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
100%
Does it follow best practices?
Impact
100%
2.56xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, well-crafted description that excels in specificity and distinctiveness. It opens with an explicit 'Use when...' clause and enumerates a comprehensive list of concrete actions and trigger terms. The only minor weakness is that it reads as a dense run-on sentence that could benefit from slightly better structural organization, but functionally it serves its purpose of skill selection very well.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple specific concrete actions: migrating, restructuring, publishing, auditing skills into tiles; converting file formats; fixing Quality/Impact/Uplift scores, frontmatter, metadata, tile.json, README, markdown reference links; pushing scores from 88-99% to 100%. Very detailed and concrete. | 3 / 3 |
Completeness | The description explicitly starts with 'Use when...' providing clear trigger guidance for when Claude should select this skill, and the extensive list of actions clearly answers 'what does this do'. Both dimensions are thoroughly covered. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a user would say: 'Tessl tile', 'SKILL.md', 'tile.json', 'frontmatter', 'metadata', 'README', 'Quality', 'Impact', 'Uplift', 'registry-vs-local', 'auto-eval', 'markdown reference links', 'artifact anchors'. These are highly domain-specific terms that users working in this space would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with very specific niche terminology like 'Tessl tile', 'tile.json', 'registry-vs-local Quality gaps', 'auto-eval wait discipline', and score ranges like '88-99% to 100%'. This is unlikely to conflict with any other skill due to its extremely specialized domain. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exceptionally well-structured skill that serves as a clear operational playbook for migrating skills to Tessl tiles. It maximizes information density through tables, command anchors, and decision trees while maintaining clarity. The progressive disclosure is exemplary, with the SKILL.md acting as a concise hub pointing to detailed phase references, and the workflow includes explicit validation gates and stop conditions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section serves a clear purpose—workflow table, command anchors, source triage, done criteria, stop conditions. There's no explanation of what Tessl is or how tiles work conceptually; it assumes Claude already knows and just provides the operational guidance. | 3 / 3 |
Actionability | Provides concrete CLI commands (tessl --version, tessl tile lint, tessl tile publish --dry-run, etc.), a specific critical inline path with numbered steps, explicit source triage decision tree, and precise done/stop criteria. The guidance is specific and directly executable. | 3 / 3 |
Workflow Clarity | The 7-phase workflow is clearly sequenced in a table with references for each phase. The critical inline path provides a minimum viable sequence. Validation checkpoints are explicit (lint before publish, wait for moderation, fetch skill-reviews, confirm every dimension 3/3 before proceeding). Stop conditions define clear failure modes with feedback loops (e.g., three consecutive eval runs below 80%). | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: the SKILL.md is a concise overview with a workflow table linking to 7 separate phase reference files, plus prerequisite-skills.md and lessons-learned.md. References are one level deep and clearly signaled with both descriptive text and markdown links. The 'Always Check First' section provides clear navigation priority. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents