admin-dashboard-qa
Use this skill when implementing, modifying, or fixing the admin dashboard (admin-dashboard-v2). Triggers for tasks involving dashboard UI, components, pages, features, hooks, or API integration. Orchestrates a rigorous QA workflow with PM review, use case writing, testing, and bug fixing cycles.
Best use case
admin-dashboard-qa is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use this skill when implementing, modifying, or fixing the admin dashboard (admin-dashboard-v2). Triggers for tasks involving dashboard UI, components, pages, features, hooks, or API integration. Orchestrates a rigorous QA workflow with PM review, use case writing, testing, and bug fixing cycles.
Teams using admin-dashboard-qa should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/admin-dashboard-qa/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How admin-dashboard-qa Compares
| Feature / Agent | admin-dashboard-qa | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use this skill when implementing, modifying, or fixing the admin dashboard (admin-dashboard-v2). Triggers for tasks involving dashboard UI, components, pages, features, hooks, or API integration. Orchestrates a rigorous QA workflow with PM review, use case writing, testing, and bug fixing cycles.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Admin Dashboard QA Workflow
This skill implements a rigorous multi-agent testing workflow for admin dashboard frontends. It automatically adapts to whichever dashboard version you're working on.
## Auto-Detection
When this skill activates, first determine which dashboard you're working on:
1. **Check the task context** - Does it mention a specific version?
2. **Check file paths** - Which package directory is involved?
3. **Default to active version** - Currently `admin-dashboard-v2`
**Dashboard Packages:**
- `packages/admin-dashboard-v2` - Current production version
- Any future `packages/admin-dashboard-*` directories
## Adaptive Configuration
Before starting, detect the dashboard's test setup:
```bash
# Find the correct package
DASHBOARD_DIR="packages/admin-dashboard-v2" # or detected version
# Check for test config
ls $DASHBOARD_DIR/vitest.config.ts # Vitest
ls $DASHBOARD_DIR/jest.config.js # Jest
ls $DASHBOARD_DIR/package.json # Check test scripts
```
Then adapt commands accordingly:
- **Vitest:** `pnpm test`, `pnpm test:coverage`
- **Jest:** `pnpm test`, `pnpm test -- --coverage`
- **Other:** Check `package.json` scripts
## Workflow Overview
```
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ PROJECT MANAGER │────▶│ USE CASE WRITER │────▶│ TESTER │
│ (Reviews scope) │ │ (Defines tests) │ │ (Executes tests)│
└─────────────────┘ └──────────────────┘ └─────────────────┘
│
┌──────────────────┐ │
│ DEVELOPER │◀─────────────┘
│ (Fixes bugs) │
└──────────────────┘
│
▼
┌──────────────────┐
│ FULL REGRESSION │
│ TEST │
└──────────────────┘
```
## Phase 1: Project Manager Review
Before any implementation begins:
1. Review the feature request/task description
2. Define acceptance criteria
3. Identify affected components
4. Estimate risk level (low/medium/high)
5. Create implementation checklist
Output a PM Summary like:
```markdown
## PM Summary: [Feature Name]
**Risk Level:** [low/medium/high]
**Affected Components:** [list]
**Acceptance Criteria:**
- [ ] Criterion 1
- [ ] Criterion 2
**Implementation Checklist:**
- [ ] Step 1
- [ ] Step 2
```
## Phase 2: Use Case Writer
Before testing, define comprehensive use cases by consulting `TESTING-MANUAL.md`:
1. Identify all user flows affected
2. Write test cases for happy paths
3. Write test cases for edge cases
4. Write test cases for error states
5. Define expected outcomes
Format each use case as:
```markdown
### UC-[ID]: [Use Case Name]
**Preconditions:** [Setup required]
**Steps:**
1. Step 1
2. Step 2
**Expected Result:** [What should happen]
**Test Type:** [unit/integration/e2e/manual]
```
## Phase 3: Developer Implementation
Implement the feature following:
1. Write unit tests FIRST (TDD when possible)
2. Implement the feature
3. Run `pnpm test` to verify unit tests pass
4. Self-review code for common issues
5. Hand off to Tester
## Phase 4: Tester Execution
Execute all defined use cases:
1. Run automated tests: `cd packages/admin-dashboard-v2 && pnpm test`
2. Check coverage: `pnpm test:coverage`
3. Execute manual test cases if needed
4. Document any failures with:
- Steps to reproduce
- Expected vs actual behavior
- Screenshot/error message if applicable
5. Report bugs to Developer
**Test Report Format:**
```markdown
## Test Report: [Feature Name]
**Date:** [YYYY-MM-DD]
**Tester:** Claude AI
### Automated Tests
- Total: X
- Passed: X
- Failed: X
- Coverage: X%
### Use Case Results
| UC ID | Description | Status | Notes |
|-------|-------------|--------|-------|
| UC-01 | ... | PASS/FAIL | ... |
### Bugs Found
1. BUG-001: [Description]
- Severity: [critical/high/medium/low]
- Steps to reproduce: ...
```
## Phase 5: Bug Fix Cycle
For each bug found:
1. Developer analyzes root cause
2. Developer implements fix
3. Developer writes regression test
4. Tester re-verifies the specific use case
5. Repeat until all bugs fixed
## Phase 6: Full Regression Test
After all bugs are fixed:
1. Run complete test suite: `pnpm test`
2. Verify coverage thresholds met (95% lines, 90% branches)
3. Re-execute ALL use cases from Testing Manual for affected features
4. Generate final test report
**IMPORTANT:** Only mark feature as complete when:
- [ ] All unit tests pass
- [ ] Coverage thresholds met
- [ ] All defined use cases pass
- [ ] No open bugs remain
## Commands
Replace `$DASHBOARD` with the detected dashboard directory (e.g., `admin-dashboard-v2`):
```bash
# Run all tests
cd planted-availability-db/packages/$DASHBOARD && pnpm test
# Run tests with coverage
cd planted-availability-db/packages/$DASHBOARD && pnpm test:coverage
# Run specific test file
cd planted-availability-db/packages/$DASHBOARD && pnpm test [path/to/test.tsx]
# Run tests in watch mode
cd planted-availability-db/packages/$DASHBOARD && pnpm test:watch
# Build check
cd planted-availability-db/packages/$DASHBOARD && pnpm build
# Lint check
cd planted-availability-db/packages/$DASHBOARD && pnpm lint
```
## Feature Discovery
When working on a NEW feature not in the Testing Manual:
1. **Explore the feature area:**
```bash
# Find related components
ls planted-availability-db/packages/$DASHBOARD/src/features/
ls planted-availability-db/packages/$DASHBOARD/src/pages/
```
2. **Find existing tests as patterns:**
```bash
# List test files for similar features
find planted-availability-db/packages/$DASHBOARD -name "*.test.tsx" -o -name "*.test.ts"
```
3. **Define NEW use cases** following the format in TESTING-MANUAL.md
4. **Add new use cases to TESTING-MANUAL.md** for future regression testing
## Reference Documents
- `TESTING-MANUAL.md` - Test case library (expand as needed)
- `TEST-REPORT-TEMPLATE.md` - Template for test reports
- Dashboard's `vitest.config.ts` or `jest.config.js` - Test configuration
- Dashboard's `package.json` - Available scriptsRelated Skills
administration
How to monitor usage, track costs, configure analytics, and measure ROI for Claude Code. Use when user asks about monitoring, telemetry, metrics, costs, analytics, or OpenTelemetry.
administering-linux
Manage Linux systems covering systemd services, process management, filesystems, networking, performance tuning, and troubleshooting. Use when deploying applications, optimizing server performance, diagnosing production issues, or managing users and security on Linux servers.
admin
Admin panel - RBAC, config, admin tools. Use when building admin UI.
admin-wsl
WSL2 Ubuntu administration from Linux side. Profile-aware - reads preferences from Windows-side profile at /mnt/c/Users/{WIN_USER}/.admin/profiles/{hostname}.json Use when: Inside WSL for apt packages, Docker, Python/uv, shell configs, systemd. Coordinates with admin-windows via shared profile ON THE WINDOWS SIDE.
admin-windows
Windows system administration with PowerShell 7.x. Profile-aware - reads your preferences for package managers (scoop vs winget), paths, and installed tools. Use when: Windows-specific admin tasks, PowerShell automation, PATH configuration, package installation, bash-to-PowerShell translation.
admin-unix
Native macOS and Linux administration (non-WSL). Profile-aware - reads preferences from ~/.admin/profiles/{hostname}.json. Use when: macOS/Linux system admin, Homebrew (macOS), apt (Linux), services. NOT for WSL - use admin-wsl instead.
admin-panel-builder
Expert assistant for creating and maintaining admin panel pages in the KR92 Bible Voice project. Use when creating admin pages, building admin components, integrating with admin navigation, or adding admin features.
admin-mcp
MCP server management for Claude Desktop. Profile-aware - reads MCP server inventory from profile.mcp.servers{} and config path from profile.paths.claudeConfig. Use when: installing MCP servers, configuring Claude Desktop, troubleshooting MCP issues.
admin-interface-rules
Rules for the Admin interface functionalities
admin-infra-vultr
Deploys infrastructure on Vultr with Cloud Compute instances, High-Frequency servers, and VPCs. Excellent value with Kubernetes autoscaling support and global data centers. Use when: setting up Vultr infrastructure, deploying cloud compute or high-frequency instances, configuring firewalls, needing good price/performance with global reach. Keywords: vultr, vultr-cli, VPS, cloud compute, high-frequency, firewall, VPC, kubernetes autoscale, infrastructure
admin-infra-oci
Deploys infrastructure on Oracle Cloud Infrastructure (OCI) with ARM64 instances (Always Free tier eligible). Handles compartments, VCNs, subnets, security lists, and compute instances. Use when: setting up Oracle Cloud infrastructure, deploying ARM64 instances, troubleshooting OUT_OF_HOST_CAPACITY errors, optimizing for Always Free tier. Keywords: oracle cloud, OCI, ARM64, VM.Standard.A1.Flex, Always Free tier, OUT_OF_HOST_CAPACITY, oci compartment, oci vcn
admin-infra-linode
Deploys infrastructure on Linode (Akamai Cloud) with Linodes, Firewalls, and VLANs. Strong Kubernetes support with Cluster Autoscaler and Akamai edge network integration. Use when: setting up Linode/Akamai infrastructure, deploying Linodes, configuring firewalls, needing Kubernetes autoscaling, wanting Akamai CDN integration. Keywords: linode, akamai, linode-cli, VPS, dedicated CPU, firewall, VLAN, kubernetes autoscale, infrastructure