This skill should be used when the user asks to "validate changes", "run validation gate", "check before merge", "quality check", or needs comprehensive validation across security, quality, and architecture.
View on GitHubboshu2/agentops
vibe-kit
January 24, 2026
Select agents to install to:
npx add-skill https://github.com/boshu2/agentops/blob/main/plugins/vibe-kit/skills/validation-chain/SKILL.md -a claude-code --skill validation-chainInstallation paths:
.claude/skills/validation-chain/# Validation Chain Skill
Orchestrate specialist agents for comprehensive change validation.
## Overview
Route changes to appropriate specialists based on file types and content patterns:
- **Security Expert**: Auth, API, secrets, user input
- **Code Quality Expert**: All code changes (default)
- **Architecture Expert**: Schema, config, service boundaries
- **UX Expert**: UI components, user-facing changes
## Execution Flow
```
1. Identify Changed Files -> git diff --name-only or explicit list
2. Classify by Domain -> Pattern matching to specialists
3. Dispatch Parallel -> Task() to each relevant specialist
4. Aggregate Findings -> Triage matrix consolidation
5. Report + Create Issues -> Blockers become beads issues
```
---
## Phase 1: File Classification
### Pattern → Specialist Mapping
| Pattern | Specialist | Rationale |
|---------|------------|-----------|
| `**/auth/**`, `**/login/**` | security-expert | Auth code |
| `**/*.yaml`, `**/*.yml` | architecture-expert | Config/schema |
| `**/components/**`, `**/ui/**` | ux-expert | UI changes |
| `**/*.py`, `**/*.go`, `**/*.ts` | code-quality-expert | All code |
| `**/secrets/**`, `**/*cred*` | security-expert | Sensitive |
| `**/api/**`, `**/routes/**` | security-expert + code-quality-expert | API |
### Classification Logic
```bash
# Get changed files
git diff --name-only HEAD~1 HEAD > /tmp/changed_files.txt
# Or from staged
git diff --cached --name-only > /tmp/changed_files.txt
```
---
## Phase 2: Parallel Dispatch
Invoke specialists in parallel via Task():
```markdown
# For security-sensitive files
Task(
subagent_type="security-expert",
model="sonnet",
prompt="Review these files for security vulnerabilities: $SECURITY_FILES"
)
# For all code files
Task(
subagent_type="code-quality-expert",
model="sonnet",
prompt="Review code quality and complexity: $CODE_FILES"
)
# For config/schema files
Task(
subagent_type="architecture-expert",
model="sonnet",