source-driven-development

Implements framework code verified against official documentation with cited sources.

Updated Aug 11, 2026
One-click install
npx skills add https://github.com/Kunj-Sharma03/agent-contextify --skill source-driven-development-kunj-sharma03
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: source-driven-development
Source: https://github.com/Kunj-Sharma03/agent-contextify/tree/main/templates/skills/source-driven-development
Command: npx skills add https://github.com/Kunj-Sharma03/agent-contextify --skill source-driven-development-kunj-sharma03

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 AI-generated framework code often relies on stale training data, producing deprecated APIs and outdated patterns that break against current library versions.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 grounds every framework-specific implementation decision in fetched official documentation, with citations the user can verify. ## 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 code. - Documentation-Grounded Implementation: Fetches the specific official docs page for each feature, follows documented API signatures, and avoids deprecated patterns. - Source Citation & Conflict Surfacing: Adds full-URL citations in code comments and conversation, and explicitly flags conflicts between docs and existing code or patterns that could not be verified. - Use Case: When building a React 19 form, the Skill detects the version from package.json, fetches react.dev docs for useActionState, implements the modern pattern, and cites the source instead of emitting a stale useState-based handler. ## Quick Start Use source-driven development to implement a form submission flow for my React project, verifying every pattern against the official docs and citing your sources.

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 dependency files like package.json, fetch the relevant official docs page for each feature, and implement only documented API signatures. Every framework-specific decision gets a full-URL citation so you can verify it.

How to avoid deprecated APIs when generating code with AI?

Check the official documentation and migration guides for your detected version before implementing. If the docs deprecate a pattern, use the replacement; if a pattern cannot be verified in official sources, flag it explicitly as unverified instead of shipping it.

Which sources are authoritative for framework code decisions?

Official documentation sites rank first, followed by official blogs and changelogs, then web standards references like MDN, then compatibility data like caniuse.com. Stack Overflow answers, blog tutorials, and AI training data are never treated as primary sources.

What happens when official docs conflict with existing project code?

The conflict is surfaced to the user with both options explained: adopt the modern documented pattern or stay consistent with the existing codebase. The Skill never silently picks one side of a docs-versus-codebase conflict.

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 unnecessary when the user explicitly prioritizes speed over verification.