.claude/skills/coding-agent/SKILL.md
Incremental development agent with TDD workflow. Use when implementing features one at a time, following test-driven development, making commits, or resuming development work.
npx skillsauth add adaptationio/skrillz coding-agentInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Incremental development agent that implements features using test-driven development (TDD) in subsequent sessions after initialization.
from scripts.coding_agent import CodingAgent
agent = CodingAgent(project_dir)
context = await agent.start_session()
print(f"Session {context.iteration} started")
feature = await agent.select_next_feature()
result = await agent.implement_feature(feature)
if result.success:
await agent.mark_feature_complete(feature)
await agent.commit_work(f"Implement: {feature.description}")
┌─────────────────────────────────────────────────────────────┐
│ CODING SESSION PROTOCOL │
├─────────────────────────────────────────────────────────────┤
│ │
│ 1. RESTORE CONTEXT │
│ ├─ Read claude-progress.txt (quick state) │
│ ├─ Read feature_list.json (work remaining) │
│ └─ Get git log (recent commits) │
│ │
│ 2. ENVIRONMENT CHECK │
│ ├─ Run init.sh if needed │
│ ├─ Verify server running │
│ └─ Run smoke tests │
│ │
│ 3. SELECT FEATURE │
│ ├─ Get highest-priority incomplete feature │
│ ├─ Read feature steps │
│ └─ Plan implementation │
│ │
│ 4. IMPLEMENT WITH TDD │
│ ├─ Write failing test │
│ ├─ Verify test fails │
│ ├─ Implement code │
│ ├─ Verify test passes │
│ └─ Verify E2E (if applicable) │
│ │
│ 5. MARK COMPLETE │
│ ├─ Update feature_list.json (passes: true) │
│ └─ IMPORTANT: Features only go false → true │
│ │
│ 6. COMMIT WORK │
│ ├─ git add relevant files │
│ ├─ Descriptive commit message │
│ └─ Reference feature ID │
│ │
│ 7. UPDATE PROGRESS │
│ ├─ Append to claude-progress.txt │
│ └─ List accomplishments and blockers │
│ │
│ 8. END SESSION │
│ ├─ Leave code in mergeable state │
│ └─ Auto-continue or shutdown │
│ │
└─────────────────────────────────────────────────────────────┘
┌─────────────────────────────────────────────────────────────┐
│ TDD CYCLE │
├─────────────────────────────────────────────────────────────┤
│ │
│ ┌──────────┐ │
│ │ 1. RED │ Write failing test │
│ └────┬─────┘ │
│ │ Test fails ✓ │
│ ▼ │
│ ┌──────────┐ │
│ │ 2. GREEN │ Write minimal code to pass │
│ └────┬─────┘ │
│ │ Test passes ✓ │
│ ▼ │
│ ┌──────────┐ │
│ │3.REFACTOR│ Clean up without breaking tests │
│ └────┬─────┘ │
│ │ All tests pass ✓ │
│ ▼ │
│ ┌──────────┐ │
│ │ 4. E2E │ Verify in browser (if needed) │
│ └────┬─────┘ │
│ │ Feature works ✓ │
│ ▼ │
│ COMMIT │
│ │
└─────────────────────────────────────────────────────────────┘
<type>: <description>
<body - what and why>
Feature: <feature-id>
Example:
feat: implement user signup with email validation
- Added SignupForm component with validation
- Created /api/auth/signup endpoint
- Added email verification check
- Tests: 8 passing
Feature: auth-001
references/CODING-WORKFLOW.md - Detailed workflowreferences/TDD-PATTERNS.md - TDD best practicesreferences/COMMIT-CONVENTIONS.md - Commit guidelinesscripts/coding_agent.py - Main CodingAgent classscripts/feature_selector.py - Feature prioritizationscripts/implementation_workflow.py - TDD implementationscripts/commit_workflow.py - Git commit workflowdevelopment
Setup secure web-based terminal access to WSL2 from mobile/tablet via ttyd + ngrok/Cloudflare/Tailscale. One-command install, start, stop, status. Use when you need remote terminal access, web terminal, browser-based shell, or mobile access to WSL2 environment.
development
Complete development workflows where Claude writes the code while Gemini and Codex provide research, planning, reviews, and different perspectives. Claude remains the main developer. Use for complex projects requiring expert planning and multi-perspective reviews.
development
Systematic progress tracking for skill development. Manages task states (pending/in_progress/completed), updates in real-time, reports progress, identifies blockers, and maintains momentum. Use when tracking skill development, coordinating work, or reporting progress.
testing
Comprehensive testing workflow orchestrating functional testing, example validation, integration testing, and usability assessment. Sequential workflow for complete skill testing from examples through scenarios to integration validation. Use when conducting thorough testing, pre-deployment validation, ensuring skill functionality, or comprehensive quality checks.