Tessl • The management layer for AI agent skills

SkillPublic

getting-started

Create and render Table v9 with the svelte adapter. Route reusable createTableHook components, Query and Virtual integration, and framework setup; use table-state for reactive ownership.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

93%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a lean, fully executable getting-started guide that assumes Claude's competence and adds only version-specific, non-obvious constraints. Its one soft spot is workflow clarity: the sequence is coherent but includes no verification or error-recovery checkpoints, which is acceptable for this skill type yet keeps it off the top anchor.

Dimension	Reasoning	Score
Conciseness	The body never explains concepts Claude already knows; it delivers only non-obvious version-specific rules ("V9 requires Svelte 5 and createTable", "data captured once cannot follow reassignment", "Put row-model slots after their prerequisite features") plus one minimal working example. Every token earns its place.	5 / 5
Actionability	The Setup section is a complete, copy-paste-ready Svelte 5 component (imports, typed columns, $state data, getter-based reactivity, FlexRender markup), and the skill gives concrete commands: "intent load @tanstack/table-core#core" and exact node_modules declaration paths for API discovery.	5 / 5
Workflow Clarity	A clear sequence is present: an explicit prerequisite step ("Before starting, run `intent load @tanstack/table-core#core`"), then setup, then constraints, then task-based routing. This is a non-destructive setup/rendering skill so no validation cap applies, but there are no checkpoints or error-recovery notes, keeping it below the top anchor.	4 / 5
Progressive Disclosure	The "Load by task" section is a well-signaled routing table: each of the three reference files (create-table-hook.md, with-tanstack-query.md, with-tanstack-virtual.md — all verified to exist and match their topics) is linked one level deep with explicit task triggers, and deeper material is correctly deferred rather than inlined.	5 / 5
	Total	19 / 20 Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description states concrete capabilities in a distinct, domain-specific niche with good natural trigger terms. Its main weakness is the absence of any explicit "Use when..." trigger guidance, which caps completeness, alongside the omission of the common "TanStack" brand phrasing.

Suggestions

Add an explicit trigger clause, e.g. "Use when setting up TanStack Table in Svelte 5 apps, migrating v8 svelte-table code, or integrating Query/Virtual with a Svelte table."

Include the natural brand and package synonyms users would say — "TanStack Table", "@tanstack/svelte-table", "Svelte 5" — to strengthen trigger term coverage.

Replace the compressed "framework setup" phrase with a concrete action (e.g. "configure tableFeatures registrations") to close the specificity gap.

Dimension	Reasoning	Score
Specificity	"Create and render Table v9 with the svelte adapter" and "Route reusable createTableHook components, Query and Virtual integration" list several concrete, specific actions. "Framework setup" is compressed topic-listing rather than a fully stated action, leaving minor gaps that keep it below the comprehensive anchor.	4 / 5
Completeness	The "what" is clear (create/render the table, route createTableHook, Query, and Virtual integrations, use table-state for reactive ownership), but there is no "Use when..." clause or equivalent explicit trigger guidance. Per the judging guidelines, a missing when-clause caps completeness at 3.	3 / 5
Trigger Term Quality	"Table v9", "svelte adapter", "Query", "Virtual", and "table-state" are natural terms users would say for this domain, giving good coverage across subtopics. The most common brand phrasings ("TanStack", "@tanstack/svelte-table", "Svelte 5") are absent, so a few natural terms are missing.	4 / 5
Distinctiveness Conflict Risk	"svelte adapter", "createTableHook", and "table-state" pin a clear niche distinct from other framework adapters. Minor overlap risk remains with closely related sibling skills (table-state, table-features), though the description explicitly routes reactive ownership to table-state.	4 / 5
	Total	15 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	13 / 16 Passed

Repository: TanStack/table
Path: packages/svelte-table/skills/getting-started/SKILL.md
Revision: c14e022

Reviewed: 16 days ago

Discovery Implementation Validation

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.

getting-started

Table of Contents

Is this your skill?