source-driven-development

Grounds framework-specific code decisions in official documentation with cited sources.

Updated May 21, 2026
One-click install
npx skills add https://github.com/nicorevo/AI-SDLC-Template --skill source-driven-development-nicorevo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: source-driven-development
Source: https://github.com/nicorevo/AI-SDLC-Template/tree/main/.opencode/skills/source-driven-development
Command: npx skills add https://github.com/nicorevo/AI-SDLC-Template --skill source-driven-development-nicorevo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated framework code often relies on stale training data, producing deprecated APIs and outdated patterns that break against current library versions. This Skill forces every framework-specific decision to be verified against official documentation and cited, so the code you receive is traceable to an authoritative source. ## Core Features & Use Cases - Stack Detection: Reads dependency files (package.json, composer.json, requirements.txt, go.mod, Cargo.toml, Gemfile) to identify exact framework versions before writing any code. - Documentation-First Implementation: Fetches the specific official docs page for the feature being built, following a strict source hierarchy (official docs, official blogs, MDN, caniuse) and rejecting Stack Overflow or blog posts as primary sources. - Citation and Conflict Surfacing: Adds full-URL source citations in code comments and conversation, and explicitly surfaces conflicts between current docs and existing codebase patterns for the user to decide. - Use Case: You ask for a form handler in a React 19 project. The Skill reads package.json, fetches react.dev/reference/react/useActionState, implements the modern Actions pattern instead of manual useState loading flags, and cites the exact doc anchor so you can verify it. ## Quick Start Ask the agent to implement a framework-specific feature using source-driven development so every pattern is verified against the official docs for your detected versions.

Frequently Asked Questions about source-driven-development

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

FAQPage Schema
How do I make AI-generated code follow current framework documentation?▼

Use source-driven development: detect exact versions from the dependency file, fetch the specific official docs page for the feature, implement the documented pattern, and cite the source URL. This replaces reliance on potentially stale training data.

What sources are authoritative for verifying framework code patterns?▼

Official documentation ranks first (react.dev, docs.djangoproject.com), followed by official blogs and changelogs, then web standards references like MDN, then compatibility data like caniuse. Stack Overflow, tutorials, and AI summaries are never valid primary sources.

Does this approach work with any programming language or framework?▼

Yes. It detects versions from package.json, composer.json, requirements.txt, pyproject.toml, go.mod, Cargo.toml, and Gemfile, covering JavaScript, PHP, Python, Go, Rust, and Ruby ecosystems. Any framework with official documentation is supported.

What happens when official docs conflict with existing project code?▼

The conflict is surfaced explicitly with both options presented: adopt the modern documented pattern or stay consistent with the existing codebase. The user decides; the agent never silently picks one side.

When should I not use documentation verification for coding tasks?▼

Skip it when correctness does not depend on a framework version, such as renaming variables, fixing typos, moving files, or writing pure logic like loops and data structures. It is also optional when the user explicitly prioritizes speed over verification.