Run Acceptance — Testing skill for Claude Code
Run the current phase's acceptance tests — attempts the automatable ones, proposes writebacks to acceptance-test-results.md and the open PR body.
How to install Run Acceptance
Installs to ~/.claude/commands/iammrcupp-claude-project-kit-run-acceptance.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/IamMrCupp/claude-project-kit/HEAD/.claude/commands/run-acceptance.md -o ~/.claude/commands/iammrcupp-claude-project-kit-run-acceptance.md Restart Claude Code, or start a new session, for it to be picked up.
What Run Acceptance does
description: Run the current phase's acceptance tests — attempts the automatable ones, proposes writebacks to acceptance-test-results.md and the open PR body. Defers UI / judgment items to the human. argument-hint: [test-N | all]
Precheck — is this a kit project?
Before doing anything else:
- Run this Bash command to print the absolute path of this project's auto-memory pointer file (
reference_ai_working_folder.md), then use theReadtool on the exact absolute path the com
Alternatives in Testing
- Axiom — Development Changelog — Purpose: Historical record of Axiom development milestones, TDD testing results, and architectural decisions 671 ★
- UI Review — Parallel user story validation — discovers YAML stories, fans out bowser-qa-agents, aggregates results 222 ★
- Comprehensive Testing Results - MCP Notification Handler Fix — Comprehensive Testing Results - MCP Notification Handler Fix skill 219 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Unity Refine
Refines a raw GitHub issue into an implementation-ready spec — problem, acceptance criteria, scope, affected s
Review Queue
Triage pending human-review items — resolve cruft, walk Decisions/Actions/Testing/Deferred Visual buckets, ref
Implement Phase
Autonomously execute a whole roadmap phase - resolve features to specs, create missing ones, then loop impleme
Create Uat Plan
Generate a human-readable User Acceptance Test plan from a completed spec, so a person can validate behavior w
Plan Freeze
Commit the active feature's spec.md + plan.md on a plan/ branch and open a PR for human review. Wraps scripts/
Verify Work
Execute a work item's testing-plan.md after implementation — run the planned activities, record results, commi
Related Agents
Project Guide
Phase-aware orchestrator and entry point for every project. On invocation, delivers a structured status snapsh
Unblocker
Runs the bounded blocker loop — at most 20 attempts, each with a distinct hypothesis and exactly one changed v
Gate Repair
Attempts to fix simple gate failures (missing templates, incomplete sections, placeholder content) before esca