intent
Turn rough ideas into clear work orders before planning or building. Use when request is vague like "add a button", "make it better", "fix the thing". Triggers on ambiguous or underspecified requests. Produces a brief with scope, acceptance criteria, and stop conditions.
95
100%
Does it follow best practices?
Impact
76%
1.00xAverage score across 3 eval scenarios
Passed
No known issues
Evaluation results
70%
Feature Brief: Analytics Dashboard
Assumption batching and brief content integrity
Assumptions grouped correctly
0%
0%
Dependent assumption separated
0%
0%
Accept + alternatives format
0%
0%
ACCEPTANCE reflects confirmed choices
100%
100%
No invented thresholds in ACCEPTANCE
100%
100%
NON-GOALS from user statements
100%
100%
ACCEPTANCE criteria are binary
100%
100%
STOP CONDITIONS present
100%
100%
Time ranges in ACCEPTANCE
100%
100%
No re-clarified items
100%
100%
All 6 sections present
100%
100%
72%
Feature Brief: API Error Monitoring
Recommended practices cherry-pick and section placement
Structured logging in ACCEPTANCE
100%
100%
SLO criterion in ACCEPTANCE
100%
100%
PagerDuty NOT in ACCEPTANCE
100%
100%
Log retention NOT in ACCEPTANCE
100%
100%
PagerDuty in RECOMMENDED PRACTICES
0%
0%
Log retention in RECOMMENDED PRACTICES
0%
0%
Selected practices not duplicated
0%
0%
NON-GOALS from user statements
100%
100%
User-stated constraints in ACCEPTANCE
100%
100%
All 6 sections present
100%
100%
No invented criteria
100%
100%
86%
Clarification Plan: Checkout Flow Improvement
Divergent interpretations and gap-closing questions
Multiple interpretations listed
100%
100%
Interpretations framed as options
73%
86%
No single interpretation adopted
100%
100%
NOT-do question included
100%
100%
Remaining unknowns listed
100%
100%
Questions target unknowns
90%
100%
No brief or implementation scope
100%
100%
Step 1 summary present
87%
50%
Max 3 questions per group
0%
0%
- Repository
- saadshahd/moo.md
- Commit
e876ef5
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.