CtrlK
BlogDocsLog inGet started
Tessl Logo

openspec-explore

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

76

1.04x
Quality

64%

Does it follow best practices?

Impact

94%

1.04x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.codex/skills/openspec-explore/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

93%

3%

Real-Time Collaboration Feature Exploration

Vague-idea exploration with diagrams

Criteria
Without context
With context

openspec list check

0%

30%

ASCII diagram present

100%

100%

Multiple directions surfaced

100%

100%

Open questions captured

100%

100%

No application code written

100%

100%

No auto-capture of OpenSpec artifacts

100%

100%

Assumption questioning

100%

100%

Next steps or offer

100%

100%

Not a scripted checklist response

100%

100%

98%

10%

Storage Strategy Decision for a New CLI Tool

Option comparison with context-seeking

Criteria
Without context
With context

Context sought first

86%

93%

ASCII comparison table

100%

100%

Context-specific tradeoffs

100%

100%

Assumption challenged

100%

90%

No application code written

100%

100%

openspec list check

0%

100%

Open questions noted

100%

100%

No auto-capture

100%

100%

92%

Notification Delivery Architecture — Mid-Change Blocker

Mid-change blocker with artifact context

Criteria
Without context
With context

Reads change artifacts

100%

100%

References artifact content

100%

100%

ASCII diagram present

100%

100%

openspec list check

0%

0%

Offer to update design — not auto-applied

100%

100%

No application code written

100%

100%

Key decisions identified

100%

100%

Open questions surfaced

100%

100%

No auto-update of design files

100%

100%

Repository
arm/mlia
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.