Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/ai-coaching
Multi-turn conversational AI for intent extraction, clarification, and generation readiness detection. Guides users through articulating creative intent with structured parameter extraction.
Passed 22 of 23 test cases with the skill, and 10 of 23 without it.
and 15 more in the full report
12 fixed10 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
An ongoing creative intent schema has turn_count = 2, all ambiguous annotations resolved, but user_confirmed_vision is currently False. What readiness state enum value applies to this schema state? Return a JSON object with 'readiness_state'.
| Checked | Without skill | With skill |
|---|---|---|
| The response sets readiness_state to "awaiting_confirmation". | Missed | Passed |
The instructions your model reads when the skill loads.
Multi-turn conversational AI that guides users through articulating intent.
The coach helps users articulate WHAT they want, not HOW to achieve it. It extracts structured intent through conversation, tracks ambiguities, and signals readiness only after user confirmation.
User Input → Intent Parser → Schema Update → Readiness Check → Coach Response
from dataclasses import dataclass, field
from datetime import datetime
from typing import Optional, List, Dict, Any
from enum import Enum
import re
class ReadinessState(str, Enum):
NOT_READY = "not_ready"
NEEDS_CLARIFICATION = "needs_clarification"
AWAITING_CONFIRMATION = "awaiting_confirmation"
READY = "ready"
@dataclass
class AmbiguousAnnotation:
test cases passed, vs 10 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.