Find agent skills by outcome

- Name concrete validation: “Run npm test”

“Add unit tests for X”

- If there are unknowns

include a tiny Open questions section (max 3).

- Verb-first: “Add…”

“Refactor…”

- Each checklist item should be a concrete action and

when helpful

- If unsure but not blocked

make a reasonable assumption and proceed.

- Identify constraints (language

frameworks

- Read README.md and any obvious docs (docs/

CONTRIBUTING.md

OpenAI Create Plan Skill

Turn a user prompt into a single

actionable plan delivered in the final assistant message.

test('should handle edge cases'

() => {

test('should fail with original bug'

() => {

test('should pass after fix'

() => {

- [ ] Fix addresses the root cause

not just symptoms

For EVERY fixed bug

provide:

3. Implement minimal

focused fix

- System impact (performance

stability

- Business impact (compliance

revenue

describe('BUG-[ID]: [Bug description]'

() => {

- Performance bottlenecks (N+1 queries

inefficient algorithms)

- User impact (UX degradation

data loss

For each identified bug

document:

- Security vulnerabilities (SQL injection

XSS

- State management issues (race conditions

inconsistent state

- Logic errors (incorrect conditions

wrong calculations