uat-mode
Detect requests for UAT generation, execution, or reporting and invoke the appropriate UAT command
Best use case
uat-mode is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
It is a strong fit for teams already working in Codex.
Detect requests for UAT generation, execution, or reporting and invoke the appropriate UAT command
Teams using uat-mode 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/uat-mode/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How uat-mode Compares
| Feature / Agent | uat-mode | Standard Approach |
|---|---|---|
| Platform Support | Codex | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Detect requests for UAT generation, execution, or reporting and invoke the appropriate UAT command
Which AI agents support this skill?
This skill is designed for Codex.
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
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# UAT Mode
Detects requests related to User Acceptance Testing of MCP tool surfaces and routes to the appropriate UAT command.
## Triggers
Primary phrases matched automatically from skill description. No additional alternate expressions defined.
## Detection Logic
### High Confidence (Auto-Suggest)
Trigger contains explicit UAT terminology or MCP testing intent:
- Contains "UAT" in any case
- Contains "acceptance test" + "MCP" or "tool" or "server"
- Contains "test" + "MCP tools" or "MCP connections"
### Medium Confidence (Suggest with Alternatives)
Trigger is about testing tools but not explicitly UAT:
- "validate the tools"
- "check MCP coverage"
- "test the server"
### Low Confidence (Don't Suggest)
Too generic to confidently route:
- "run tests" (could be unit tests)
- "check coverage" (could be code coverage)
- "test this" (too vague)
## Behavior
### When No UAT Plan Exists
1. Inform user no plan exists
2. Offer to generate one: "I'll generate a UAT plan first. Run `/uat-generate`?"
3. If user agrees, invoke `/uat-generate`
4. After generation, offer to execute: "Plan ready. Execute it?"
### When UAT Plan Exists But No Results
1. Show existing plan summary (phases, test count)
2. Offer to execute: "Found existing plan. Execute it?"
3. If user agrees, invoke `/uat-execute`
### When Results Exist
1. Show latest results summary (pass/fail counts)
2. Offer options:
- View full report: `/uat-report`
- Re-run tests: `/uat-execute`
- Generate new plan: `/uat-generate`
### Full Pipeline Request
When user says "acceptance test this server" or similar:
1. Generate plan: `/uat-generate`
2. Human reviews plan
3. Execute plan: `/uat-execute`
4. Generate report: `/uat-report`
## Response Templates
### Plan Generated
```
UAT plan generated with {N} tests across {M} phases.
Review the plan at: {path}
Ready to execute? Use `/uat-execute {path}` or just say "run the UAT".
```
### Execution Complete
```
UAT execution complete:
Passed: {pass}/{total} ({percentage}%)
Failed: {fail}
Issues filed: {count}
View full report with `/uat-report` or say "show UAT results".
```
### No MCP Servers
```
No MCP servers detected. UAT-MCP requires at least one connected MCP server.
Check your MCP configuration and try again.
```
## Integration Notes
- **Priority**: High (when UAT keywords detected)
- **Exclusivity**: Full (takes over the interaction when triggered)
- **Fallback**: If UAT addon not installed, suggest `aiwg use uat-mcp`
## Related
- Commands: `/uat-generate`, `/uat-execute`, `/uat-report`
- Agents: `uat-planner`, `uat-executor`
- Issue: #380
## References
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/vague-discretion.md — Measurable UAT completion criteria
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/README.md — SDLC framework context for acceptance testing
- @$AIWG_ROOT/docs/cli-reference.md — CLI reference for uat commands
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/native-ux-tools.md — Interactive question patterns for UAT flowRelated Skills
dev-mode-init
Switch AIWG CLI to dev mode (local repo source), rebuild, deploy dev tools, and run a health check — all via the Steward agent
rlm-mode
Detect requests for recursive decomposition and large-scale operations that benefit from RLM processing
execution-mode
Set or report the reproducibility mode governing how AIWG workflows execute, from standard to fully auditable
aiwg-orchestrate
Route structured artifact work to AIWG workflows via MCP with zero parent context cost
venv-manager
Create, manage, and validate Python virtual environments. Use for project isolation and dependency management.
pytest-runner
Execute Python tests with pytest, supporting fixtures, markers, coverage, and parallel execution. Use for Python test automation.
vitest-runner
Execute JavaScript/TypeScript tests with Vitest, supporting coverage, watch mode, and parallel execution. Use for JS/TS test automation.
eslint-checker
Run ESLint for JavaScript/TypeScript code quality and style enforcement. Use for static analysis and auto-fixing.
repo-analyzer
Analyze GitHub repositories for structure, documentation, dependencies, and contribution patterns. Use for codebase understanding and health assessment.
pr-reviewer
Review GitHub pull requests for code quality, security, and best practices. Use for automated PR feedback and approval workflows.
YouTube Acquisition
yt-dlp patterns for acquiring content from YouTube and video platforms
Quality Filtering
Accept/reject logic and quality scoring heuristics for media content