prd-standards
Skill7 starsChanged 3 months agoMITView on GitHub
Defines PRD structure, user story format with 4 Risks assessment, EARS-format acceptance criteria, and delivery readiness thresholds. Use when writing PRDs, drafting user stories, defining acceptance criteria, or reviewing PRD quality and completeness.
In this repository15 other files it gives its agents.
- blueprint-standardsSkill
- business-contextSkill
- design-perspectiveSkill
- hypothesis-disciplineSkill
- product-principlesSkill
- prototype-guideSkill
- recipe-blueprintSkill
- recipe-defineSkill
- recipe-discoverSkill
- recipe-personaSkill
- recipe-prototype-promptSkill
- recipe-refine-visualsSkill
- recipe-reflectSkill
- recipe-validateSkill
- recipe-visionSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 55
Use EARS-format acceptance criteria when its event, state, or conditional form makes the requirement more testable or a downstream consumer …
- Distinctive: line 58
Use When (event-driven), While (state-driven), or If-Then (conditional) patterns
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
PRD Standards
Purpose
Canonical reference for PRD quality — shared by both authoring (recipe-define) and review (doc-reviewer) workflows. Ensures the author and reviewer apply the same standards.
Reference Selection
| Task | Read |
| Writing or reviewing a full PRD | references/prd-template.md |
| Writing or reviewing acceptance criteria | references/acceptance-criteria.md |
| Assessing story readiness or drafting user stories | references/user-story-guide.md |
Relationship to product-principles
4 Risks framework, Confidence Meter (0-10), and OST hierarchy are defined in product-principles. This skill operationalizes them in the PRD context — templates, thresholds, and format. For authoritative definitions, always defer to product-principles.
PRD Structure
A nautilus PRD uses the portions of the standard structure required by its delivery consumer. See references/prd-template.md for the available structure.
Core sections (include when they carry a delivery decision or required evidence):
- Overview (one-line summary, background)
- Users and Stories
- Functional Requirements (with EARS-format ACs)
- Design Context
- Non-Functional Requirements (including accessibility)
- Success Criteria (tied to Product Outcomes)
- Technical Considerations
Nautilus extensions (include at the smallest scope that affects delivery):
- Hypothesis & validation references in Overview
- 4 Risks evidence at the scope that changes delivery readiness
- Design Context derived from design artifacts and prototypes
- Unvalidated assumptions section in Technical Considerations
User Story Standards
User stories remain grounded in an evidenced persona or user distinction. Record 4 Risks evidence at the smallest scope that changes delivery readiness; shared evidence does not need to be repeated per story. See references/user-story-guide.md for the output and readiness rules.
Key rules:
- Reference a specific persona from
docs/product/personas/, not generic "user" - Each material risk has evidence available to the delivery decision
- "Validated enough" is judged by cost x risk x reversibility, not a fixed threshold
- Remaining risks are documented explicitly, not hidden
Acceptance Criteria Standards
Use EARS-format acceptance criteria when its event, state, or conditional form makes the requirement more testable or a downstream consumer requires it. See references/acceptance-criteria.md for selection, quality, and traceability rules.
Key rules:
- Use When (event-driven), While (state-driven), or If-Then (conditional) patterns
- Each AC is testable with a clear pass/fail
- User-facing ACs cover relevant states (loading, empty, error, partial, success)
- Accessibility ACs included for UI features
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

