From ai-maestro-programmer-agent
Setup project configuration and tooling. Use when starting work on new project. Trigger with /ampa-project-setup or when initializing a new project. Loaded by ai-maestro-programmer-agent-main-agent.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-maestro-programmer-agent:ampa-project-setupai-maestro-programmer-agent-main-agentThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Project environment setup for AMPA (see agent definition for role context and
Project environment setup for AMPA (see agent definition for role context and supported languages table). Covers language detection, package manager initialization, dependency installation, linting, testing, and SERENA MCP activation.
Use when starting work on a new project or onboarding to a project that lacks tooling. For per-task environment verification, see Step 3 of ampa-task-execution.
Copy this checklist and track your progress:
find_symbol.If any setup step fails, do not proceed to the next step. Report the failure to AMOA with the step name, error output, and the log file path. Wait for guidance before retrying.
| Document | Description |
|---|---|
| op-detect-project-language.md | When to Use, Prerequisites, Procedure, Examples, Error Handling |
| op-initialize-package-manager.md | When to Use, Prerequisites, Procedure, Examples, Error Handling |
| op-install-dependencies.md | When to Use, Prerequisites, Procedure, Examples, Error Handling |
| op-configure-linting.md | When to Use, Prerequisites, Procedure, Examples, Error Handling |
| ruff-configuration-patterns.md | When to Configure Ruff for a New Project, Standard ruff.toml Template for AI Maestro Programmer Projects, What Each Rule Set Does, What Each Ignored Rule Means, Per-File Ignore Patterns, Formatter Settings, How to Run Ruff, Customizing Ruff for Specific Project Types |
| op-setup-testing-framework.md | When to Use, Prerequisites, Procedure, Examples, Error Handling |
| op-activate-serena-mcp.md | When to Use, Prerequisites, Procedure, Examples, Error Handling |
This skill operates under the AI Maestro approval tiers — the escalation
ladder Tier 0 (self-authority for in-scope work + DERIVED NPT/EHT tasks) →
CHIEF-OF-STAFF → MANAGER → USER. See the ampa-prrd-trdd-kanban skill and
~/.claude/rules/trdd-approval-tiers.md for which transitions need approval.
A MEMBER never self-approves its own releases — entering the release
pipeline (publish/deploy) is USER/MANAGER-authorized, and the INTEGRATOR
(not the MEMBER) owns the → complete flip.
Whole-repo audit for over-engineering: finds dead code, unnecessary abstractions, stdlib-replaceable dependencies. Outputs ranked findings and net line/dep savings.
npx claudepluginhub emasoft/ai-maestro-programmer-agent