Edge CasesProduct ManagementDeliveryAI Agent Skill
deliver-edge-cases
A structured PM workflow for surfacing and cataloguing edge cases before a feature is considered ready to ship.
Install Options
Install into Claude Code, Cursor, Codex, or Antigravity with:
$ npx skills add product-on-purpose/pm-skills@deliver-edge-cases
Real Work Situation Solved
Write acceptance criteria for an AI feature without missing edge cases
“You've drafted acceptance criteria - but did you cover the cases where the AI answers wrong, ambiguous, or unsafe?”
5-Step Action Framework
- 1Write each scenario as Given/When/Then, not general prose.
- 2Cover the "normal" happy path first, then the "boundary" cases (minimum/maximum input).
- 3Add an "ambiguous" scenario - when the input doesn't give the AI enough to answer confidently.
- 4Add an "unsafe" scenario - when the input deliberately probes for a vulnerability or asks for policy-violating content.
- 5For every scenario, spell out the expected behavior when the AI gets it wrong - not just when it gets it right.
Before
"The AI must answer the user's question correctly."
After
"Given a question outside the model's training data, When confidence is too low to answer, Then the AI must say 'I'm not sure' instead of guessing."
Related Course Lesson
AI Agents for PM • Lesson 17
SKILL.md Source Instructions
SKILL.md • Read-only preview# Deliver Edge Cases Skill Systematically walk through boundary conditions, error states, and unusual inputs, then document expected behavior for each before calling a feature "done".