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
100%
Does it follow best practices?
Impact
100%
1.11xAverage score across 4 eval scenarios
Advisory
Suggest reviewing before use
The data platform team built a Kafka stream-processing skill and packaged it as a Tessl tile. They've been iterating on the skill content and are now ready to submit to the registry for other teams to install. A colleague ran tessl skill review and reported that the Quality score was stuck around 88% despite the skill content being solid.
The tile files are at inputs/tile.json and inputs/skills/stream-processor/SKILL.md. The team wants the tile to score as close to 97% Quality as possible before they publish — without changing the actual skill guidance content, only the structural and metadata aspects that the Tessl quality rubric evaluates.
Your task is to audit the tile and produce fixed versions of the files, plus a README.md for the tile root. Explain what issues you found in a file called audit-report.md.
Write the following files to your working directory:
tile.json — corrected tile manifestskills/stream-processor/SKILL.md — corrected skill with fixed frontmatter and enhanced descriptionREADME.md — tile-root readme suitable for the Tessl registryaudit-report.md — a short report listing each issue found and the fix applied