New Feature Setup

SkillDev tools

Create a new feature with proposal, retrospective, and branch. Use when starting new development work.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the New Feature Setup skill

What this skill tells your AI

The instructions your AI receives, as published by stevegjones/ai-first-sdlc-practices in skills/new-feature/SKILL.md and read by ahel’s review.

Create a new feature with all required artifacts. Arguments:

  • $0 — Feature number (e.g., 70)
  • $1 — Feature name for branch (e.g., plugin-migration)
  • $2+ — Optional title (defaults to name with spaces)

Steps

  1. Create the feature proposal at docs/feature-proposals/$0-$1.md

    • Use the template from templates/proposal.md
    • Replace placeholders:
      • FEATURE_NUMBER$0
      • FEATURE_NAME$1
      • FEATURE_TITLE$2 (or derive from $1 by replacing hyphens with spaces)
      • CREATED_DATE → today's date (YYYY-MM-DD)
  2. Create the retrospective at retrospectives/$0-$1.md

  3. Create the feature branch

git checkout main
git pull
git checkout -b feature/$1
  1. Run syntax validation
/sdlc-core:validate --syntax

If the validate skill is not available (e.g., first-time setup), run the inline fallback:

python -c "
import ast, pathlib
for f in pathlib.Path('.').rglob('*.py'):
    if '.venv' in str(f): continue
    ast.parse(f.read_text())
print('Syntax OK')
"
  1. Check for CI/CD (first feature only)

If .github/workflows/ does not exist or contains no workflow files:

No CI/CD workflow found. Run /sdlc-core:setup-ci to add GitHub Actions validation.
  1. Report the created files and branch name to the user.

Signals

GitHub stars
41
Forks
6
Last commit
Aug 2026
Advanced
Catalog kind
skill
Gateway key
new-feature-stevegjones
Source
github.com/stevegjones/ai-first-sdlc-practices