CtrlK
BlogDocsLog inGet started
Tessl Logo

sharaf/migrate-to-tessl

Use when migrating, restructuring, publishing, or auditing an existing Claude skill into a Tessl tile; converting flat .md files or SKILL.md bundles; fixing Tessl Quality, Impact, Uplift, frontmatter, metadata, tile.json summary, README, markdown reference links, registry-vs-local Quality gaps, artifact anchors, auto-eval wait discipline, or pushing tile scores from 88-99% to 100%.

100

1.17x
Quality

100%

Does it follow best practices?

Impact

100%

1.17x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Overview
Quality
Evals
Security
Files

Evaluation results

100%

52%

Prepare a Skill Bundle for Tessl Publication

Tessl skill bundle restructuring

Criteria
Without context
With context

Markdown links for refs

100%

100%

No backtick paths remain

100%

100%

Standard top-level frontmatter

40%

100%

Metadata block present

0%

100%

Metadata string values only

0%

100%

metadata.version present

0%

100%

Use when clause in description

0%

100%

tile.json summary synced

30%

100%

README at tile root

60%

100%

Reference files in correct location

100%

100%

100%

60%

Maximize Tile Quality Before Registry Submission

Tile quality audit and frontmatter fix

Criteria
Without context
With context

Non-standard keys removed

0%

100%

Metadata block added

0%

100%

String-only metadata values

0%

100%

metadata.version key

0%

100%

Top-level version removed

0%

100%

Use when clause

100%

100%

tile.json summary updated

0%

100%

README.md created

100%

100%

README includes when-to-use

75%

100%

Audit report created

100%

100%

100%

70%

Write a Tessl Migration Runbook for the Platform Team

Migration runbook and preflight guide

Criteria
Without context
With context

CLI version check

62%

100%

Login check

87%

100%

Required skills check

10%

100%

Project creation timing

0%

100%

Eval caching pitfall

0%

100%

Activation vs content eval

0%

100%

Default visibility private

100%

100%

Default version 0.1.0

0%

100%

Default eval agent

0%

100%

Dry-run before publish

100%

100%

Minor bump for final publish

0%

100%

Stop conditions listed

57%

100%

Evaluated
Agent
Claude
Model
Claude Sonnet 4.6

Table of Contents