Software and AI engineering
Chwezi Dev Engine: AI and Software Engineering Skills
A public engineering skills engine for routing AI applications, agents, RAG, architecture, APIs, databases, frontend, security, DevOps, SaaS, and delivery work.
Inspect on GitHub Chwezi Dev EngineRepository facts verified locally on 22 August 2026
Direct answer
Chwezi Dev Engine turns a broad software or AI request into a more accurate engineering route. Its catalogue covers AI applications, agents, RAG, gateways, evaluations, human oversight, architecture, APIs, databases, frontend, mobile, security, cloud, DevOps, SaaS, and SDLC work.
Who it serves
Software engineers, technical leads, architects, product teams, and organisations that want AI-assisted delivery with explicit boundaries and evidence.
175
Active skills reported by the repository
127
Routing fixtures reported
100%
Precision@3 reported
16 Aug 2026
Last repository verification
Non-negotiable operating rule
Human in the middle. Every time.
Nothing is considered finished merely because an AI tool or skills engine produced it. A responsible person reviews the facts, logic, sources, calculations, code, security, privacy, context, and quality of the output before it is published, deployed, submitted, or used to make a decision. For some actions, the engine must stop until the user explicitly types that they approve the action; approval must never be inferred from silence or a vague request.
Human responsibility: approve, correct, escalate, reject, stop, or roll back the work.
Engine responsibility: make the method, evidence, limits, review points, and approval pauses visible.
In practice
A second view of the work this engine supports
The visuals illustrate the domain; they do not replace evidence, controls, or the human review required before a consequential decision or action.
Capability map
What this engine covers
The list below is a plain-language summary of the repository's verified capability surface. It is not a promise that every project needs every skill.
- AI applications, agents, RAG, gateways, evaluations, human oversight, AI safety, and AI cost controls.
- Architecture, APIs, distributed systems, contracts, migrations, platform engineering, and SaaS boundaries.
- Frontend, mobile, databases, languages, security, DevOps, cloud, reliability, and deployment routes.
- Product discovery, delivery control, requirements, testing, operations, governance, and rollback thinking.
How to use it
A repeatable route from request to evidence
Frame the request
Separate the desired outcome, system boundary, users, data, constraints, and failure consequences.
Route by domain
Choose the narrowest accurate skill family and add specialist engines only when the work crosses domains.
Build with controls
Use the selected skill inputs, decision rules, security and evidence requirements, and explicit degraded behaviour.
Verify and hand over
Test normal and failure paths, capture evidence, document operations, and keep rollback and ownership visible.
Good fit
When to use this engine
- You need a safer route for an AI agent, RAG system, or AI-enabled SaaS feature.
- A software request crosses architecture, frontend, database, security, and deployment boundaries.
- A team wants repeatable engineering judgement available to Codex, Claude Code, or another agent runner.
- A delivery needs acceptance evidence, operational handoff, cost awareness, and recovery planning.
Boundaries
What it does not replace
- It does not create evidence merely by writing confidently; source claims and project facts still need verification.
- It does not remove accountable human review, specialist judgement, approval authority, or professional sign-off.
- It does not authorise live account changes, client communications, production changes, or submissions without explicit permission.
Continue the route
Related first-party guidance
SRS Skills
Use the formal SDLC documentation engine when the deliverable is a requirements, architecture, test, deployment, or governance artefact.
Website Skills
Use the website delivery engine for content, SEO, conversion, accessibility, performance, and launch operations.
Digital Research Skills
Route current or uncertain technical, market, policy, or standards claims through evidence-led research.
Frequently asked
Questions about Chwezi Dev Engine
What is Chwezi Dev Engine?
It is a public catalogue of reusable software-engineering skills for AI, applications, architecture, APIs, databases, frontend, mobile, security, cloud, DevOps, SaaS, and SDLC work.
Is Chwezi Dev Engine an autonomous coding agent?
No. It provides routing and execution guidance for an agent runner or engineering team. People still own scope, access, review, release, and production decisions.
Where can I inspect the source skills?
The public source repository is available on GitHub, linked from this page in a new tab.
Ready to discuss your project?
Every engagement begins with a conversation. Book a consultation to explore how Peter's experience can serve your organisation.