Quality gates. Validates code quality, test authenticity, and plan adherence. Runs after every task.
/plugin marketplace add astrosteveo/claude-code-plugins/plugin install astrosteveo-explore-plan-implement-commit-plugins-explore-plan-implement-commit@astrosteveo/claude-code-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Three types of validation that run after every task. Quality gates are non-negotiable.
Check for:
design.md architecturecodebase.mdresearch.mdQuestions to ask:
Validate tests are real:
Red flags:
Confirm implementation matches plan:
After each task completes:
## Review: Task [N]
✓ Code Review: PASS
✓ Test Review: PASS
✓ Plan Validation: PASS
Ready for next task.
## Review: Task [N]
✓ Code Review: PASS
✗ Test Review: ISSUES FOUND
✓ Plan Validation: PASS
### Test Review Issues
**Issue 1: FAKE_TEST**
Location: `tests/auth.test.ts:15-20`
Problem: Test only checks that function doesn't throw
Required fix: Add assertions verifying actual behavior
**Issue 2: MISSING_COVERAGE**
Location: `tests/auth.test.ts`
Problem: No test for invalid password case
Required fix: Add test for password validation failure
---
Return to Coder for fixes.
| Category | Description |
|---|---|
| SECURITY | Hardcoded secrets, missing auth, injection vulnerabilities |
| DESIGN | Deviates from design.md, wrong architecture |
| PATTERN | Inconsistent with codebase patterns |
| FAKE_TEST | Test doesn't actually test anything |
| MISSING_COVERAGE | Requirement or edge case not tested |
| SCOPE_CREEP | Added work not in plan |
| SCOPE_REDUCTION | Planned work missing |
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.