Tessl • The management layer for AI agent skills

SkillPublic

table-state

Read and control Table v9 state in ember. Use for tracked reads, subscriptions, controlled slices, and framework-specific reactive boundaries.

Quality

85%

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 content is a model reference-skill body: lean, dense with non-obvious framework-specific rules, an executable controlled-state example, and one clearly signaled one-level-deep reference that was verified to exist. The only soft spot is workflow clarity, where the common "my table state isn't re-rendering" failure mode has rules but no explicit troubleshooting loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and imperative with zero padding: it never explains what Ember, Glimmer, or reactive state are, and every line (tracking rule, complete gts example, five boundary bullets, reference pointers, API-discovery paths) adds information Claude would not already know. It matches the "every token earns its place" anchor.	5 / 5
Actionability	The "Controlled tracked setup" section is a complete, executable, copy-paste-ready .gts component covering the common controlled-state case, and "API discovery" gives exact node_modules declaration paths to inspect. The "Reactive boundaries" bullets give concrete do/don't rules (e.g. "Mutating `this.pagination.pageIndex++` does not notify the thunk"), matching the fully-executable top anchor.	5 / 5
Workflow Clarity	Sequence is explicit ("Load `intent load @tanstack/table-core#table-state` first") followed by a coherent setup, boundaries, references, and discovery progression. There are no validation checkpoints, but the skill is non-destructive so the cap does not apply; it falls just short of anchor 5 because no troubleshooting guidance exists for the likely failure mode (state updates not re-rendering).	4 / 5
Progressive Disclosure	The body stays an overview and the single detail file, [reactivity](references/reactivity.md), is one level deep, present in the bundle, clearly signaled, and annotated with exactly when to read it. Advanced material (shared atoms, detailed subscription examples) is correctly split out to that reference.	5 / 5
	Total	19 / 20 Passed

Description

73%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 is third-person, concise, and answers both what the skill does and when to use it, with an explicit "Use for" clause and genuinely distinct Ember-specific triggers. Its main weakness is specificity: beyond "read and control state", the capability list leans on abstract reactive-boundary jargon rather than plain concrete actions, and it omits natural synonyms like "TanStack" or "useTable".

Suggestions

Replace abstract phrases like "framework-specific reactive boundaries" with concrete actions, e.g. "Read and control Table v9 state in ember: subscribe to tracked pagination, sorting, and visibility state, and keep it in sync with Glimmer tracked properties."

Add natural synonyms users would say, such as "TanStack Table", "useTable", and "table state", to the trigger list.

Make the "when" clause more concrete by naming the concrete states a user would mention (e.g. "Use when tracked reads, state subscriptions, or controlled state slices in ember tables are needed").

Dimension	Reasoning	Score
Specificity	"Read and control Table v9 state in ember" names the domain with two concrete actions, but companion phrases like "framework-specific reactive boundaries" and "controlled slices" are jargon-abstract rather than concrete capabilities. It sits between anchor 3 (1-2 concrete actions, not comprehensive) and anchor 4 (several specific actions), closer to 3 because only two plainly concrete actions are stated.	3 / 5
Completeness	Both parts are present: a clear "what" ("Read and control Table v9 state in ember") and an explicit "Use for..." trigger clause. It falls short of anchor 5 because trigger phrases like "framework-specific reactive boundaries" are less concrete than the crisp, natural triggers in the top anchor.	4 / 5
Trigger Term Quality	"tracked reads", "subscriptions", "Table v9", and "ember" are terms a user with this need would naturally say. Coverage is good but misses common synonyms a user might use, such as "TanStack", "useTable", or "table state".	4 / 5
Distinctiveness Conflict Risk	The pairing of "ember", "Table v9", and "tracked" carves out a clear niche with distinct triggers and minimal risk of firing for unrelated skills. It is not generic, and the framework qualifier separates it from sibling table-state skills.	5 / 5
	Total	16 / 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: 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: TanStack/table
Path: packages/ember-table/skills/table-state/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.

table-state

Table of Contents

Is this your skill?