# Dev Experts

> Apply opinionated developer personas for architecture decisions, production debugging, language-specific code review, comprehensive reviewer passes, and test strategy. Use when you need an architect plan, devops investigation, Rust/Python/C++ review, grumpy reviewer audit, or tester-driven test plan. Triggers: architect, devops, rust-dev, python-dev, cpp-dev, reviewer, tester, pre-merge review, r…

- **Type:** Skill
- **Install:** `agentstack add skill-deevsdeevs-agent-system-dev-experts`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [DeevsDeevs](https://agentstack.voostack.com/s/deevsdeevs)
- **Installs:** 0
- **Category:** [Cloud & Infrastructure](https://agentstack.voostack.com/c/cloud-infrastructure)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [DeevsDeevs](https://github.com/DeevsDeevs)
- **Source:** https://github.com/DeevsDeevs/agent-system/tree/main/dev-experts

## Install

```sh
agentstack add skill-deevsdeevs-agent-system-dev-experts
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Dev Experts

Use a single skill with persona selection. If the user specifies a persona name, use that persona. If not specified, ask which persona to use and suggest one based on the task.

## Persona Map

- `architect` → `agents/architect.md`
- `devops` → `agents/devops.md`
- `rust-dev` → `agents/rust-dev.md`
- `python-dev` → `agents/python-dev.md`
- `cpp-dev` → `agents/cpp-dev.md`
- `reviewer` → `agents/reviewer.md`
- `tester` → `agents/tester.md`

## Workflow

1. Read `README.md` for the global flow and constraints.
2. Read the selected persona file and follow its workflow verbatim.
3. Spawn a child agent with `agent_type` equal to the selected persona (`architect`, `devops`, `rust-dev`, `python-dev`, `cpp-dev`, `reviewer`, `tester`).
4. Pass clear task context in the spawn message, then use `wait` for completion.
5. If needed, send targeted follow-ups with `send_input`, then `wait` again.
6. Synthesize the child agent output for the user and include concrete file references.
7. If the user asks for "refactor for maintainability", follow the persona's refactoring mode and create the plan file as described.
8. If the task is ambiguous across personas, ask a single clarifying question and proceed.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [DeevsDeevs](https://github.com/DeevsDeevs)
- **Source:** [DeevsDeevs/agent-system](https://github.com/DeevsDeevs/agent-system)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-deevsdeevs-agent-system-dev-experts
- Seller: https://agentstack.voostack.com/s/deevsdeevs
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.