source-driven-development

OWNER/REPO · updated May 18, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/addyosmani/agent-skills --skill source-driven-development
0 commentsdiscussion
summary

Grounds every implementation decision in official documentation for authoritative, source-cited code.

skill.md
name
source-driven-development
description
Grounds every implementation decision in official documentation. Use when you want authoritative, source-cited code free from outdated patterns. Use when building with any framework or library where correctness matters.

Source-Driven Development

Overview

Every framework-specific code decision must be backed by official documentation. Don't implement from memory — verify, cite, and let the user see your sources. Training data goes stale, APIs get deprecated, best practices evolve. This skill ensures the user gets code they can trust because every pattern traces back to an authoritative source they can check.

When to Use

  • The user wants code that follows current best practices for a given framework
  • Building boilerplate, starter code, or patterns that will be copied across a project
  • The user explicitly asks for documented, verified, or "correct" implementation
  • Implementing features where the framework's recommended approach matters (forms, routing, data fetching, state management, auth)
  • Reviewing or improving code that uses framework-specific patterns
  • Any time you are about to write framework-specific code from memory

When NOT to use:

  • Correctness does not depend on a specific version (renaming variables, fixing typos, moving files)
  • Pure logic that works the same across all versions (loops, conditionals, data structures)
  • The user explicitly wants speed over verification ("just do it quickly")

The Process

DETECT ──→ FETCH ──→ IMPLEMENT ──→ CITE
  │          │           │            │
  ▼          ▼           ▼            ▼
 What       Get the    Follow the   Show your
 stack?     relevant   documented   sources
            docs       patterns

Step 1: Detect Stack and Versions

Read the project's dependency file to identify exact versions:

package.json    → Node/React/Vue/Angular/Svelte
composer.json   → PHP/Symfony/Laravel
requirements.txt / pyproject.toml → Python/Django/Flask
go.mod          → Go
Cargo.toml      → Rust
Gemfile         → Ruby/Rails

State what you found explicitly:

STACK DETECTED:
- React 19.1.0 (from package.json)
- Vite 6.2.0
- Tailwind CSS 4.0.3
→ Fetching official docs for the relevant patterns.

If versions are missing or ambiguous, ask the user. Don't guess — the version determines which patterns are correct.

Step 2: Fetch Official Documentation

Fetch the specific documentation page for the feature you're implementing. Not the homepage, not the full docs — the relevant page.

Source hierarchy (in order of authority):

PrioritySourceExample
1Official documentationreact.dev, docs.djangoproject.com, symfony.com/doc
2Official blog / changelogreact.dev/blog, nextjs.org/blog
3Web standards referencesMDN, web.dev, html.spec.whatwg.org
4Browser/runtime compatibilitycaniuse.com, node.green

Not authoritative — never cite as primary sources:

  • Stack Overflow answers
  • Blog posts or tutorials (even popular ones)
  • AI-generated documentation or summaries
  • Your own training data (that is the whole point — verify it)

Be precise with what you fetch:

BAD:  Fetch the React homepage
GOOD: Fetch react.dev/reference/react/useActionState

BAD:  Search "django authentication best practices"
GOOD: Fetch docs.djangoproject.com/en/6.0/topics/auth/

After fetching, extract the key patterns and note any deprecation warnings or migration guidance.

When official sources conflict with each other (e.g. a migration guide contradicts the API reference), surface the discrepancy to the user and verify which pattern actually works against the detected version.

Step 3: Implement Following Documented Patterns

Write code that matches what the documentation shows:

  • Use the API signatures from the docs, not from memory
  • If the docs show a new way to do something, use the new way
  • If the docs deprecate a pattern, don't use the deprecated version
  • If the docs don't cover something, flag it as unverified

When docs conflict with existing project code:

CONFLICT DETECTED:
The existing codebase uses useState for form loading state,
but React 19 docs recommend useActionState for this pattern.
(Source: react.dev/reference/react/useActionState)

Options:
A) Use the modern pattern (useActionState) — consistent with current docs
B) Match existing code (useState) — consistent with codebase
→ Which approach do you prefer?

Surface the conflict. Don't silently pick one.

Step 4: Cite Your Sources

Every framework-specific pattern gets a citation. The user must be able to verify every decision.

In code comments:

// React 19 form handling with useActionState
// Source: https://react.dev/reference/react/useActionState#usage
const [state, formAction, isPending] = useActionState(submitOrder, initialState);

In conversation:

I'm using useActionState instead of manual useState for the
form submission state. React 19 replaced the manual
isPending/setIsPending pattern with this hook.

Source: https://react.dev/blog/2024/12/05/react-19#actions
"useTransition now supports async functions [...] to handle
pending states automatically"

Citation rules:

  • Full URLs, not shortened
  • Prefer deep links with anchors where possible (e.g. /useActionState#usage over /useActionState) — anchors survive doc restructuring better than top-level pages
  • Quote the relevant passage when it supports a non-obvious decision
  • Include browser/runtime support data when recommending platform features
  • If you cannot find documentation for a pattern, say so explicitly:
UNVERIFIED: I could not find official documentation for this
pattern. This is based on training data and may be outdated.
Verify before using in production.

Honesty about what you couldn't verify is more valuable than false confidence.

Common Rationalizations

RationalizationReality
"I'm confident about this API"Confidence is not evidence. Training data contains outdated patterns that look correct but break against current versions. Verify.
"Fetching docs wastes tokens"Hallucinating an API wastes more. The user debugs for an hour, then discovers the function signature changed. One fetch prevents hours of rework.
"The docs won't have what I need"If the docs don't cover it, that's valuable information — the pattern may not be officially recommended.
"I'll just mention it might be outdated"A disclaimer doesn't help. Either verify and cite, or clearly flag it as unverified. Hedging is the worst option.
"This is a simple task, no need to check"Simple tasks with wrong patterns become templates. The user copies your deprecated form handler into ten components before discovering the modern approach exists.

Red Flags

  • Writing framework-specific code without checking the docs for that version
  • Using "I believe" or "I think" about an API instead of citing the source
  • Implementing a pattern without knowing which version it applies to
  • Citing Stack Overflow or blog posts instead of official documentation
  • Using deprecated APIs because they appear in training data
  • Not reading package.json / dependency files before implementing
  • Delivering code without source citations for framework-specific decisions
  • Fetching an entire docs site when only one page is relevant

Verification

After implementing with source-driven development:

  • Framework and library versions were identified from the dependency file
  • Official documentation was fetched for framework-specific patterns
  • All sources are official documentation, not blog posts or training data
  • Code follows the patterns shown in the current version's documentation
  • Non-trivial decisions include source citations with full URLs
  • No deprecated APIs are used (checked against migration guides)
  • Conflicts between docs and existing code were surfaced to the user
  • Anything that could not be verified is explicitly flagged as unverified
how to use source-driven-development

How to use source-driven-development on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your development machine
  • Node.js version 16.0+ with npm package manager (verify with node --version)
  • Active project directory or workspace where you want to add source-driven-development
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/addyosmani/agent-skills --skill source-driven-development

The skills CLI fetches source-driven-development from GitHub repository OWNER/REPO and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/source-driven-development

Reload or restart Cursor to activate source-driven-development. Access the skill through slash commands (e.g., /source-driven-development) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

Accelerate Code Development

Use skill to generate boilerplate code, refactor legacy code, and write tests faster

Example

Generate React component with TypeScript types, styled-components, and comprehensive test suite in minutes

Reduce development time by 40-60% for repetitive coding tasks

Code Review Automation

Systematically review code for bugs, security issues, and style violations

Example

Analyze pull requests for common anti-patterns, suggest performance improvements, flag security vulnerabilities

Catch 70%+ of code issues before human review, improve code quality

Debug Complex Issues

Trace errors through stack traces and identify root causes faster

Example

Analyze error logs, suggest probable causes, recommend fixes with code examples

Cut debugging time by 30-50%, especially for unfamiliar codebases

Learn New Technologies

Get explanations, examples, and best practices for unfamiliar frameworks

Example

Understand Next.js app router, learn Rust ownership, grasp Kubernetes concepts with practical examples

Accelerate learning curve by 2-3x, reduce onboarding time for new tech stacks

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client with skill installation support
  • Basic understanding of programming concepts and version control (Git)
  • Code editor or IDE for testing generated code (VS Code, JetBrains, etc.)
  • Test environment separate from production for validating skill outputs

Time Estimate

15-30 minutes to install and see first useful output

Installation Steps

  1. 1.Install the skill using provided installation command
  2. 2.Verify skill is loaded in Claude Desktop (check ~/.claude/skills directory)
  3. 3.Test skill with simple prompt: 'Help me review this code snippet'
  4. 4.Gradually increase complexity: code generation → refactoring → architecture advice
  5. 5.Review all generated code before committing to repository
  6. 6.Iterate on prompts to improve output quality and relevance
  7. 7.Share effective prompts with team for consistency

Common Pitfalls

  • Blindly trusting generated code without testing—always run tests and manual review
  • Not providing enough context about your project structure and coding standards
  • Expecting perfection on first generation—iteration and refinement are normal
  • Sharing proprietary code or API keys in prompts—maintain confidentiality
  • Over-relying on skill for critical security or business logic code
  • Skipping documentation of why AI-generated code was chosen over alternatives

Best Practices

✓ Do

  • +Always review and test AI-generated code before merging
  • +Provide clear context: language, framework, coding standards, constraints
  • +Use for boilerplate, tests, docs—areas where mistakes are easily caught
  • +Iterate on prompts: start broad, refine with specific requirements
  • +Combine AI suggestions with human judgment and domain expertise
  • +Document successful prompt patterns for team reuse
  • +Keep version control so you can rollback if needed
  • +Use skill for learning and exploration, not production-critical features initially

✗ Don't

  • Don't commit AI code without thorough testing and review
  • Don't expose sensitive code, credentials, or proprietary algorithms
  • Don't use for security-critical code (auth, crypto, payments) without expert review
  • Don't skip peer review process just because AI generated it
  • Don't assume code follows your team's conventions—verify
  • Don't let junior developers skip learning fundamentals by relying solely on AI
  • Don't ignore compiler warnings or test failures in generated code

💡 Pro Tips

  • Describe desired patterns explicitly: 'Use async/await, avoid callbacks'
  • Ask for alternatives: 'Show 3 approaches to solve this, with tradeoffs'
  • Request explanations: 'Explain why this approach is better than X'
  • Use skill for 70% generation + 30% manual refinement for best results
  • Build a prompt library for common patterns (API endpoints, components, tests)
  • Pair program with AI: describe problem → review solution → iterate → refine

When to Use This

✓ Use When

Use coding skills for boilerplate generation, code reviews, refactoring legacy code, writing tests, learning new frameworks, and debugging non-critical issues. Best for repetitive tasks where errors are easy to catch.

✗ Avoid When

Avoid for production security features (auth, encryption, payment processing), complex business logic requiring deep domain knowledge, performance-critical algorithms, or when learning fundamentals is more valuable than speed.

Learning Path

  1. 1Start with simple tasks: generate functions, write tests, explain code
  2. 2Progress to code review: analyze PRs, suggest improvements
  3. 3Advanced: architectural decisions, refactoring strategies, performance optimization
  4. 4Expert: use for exploring new paradigms, researching best practices, mentoring juniors

Integration

  • VS Code
  • JetBrains IDEs
  • Cursor
  • GitHub Copilot
  • Git workflows

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.527 reviews
  • Omar Jackson· Dec 20, 2024

    Keeps context tight: source-driven-development is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Chaitanya Patil· Dec 8, 2024

    Solid pick for teams standardizing on skills: source-driven-development is focused, and the summary matches what you get after install.

  • William Park· Dec 4, 2024

    I recommend source-driven-development for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Piyush G· Nov 27, 2024

    We added source-driven-development from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • Shikha Mishra· Oct 18, 2024

    source-driven-development fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Nikhil Thompson· Oct 2, 2024

    source-driven-development reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Ama Abbas· Sep 21, 2024

    source-driven-development has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Ava Jackson· Sep 9, 2024

    Keeps context tight: source-driven-development is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Ava Wang· Aug 28, 2024

    source-driven-development is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Ama Ramirez· Aug 12, 2024

    Solid pick for teams standardizing on skills: source-driven-development is focused, and the summary matches what you get after install.

showing 1-10 of 27

1 / 3