CtrlK
BlogDocsLog inGet started
Tessl Logo

try-tessl/agent-quality

Analyze agent sessions against verifier checklists, detect friction points, and create structured verifiers from skills and docs. Produces per-session verdicts and aggregated quality reports.

88

2.93x
Quality

86%

Does it follow best practices?

Impact

97%

2.93x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Evaluation results

93%

85%

Set Up Compliance Tracking for the Frontend Design Tile

Criteria
Without context
With context

Companion tile outside .tessl/

0%

100%

tile.json present

0%

100%

docs key in tile.json

0%

100%

docs/overview.md present

0%

100%

Every verifier linked in overview

0%

100%

Flat verifiers dir at tile root

0%

100%

Sources field included

0%

100%

Kebab-case file names

100%

100%

watch-local install command

0%

0%

Binary checklist rules

0%

100%

100%

77%

Automate the Session Analysis Workflow

Criteria
Without context
With context

SCRIPTS_PATH find pattern

0%

100%

Correct script path in find

0%

100%

python3 invocation

0%

100%

SCRIPTS_PATH empty check

0%

100%

max-sessions flag

0%

100%

search-before-analyze pattern

46%

100%

Small batch for search results

60%

100%

No auto Phase 2 progression

100%

100%

100%

31%

Add Compliance Verifiers to the Data Pipeline Tile

Criteria
Without context
With context

Verifiers in skill dir

100%

100%

Flat verifiers dir

75%

100%

Kebab-case file names

75%

100%

Sources field omitted

100%

100%

Activation verifier

100%

100%

Binary checklist rules

60%

100%

Multi-part decomposition

30%

100%

Specific decision-point relevant_when

0%

100%

Context fields present

0%

100%

Prohibition verifier present

100%

100%

Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents