Ai Coding Workflow
Modern AI-assisted development workflow
Install
$ agentstack add skill-ssrjkk-claude-skills-ai-coding-workflow ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-ssrjkk-claude-skills-ai-coding-workflow) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
AI Coding Workflow
> A systematic approach to modern AI-assisted software development from spec to deployment.
Quick Start
# 1. Specification
cat > spec.md << 'EOF'
## Feature: User Authentication
- Email/password login with JWT
- OAuth (Google, GitHub)
- Session management with refresh tokens
- Rate limiting on login attempts
EOF
# 2. Architecture review with AI
claude -p "Review this spec for completeness. Identify missing edge cases and security considerations." < spec.md
# 3. Implementation with AI pair programming
claude -p "Implement the authentication system per spec.md. Use FastAPI, SQLAlchemy, and python-jose. Include comprehensive error handling."
# 4. Test generation
claude -p "Write pytest tests for the auth module. Cover: happy path, invalid credentials, token expiry, rate limiting, OAuth flow."
# 5. Code review
claude -p "Review the auth module for security vulnerabilities, specifically: SQL injection, JWT secret handling, timing attacks on comparison."Key Concepts
The modern AI workflow: Spec → Architecture Review → Implementation → Test Generation → Code Review → Deployment. Each phase uses AI differently—from creative generation to critical analysis.
When to Use
- Starting new projects with AI from the ground up
- Adding complex features to existing codebases
- Implementing security-critical code that needs thorough review
Validation
- Each phase produces artifacts (spec, tests, code) that build on previous phases
- AI-generated code passes existing test suite
- Security review identifies no critical vulnerabilities
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ssrjkk
- Source: ssrjkk/claude-skills
- License: MIT
- Homepage: https://claude.ai
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.