Agent Roles — Testing skill for Claude Code
Agent Roles — Discover / Design / Draft / Gate / Test / Review Split for mxcli Projects.
How to install Agent Roles
Installs to ~/.claude/skills/mendixmau-mxcli-project-toolkit-agent-roles/SKILL.md
mkdir -p ~/.claude/skills/mendixmau-mxcli-project-toolkit-agent-roles && curl -fsSL https://raw.githubusercontent.com/MendixMau/mxcli-project-toolkit/HEAD/skills/agent-roles.md -o ~/.claude/skills/mendixmau-mxcli-project-toolkit-agent-roles/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Agent Roles does
Agent Roles — Discover / Design / Draft / Gate / Test / Review Split for mxcli Projects
**Applies to:** any mxcli project. **Requires:** bash and Python 3 — this skill runs toolkit shell scripts. Run `bin/doctor.sh` once on a new machine; it names anything missing and how to get it. Windows: use Git Bash, and see the Prerequisites section of `conversion-runbook.md`. **Purpose:** How to generate a project's `.claude/agents/*.md` subagent definitions so discovery, architecture, MDL drafting, pos
Alternatives in Testing
- Agent Skills Spec — A skill is a folder of instructions, scripts, and resources that agents can discover and load dynamically to p 1.9k ★
- Spec Draft PR — Turn a feature idea or GitHub issue into a one-page spec saved to Documentation/specs/ and opened as a draft P 324 ★
- Al PR Prepare.Prompt — Prepare a clean, documented pull request draft for AL features or fixes with summary, testing notes, and check 109 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Book Write
Draft, review, and finalize one chapter — full pipeline with a pre-draft validity check, the seven-check QA ga
Happysquad Loop
Run the full happysquad loop (architect → implement → test → conflict-gate → review) on a task, iterating unti
Ab Test Setup
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation
Sdflow Skills
Spec-driven development workflow for Claude Code / Codex: clarify → grill → generate the four artifacts, multi
Phased Engineering Pipeline
Claude Code skill for building software with AI agents: seven roles, vertical-slice phases, deterministic chec
Squad Assemble
Analyze a spec/requirement and produce a recommended team composition (review mode, models, specialists, limit
Related Agents
Gate Agent
Runs {{PROJECT}}'s build/quality gates after a script has been executed against the .mpr, and reports pass/fai
Octopus Reviewer
Reviews code against this project's standards — the core/UI split, typing, process safety, test coverage, desi
Ab Multivariate Testing Subagent
Cross-cutting sub-agent owning A/B, split, and multivariate web-testing methodology — sample-size/power calcul