CtrlK
BlogDocsLog inGet started
Tessl Logo

consult

Simulates expert perspectives grounded in documented positions. Use when asking "what would [expert] say", "best practice", "panel", "debate", or needing domain guidance. Triggers on expert names, style requests, tradeoff questions, or "stuck on".

84

1.54x
Quality

83%

Does it follow best practices?

Impact

79%

1.54x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

48%

8%

Microservices vs Modular Monolith: Architecture Decision

Expert anonymity and AskUserQuestion format

Criteria
Without context
With context

Uses AskUserQuestion

0%

0%

No expert names in labels

100%

100%

No expert names in descriptions

100%

100%

No expert names in detail panels

100%

100%

One bold sentence before prompt

0%

0%

No paragraph before prompt

0%

0%

Label is conclusion-first

0%

60%

Description states why it matters

0%

50%

Go deeper option present

0%

0%

Concerns by decision not by expert

100%

100%

96%

57%

Persistent Data Corruption After Cache Layer Migration

Detail panel structure and forbidden headers

Criteria
Without context
With context

ALL CAPS section headers

0%

100%

No POSITIONS header

100%

100%

No TENSION header

100%

100%

No CONCERN header

100%

100%

Only WHY IT MATTERS and TRADEOFF

0%

100%

Line length ~40 chars

0%

100%

Dashes for bullets

100%

100%

No markdown in panel

0%

75%

Panel does not repeat label

70%

80%

Unblock mode selected

0%

100%

TRADEOFF has Gain and Pay

0%

100%

95%

20%

Developer Onboarding Flow: Design Review

Mode detection and minimal text framing

Criteria
Without context
With context

Review mode detected

53%

100%

3-4 experts selected

100%

100%

Cross-domain diversity

100%

100%

Max 2 from same domain row

100%

100%

Breadth over depth

100%

100%

Gaps identified

100%

100%

Uses AskUserQuestion

0%

50%

No expert names in output

100%

100%

Go deeper option

0%

100%

One bold framing sentence

40%

100%

Repository
saadshahd/moo.md
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.