Skill0 repo starsupdated yesterday

mindforge-verify-work

mindforge-verify-work performs conversational user acceptance testing on built features while maintaining session state across multiple tests. Use this skill to validate that completed development work functions correctly from an end-user perspective, automatically diagnose any failures encountered, plan remediation steps, and prepare fixes for execution. It generates timestamped UAT reports documenting all test results and their outcomes.

View source Repository: MindForge

Install in Claude Code

Copy

git clone --depth 1 https://github.com/sairam0424/MindForge /tmp/mindforge-verify-work && cp -r /tmp/mindforge-verify-work/.agent/skills/mindforge-verify-work ~/.claude/skills/mindforge-verify-work

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

<objective>
Validate built features through conversational testing with persistent state.

Purpose: Confirm what the agent built actually works from user's perspective. One test at a time, plain text responses, no interrogation. When issues are found, automatically diagnose, plan fixes, and prepare for execution.

Output: {phase_num}-UAT.md tracking all test results. If issues found: diagnosed gaps, verified fix plans ready for /mindforge-execute-phase
</objective>

<execution_context>
@.agent/workflows/mindforge-verify-work.md
@.agent/templates/UAT.md
</execution_context>

<context>
Phase: $ARGUMENTS (optional)
- If provided: Test specific phase (e.g., "4")
- If not provided: Check for active sessions or prompt for phase

Context files are resolved inside the workflow (`init verify-work`) and delegated via `<files_to_read>` blocks.
</context>

<process>
Execute the verify-work workflow from @.agent/workflows/mindforge-verify-work.md end-to-end.
Preserve all workflow gates (session management, test presentation, diagnosis, fix planning, routing).
</process>