Fullstack Guardian logo

Fullstack Guardian

CommunityPopular
Jeffallan
fullstack-guardian

Builds security-focused full-stack web applications by implementing integrated frontend and backend components with layered security at every level. Covers the complete stack from database to UI, enforcing auth, input validation, output encoding, and parameterized queries across all layers. Use when implementing features across frontend and backend, building REST APIs with corresponding UI, connecting frontend components to backend endpoints, creating end-to-end data flows from database to UI, or implementing CRUD operations with UI forms. Distinct from frontend-only, backend-only, or API-only skills in that it simultaneously addresses all three perspectives—Frontend, Backend, and Security—within a single implementation workflow. Invoke for full-stack feature work, web app development, authenticated API routes with views, microservices, real-time features, monorepo architecture, or technology selection decisions.

Overview

PublisherJeffallan
Repositoryclaude-skills
Skill namefullstack-guardian
Stars
11.5K
Forks
1.1K
Bundled files
10
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 10 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Jeffallan on GitHub. Read the source before you install it.

Installation

Install the Fullstack Guardian AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Jeffallan/claude-skills.git /tmp/claude-skills
mkdir -p .claude/skills
cp -r /tmp/claude-skills/skills/fullstack-guardian .claude/skills/fullstack-guardian
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fullstack Guardian in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Fullstack Guardian on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Fullstack Guardian is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Fullstack Guardian

Security-focused full-stack developer implementing features across the entire application stack.

Core Workflow

  1. Gather requirements - Understand feature scope and acceptance criteria
  2. Design solution - Consider all three perspectives (Frontend/Backend/Security)
  3. Write technical design - Document approach in specs/{feature}_design.md
  4. Security checkpoint - Run through references/security-checklist.md before writing any code; confirm auth, authz, validation, and output encoding are addressed
  5. Implement - Build incrementally, testing each component as you go
  6. Hand off - Pass to Test Master for QA, DevOps for deployment

Reference Guide

Load detailed guidance based on context:

TopicReferenceLoad When
Design Templatereferences/design-template.mdStarting feature, three-perspective design
Security Checklistreferences/security-checklist.mdEvery feature - auth, authz, validation
Error Handlingreferences/error-handling.mdImplementing error flows
Common Patternsreferences/common-patterns.mdCRUD, forms, API flows
Backend Patternsreferences/backend-patterns.mdMicroservices, queues, observability, Docker
Frontend Patternsreferences/frontend-patterns.mdReal-time, optimization, accessibility, testing
Integration Patternsreferences/integration-patterns.mdType sharing, deployment, architecture decisions
API Designreferences/api-design-standards.mdREST/GraphQL APIs, versioning, CORS, validation
Architecture Decisionsreferences/architecture-decisions.mdTech selection, monolith vs microservices
Deliverables Checklistreferences/deliverables-checklist.mdCompleting features, preparing handoff

Constraints

MUST DO

  • Address all three perspectives (Frontend, Backend, Security)
  • Validate input on both client and server
  • Use parameterized queries (prevent SQL injection)
  • Sanitize output (prevent XSS)
  • Implement proper error handling at every layer
  • Log security-relevant events
  • Write the implementation plan before coding
  • Test each component as you build

MUST NOT DO

  • Skip security considerations
  • Trust client-side validation alone
  • Expose sensitive data in API responses
  • Hardcode credentials or secrets
  • Implement features without acceptance criteria
  • Skip error handling for "happy path only"

Three-Perspective Example

A minimal authenticated endpoint illustrating all three layers:

[Backend] — Authenticated route with parameterized query and scoped response:

python
@router.get("/users/{user_id}/profile", dependencies=[Depends(require_auth)])
async def get_profile(user_id: int, current_user: User = Depends(get_current_user)):
    if current_user.id != user_id:
        raise HTTPException(status_code=403, detail="Forbidden")
    # Parameterized query — no raw string interpolation
    row = await db.fetchone("SELECT id, name, email FROM users WHERE id = ?", (user_id,))
    if not row:
        raise HTTPException(status_code=404, detail="Not found")
    return ProfileResponse(**row)   # explicit schema — no password/token leakage

[Frontend] — Component calls the endpoint and handles errors gracefully:

typescript
async function fetchProfile(userId: number): Promise<Profile> {
  const res = await apiFetch(`/users/${userId}/profile`);   // apiFetch attaches auth header
  if (!res.ok) throw new Error(await res.text());
  return res.json();
}
// Client-side input guard (never the only guard)
if (!Number.isInteger(userId) || userId <= 0) throw new Error("Invalid user ID");

[Security]

  • Auth enforced server-side via require_auth dependency; client header is a convenience, not the gate.
  • Response schema (ProfileResponse) explicitly excludes sensitive fields.
  • 403 returned before any DB access when IDs don't match — no timing leak via 404.

Output Templates

When implementing features, provide:

  1. Technical design document (if non-trivial)
  2. Backend code (models, schemas, endpoints)
  3. Frontend code (components, hooks, API calls)
  4. Brief security notes

Documentation

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Fullstack Guardian AI skill do?

Builds security-focused full-stack web applications by implementing integrated frontend and backend components with layered security at every level. Covers the complete stack from database to UI, enforcing auth, input validation, output encoding, and parameterized queries across all layers. Use when implementing features across frontend and backend, building REST APIs with corresponding UI, connecting frontend components to backend endpoints, creating end-to-end data flows from database to UI, or implementing CRUD operations with UI forms. Distinct from frontend-only, backend-only, or API-o...

Why use Fullstack Guardian on TypingMind?

Because you install it once and use it with any model. Fullstack Guardian is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Fullstack Guardian in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Jeffallan/claude-skills/tree/main/skills/fullstack-guardian. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Fullstack Guardian?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Fullstack Guardian?

As many as you like. As long as a model supports skills, you can use Fullstack Guardian with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Fullstack Guardian AI skill free?

Yes. It is published on GitHub by Jeffallan under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇