- Breaking down complex features into implementable tasks for cross-functional teams
- Assessing technical feasibility and proposing high-level architecture or API contracts
- Prioritizing work, planning sprints, and sequencing dependent work
- Defining clear acceptance criteria and test scope before development
- Preparing handoffs between design, backend, frontend, and QA agents
Best practices
- Start with API contracts and data models before creating implementation tasks
- Ensure each task is completable by a single agent and includes testing and security steps
- Keep tasks coarse enough to avoid needless fragmentation but specific enough to be actionable
- Minimize dependencies so work can proceed in parallel where possible
- Include priority and acceptance criteria for every task to streamline triage and QA
Example use cases
- Turn a product spec for a new feature into a prioritized sprint backlog with dependencies
- Draft API endpoints and data models, then generate implementation tasks for frontend and backend
- Refine an ambiguous feature request into clearly scoped tasks with measurable acceptance tests
- Re-plan a monorepo migration by listing parallelizable tasks and required sequencing
FAQ
No. The agent generates tasks and plans; execution and code changes should be delegated to implementation and QA agents.
How detailed should each task be?
Each task should be specific enough to be completed by a single agent, include acceptance criteria and test steps, but avoid splitting a cohesive work item into unnecessary sub-tasks.
