skills.rest
diane-defores
diane-deforesOFFICIAL
Explore all skills by this author →
GitHub

sf-test

Guide human testers through manual user scenarios and record bug evidence.

Updated Aug 27, 2026
Search Tags:#product validation#manual testing#bug report#AI verification#bug tracking#test campaign
One-click install
npx skills add https://github.com/diane-defores/shipflow --skill sf-test
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sf-test
Source: https://github.com/diane-defores/shipflow/tree/main/skills/sf-test
Command: npx skills add https://github.com/diane-defores/shipflow --skill sf-test

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It addresses the challenge of verifying real user flows in AI-assisted product development by guiding human testers through concrete steps and recording durable evidence, thereby transforming ephemeral observations into project memory.

Core Features & Use Cases

  • Manual Test Campaigns: Guides users through specific user scenarios to validate features or bugs.
  • Structured Result Logging: Prompts for clear pass/fail outcomes, environment details, and evidence collection.
  • Bug Recording: Creates detailed bug files for failing scenarios and updates compact indices for triage.
  • Use Case: When a new feature is deployed, run guided manual tests, record outcomes, and link failures to bug reports for streamlined debugging.

Quick Start

Initiate a manual test of the login flow, follow the steps, then report the results directly in the prompt.

Frequently Asked Questions about sf-test

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I perform manual testing for AI-assisted applications?▼

Manual testing for AI-assisted applications is guided by walking human testers through concrete user scenarios to validate features, capturing structured pass/fail outcomes and environment details for durable project memory.

What is the best way to track bugs found during product validation?▼

Tracking bugs found during product validation is best handled by creating detailed bug files for failing scenarios and updating compact indices for triage. This manages the bug lifecycle and links failures directly to streamlined debugging.

How do I capture and log process evidence during a test campaign?▼

Capturing process evidence during a test campaign is achieved through structured result logging that prompts for clear pass/fail outcomes, environment details, and evidence collection, ensuring verification data is durably recorded.

Can I use manual test campaigns to verify newly deployed AI features?▼

Manual test campaigns can verify newly deployed AI features by guiding you through specific user scenarios, recording outcomes, and linking any failures to detailed bug reports for streamlined debugging and project memory.

Why does AI workflow verification require structured bug reports?▼

AI workflow verification requires structured bug reports because ephemeral human observations must be transformed into durable project memory, enabling reliable bug lifecycle management and streamlined debugging for future iterations.

Related Skills

Explore More Software Engineering Skills→
Lev-itLev-it

test-scenarios

Create structured test scenarios from user stories.

Official
Intermediate
CANTAGESTUDIOCANTAGESTUDIO
3

systematic-debugging

Diagnose software defects through a four-phase root-cause investigation framework.

Community
Advanced
anderson-0anderson-0
4

qa-generate-e2e-tests

Generate automated end-to-end tests for API services and UI workflows.

Community
Intermediate
proffesor-for-testingproffesor-for-testing
436

shift-left-testing

Generate and execute unit, integration, and end-to-end tests within CI/CD workflows.

Community
Advanced