Tessl • The management layer for AI agent skills

SkillPublic

table-state

Choose Table v9 state ownership, atoms, initialization, updates, and resets. Load for controlled slices or state coordination; use the adapter state skill for reactive reads.

Quality

87%

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.

An exemplary lean skill body: contract-dense prose, one executable example, a decision table, and explicit routing to sibling skills for out-of-scope depth. The only gap is the absence of explicit validation checkpoints, which is largely inapplicable to a configuration-decision skill.

Dimension	Reasoning	Score
Conciseness	Every sentence carries v9-specific contract information (owner precedence, reset semantics, atom resolution, feature gating) with zero padding or explanation of concepts Claude already knows. The single code example is compact and purposeful, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	A complete, copy-paste-ready code example with real imports (constructTable, initialState, table.setPageSize, resetPagination) plus concrete API names (functionalUpdate, on<Slice>Change, table.atoms.pagination.get()) and exact .d.ts paths to inspect. The ownership table maps each choice to its exact configuration and update path, matching the fully-executable anchor.	5 / 5
Workflow Clarity	The decision flow is clearly sequenced: default to internal ownership, pick one owner per slice (with a decision table), edge-case rules for mismatched configs, then read/write semantics, initialization, and resets. This sits at the 'clear sequence with most checkpoints present' anchor; it lacks the explicit validation/verification checkpoints of the 5 anchor, though none are strictly required for a non-destructive configuration-choice skill.	4 / 5
Progressive Disclosure	No bundle files exist, and none are needed: the body is a well-organized set of short sections that correctly delegates depth to other skills ('Read core first', 'load the adapter's table-state skill for reactive reads'). Scope is kept tight with clear section headers and one-level-deep routing, matching the well-organized-structure anchor for self-contained skills.	5 / 5
	Total	19 / 20 Passed

Description

78%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.

A compact, third-person description with a clear niche, explicit what/when structure, and deliberate disambiguation from the adapter skill. Its main weakness is trigger phrasing that leans on domain jargon ('controlled slices', 'state coordination') rather than the natural terms a user would say.

Suggestions

Add natural trigger phrases users would actually type, e.g. 'Use when configuring TanStack Table state, controlled slices, or onStateChange-style callbacks'.

Include one plain-language synonym for the jargon triggers, such as 'table state' or 'controlled state', to broaden keyword coverage.

Consider naming the library ('TanStack Table v9') in the first sentence instead of just 'Table v9' for discoverability.

Dimension	Reasoning	Score
Specificity	"Choose Table v9 state ownership, atoms, initialization, updates, and resets" names the domain and five concrete facets (ownership, atoms, initialization, updates, resets), matching the anchor for several specific items with only minor coverage gaps. It falls short of the 5 anchor because a single verb ('Choose') governs the facets rather than multiple distinct concrete actions.	4 / 5
Completeness	The 'what' is explicit (choose ownership, atoms, initialization, updates, resets) and the 'when' is present via "Load for controlled slices or state coordination". This matches the anchor where both exist but the trigger could be more concrete — the when-clause relies on jargon ('controlled slices') rather than natural trigger phrases, so it does not reach the 5 anchor.	4 / 5
Trigger Term Quality	Phrases like "controlled slices", "state coordination", "state ownership", and "atoms" give good keyword coverage of the domain, matching the 'good coverage, a few natural terms missing' anchor. Common user phrasings like 'table state', 'controlled state', or 'state management' are absent, keeping it below 5.	4 / 5
Distinctiveness Conflict Risk	"Table v9" pins a clear niche and the description actively disambiguates from the sibling skill ("use the adapter state skill for reactive reads"), matching the clear-niche/minimal-conflict anchor. Lower anchors (broad overlap with similar skills) do not fit given this explicit routing.	5 / 5
	Total	17 / 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/table-core/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?