ask-questions-if-underspecified
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
Install with Tessl CLI
npx tessl i github:Dicklesworthstone/pi_agent_rust --skill ask-questions-if-underspecified62
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Evaluation results
100%
60%User Notification System
Structured clarifying questions
Numbered questions
100%
100%
Question count
0%
100%
Multiple-choice options
0%
100%
Default marked
0%
100%
Fast-path response
16%
100%
Not-sure option
0%
100%
Compact reply format
30%
100%
No implementation started
100%
100%
Branch-eliminating questions
100%
100%
Short scannability
42%
100%
No open-ended questions
28%
100%
Without context: $0.1131 · 33s · 10 turns · 13 in / 1,426 out tokens
With context: $0.2038 · 54s · 12 turns · 276 in / 2,088 out tokens
68%
3%Refactor the Payment Module
Assumption listing and requirement restatement
Assumptions as numbered list
33%
75%
Confirmation requested
0%
0%
No implementation in assumptions doc
50%
87%
Requirement restatement
83%
66%
Restatement includes constraints
100%
87%
Assumptions cover scope
100%
100%
Assumptions cover constraints
100%
100%
Does not re-ask questions
100%
100%
Assumptions cover safety
70%
60%
Restatement includes success criteria
40%
30%
Without context: $0.2357 · 1m 12s · 12 turns · 19 in / 3,693 out tokens
With context: $0.3785 · 1m 49s · 17 turns · 133 in / 5,558 out tokens
90%
28%Add Rate Limiting to the Public API
Smart question selection
Discovered section present
100%
100%
Language/runtime discovered
100%
100%
Framework discovered
100%
100%
Redis discovered
100%
100%
No discoverable questions asked
100%
100%
Numbered questions
100%
100%
Multiple-choice format
0%
100%
Default indicated
0%
100%
Question count
0%
0%
Genuine unknowns asked
100%
100%
Compact reply format
0%
100%
Without context: $0.1432 · 44s · 8 turns · 13 in / 2,017 out tokens
With context: $0.2467 · 1m 7s · 12 turns · 309 in / 3,174 out tokens
- Evaluated
- Agent
- Claude Code
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.