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, refactor for maintainability.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add DeevsDeevs/agent-system --skill dev-experts --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Dev Experts?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/deevsdeevs-dev-experts)More formats (shields.io, HTML) on the badges page.
---
name: dev-experts
description: "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, refactor for maintainability."
---
# 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.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!