- Home
- Skills
- Anthropics
- Knowledge Work Plugins
- Feature Spec
feature-spec_skill
- Python
- Official
7.4k
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 anthropics/knowledge-work-plugins --skill feature-spec- SKILL.md8.7 KB
Overview
This skill generates clear, structured product requirements documents (PRDs) and feature specifications to define what to build, why it matters, and how to measure success. It produces problem statements, goals, non-goals, prioritized user stories, requirements with acceptance criteria, success metrics, open questions, and timeline guidance. Use it to align stakeholders and reduce ambiguity before development starts.
How this skill works
Provide the feature context and any supporting research or metrics. The skill drafts a PRD using a standard template: problem statement, goals, non-goals, user stories, categorized requirements (P0/P1/P2), acceptance criteria, success metrics, open questions, and timeline considerations. It emphasizes testable acceptance criteria, measurable outcomes, and scope controls to prevent creep.
When to use it
- Scoping a new feature before design and engineering work begins
- Writing a PRD to align product, design, and engineering stakeholders
- Defining acceptance criteria for tickets or launch gating
- Prioritizing requirements during planning or roadmap discussions
- Documenting product decisions for future reference and audits
Best practices
- Start with a concise, evidence-backed problem statement tied to data or customer feedback
- Keep P0 requirements minimal and ask: 'Would the feature still solve the problem without this?'
- Write user stories focused on user needs and benefits, not UI implementations
- Use Given/When/Then acceptance criteria to make testing unambiguous
- Define specific success metric targets, a measurement method, and evaluation windows
- List non-goals explicitly to prevent scope creep and set stakeholder expectations
Example use cases
- Specifying an SSO integration: problem, user stories for admins and users, P0 requirements, and rollout metrics
- Drafting an onboarding improvement PRD to increase activation and reduce time-to-first-value
- Documenting a billing change with compliance deadlines, dependencies, and timeline phasing
- Creating acceptance criteria for a mobile feature that includes edge cases and error handling
- Prioritizing a set of feature requests into Must-have, Should-have, and Future considerations
FAQ
Include user research, support tickets, usage metrics, or customer feedback that quantifies frequency and impact.
How many success metrics should I define?
Pick 3–5: a couple of leading indicators (adoption, activation) and one or two lagging indicators (retention, revenue) with concrete targets and measurement method.