dev-workflow

Enforce tiered approval-gated development with RFCs, smoke tests, and multi-agent review.

1|Updated May 16, 2026
One-click install
npx skills add https://github.com/enigmaicon-eng/AI-Enterprise-OS --skill dev-workflow-enigmaicon-eng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dev-workflow
Source: https://github.com/enigmaicon-eng/AI-Enterprise-OS/tree/main/examples/claude-dev-workflow
Command: npx skills add https://github.com/enigmaicon-eng/AI-Enterprise-OS --skill dev-workflow-enigmaicon-eng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents risky or inconsistent coding changes by forcing every development task into a clear XS/M/L tier with required RFC gating, an explicit “image of result” approval step, mandatory smoke tests, and multi-agent review (including security review for bigger or auth/data-impacting work).

Core Features & Use Cases

  • Tiered development workflow (XS / M / L) that defines ceremony level per task size and risk, including “choose higher if unsure.”
  • User-level “image of result” approval before code (Step 0.5) to align UX outcomes with the user before implementation details.
  • RFC gating for M/L using PROJECT/rfc/NNN-title.md to lock the plan (problem → options → chosen → risks → verification) before any coding begins.
  • Mandatory smoke test even for XS plus test guidance (unit vs integration vs E2E) to catch refactor breakage quickly.
  • Multi-agent review pipeline where M tier uses a code-review subagent and L tier additionally requires /security-review and /review, culminating in a final user approval for M/L.
  • Incremental security levels (S1 → S2 → S3) with different security/scanning/threat-model expectations as the project matures.
  • Blameless incident logging and Definition of Done (DOD) via PROJECT/incidents.md and a pre-report checklist to keep changes consistent and auditable.

Quick Start

Tell the AI: “Dev workflow—classify this coding task as XS/M/L, draft the RFC and image of result if required, then wait for my approval before writing code.”

Frequently Asked Questions about dev-workflow

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enforce a tiered code review workflow for small and large coding tasks?

A tiered code review workflow classifies coding tasks as XS, M, or L to apply the correct ceremony level, requiring RFC gating for M/L tasks and multi-agent reviews before merging. This prevents risky or inconsistent code changes by scaling process overhead to task size.

What's the best way to require RFC approval before writing code for major changes?

Requiring RFC approval before coding involves locking the implementation plan in a markdown file detailing the problem, options, chosen approach, risks, and verification steps. This gating mechanism ensures all major and large tasks are peer-reviewed and explicitly approved before development begins.

Can I use this development workflow for Notion or Jira product management content?

This development workflow explicitly excludes product and project management content like Notion, Jira, or Confluence text and hypotheses. It strictly applies to coding tasks across scripts, applications, MCP servers, and SaaS work to enforce technical quality and security controls.

How do smoke tests fit into an XS tier development process?

Smoke tests are mandatory even for XS tier tasks to catch refactor breakage quickly, alongside guided test selection for unit, integration, or E2E coverage. This ensures every code change, regardless of size, passes basic functional validation before undergoing final review.

When should I run a security review for code changes handling authentication?

A security review is required for L tier tasks and any code changes impacting authentication or data-handling logic. This multi-agent review process applies incremental security levels S1 through S3, scaling scanning and threat-model expectations as the project matures.

How to log blameless incidents and track Definition of Done for code releases?

Logging blameless incidents and tracking Definition of Done requires appending post-mortem entries to an incident log file and completing a pre-report checklist. This keeps changes consistent, auditable, and focused on process improvement rather than individual fault.