Add recipe-coach community ability

[sterling-prog]

What This Ability Does

Recipe Coach is a voice-guided cooking assistant. The user names a dish or ingredient, and the Ability generates a full recipe via the Personality's built-in LLM, then walks them through it step by step.

Features

• Zero setup — no API keys required, uses the built-in LLM
• Hands-free cooking — voice commands: next, repeat, stop
• Voice-optimized — short sentences, ingredients read in small groups, natural pacing
• Graceful exits — resume_normal_flow() on every exit path

Conversation Flow

1. Ask what the user wants to cook
2. Generate a recipe (ingredients + numbered steps) via LLM
3. Read ingredients in groups of 3
4. Confirm readiness before starting
5. Walk through steps one at a time with next/repeat/stop controls

Suggested Trigger Words

• "recipe coach"
• "help me cook"
• "walk me through a recipe"
• "teach me to cook"

Checklist

• PR targets dev branch
• Files in community/recipe-coach/
• main.py follows SDK pattern (extends MatchingCapability, has register_capability + call)
• README.md with description, triggers, setup, and example conversation
• resume_normal_flow() on every exit path
• No print() — uses editor_logging_handler
• No blocked imports
• No asyncio.sleep() or asyncio.create_task()
• No hardcoded API keys
• Error handling on all operations
• Short, natural spoken responses

[github-actions]

✅ Ability Validation Passed

📋 Validating: community/recipe-coach
  ✅ All checks passed!

[github-actions]

🔀 Branch Merge Check

PR direction: add-recipe-coach → dev

✅ Passed — add-recipe-coach → dev is a valid merge direction

[github-actions]

🔍 Lint Results

🔧 Auto-formatted

Some files were automatically cleaned and formatted with autoflake + autopep8 and committed.

• ✅ Unused imports removed (autoflake)
• ✅ Unused variables removed (autoflake)
• ✅ PEP8 formatting applied (autopep8)

✅ __init__.py — Empty as expected

Files linted: community/recipe-coach/main.py

✅ Flake8 — Passed

✅ All checks passed!

[Rizwan-095]

Approved for community.

We will proceed with adopting this ability for a 30-day evaluation period to monitor performance, identify any bugs, and implement any necessary fixes or optimizations. If the ability proves stable and meets our quality standards during this period, we will move forward with publishing it to the marketplace, ensuring full credit is given to the original author for their work and contribution.

We truly appreciate your effort and encourage you to continue developing and submitting new abilities. Contributions like yours help strengthen the ecosystem, and we look forward to seeing more of your work.