Name: core
Rating: 66.4 (1 reviews)
Author: TanStack

core

Use TanStack Table v9 as a headless data-grid state and row-processing engine. Load for first-table architecture, stable data and columns, row numbering with getDisplayIndex, semantic rendering, framework adapter choice, or deciding what Table owns versus the renderer.

Quality

80%

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

90%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 an efficient, highly actionable reference with executable code and well-structured sections; its only weakness is that it reads as a pattern catalog rather than a guided multi-step workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence: a one-line boundary statement, tight code blocks, and single-sentence explanations of V9-specific behavior, with no padding about what tables or libraries are.	5 / 5
Actionability	It provides copy-paste-ready, fully executable TypeScript (imports, constructTable, column helpers, row iteration) plus wrong/correct pairs for common mistakes that cover the central cases.	5 / 5
Workflow Clarity	Clear sequences exist (Setup, then API Discovery: inspect the table-core .d.ts, follow the implementation, then the adapter getting-started skill), and no validation checkpoints are required because the operations are non-destructive model work.	4 / 5
Progressive Disclosure	Content is well-organized into Setup, Core Patterns, Common Mistakes, and API Discovery with the only external pointer being a clearly signaled one-level-deep reference to the adapter getting-started skill; minor gap is that ~160 lines are fully inlined with no file split.	4 / 5
	Total	18 / 20 Passed

Description

71%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 clearly identifies a distinct, well-scoped niche and provides explicit trigger guidance, but it is somewhat jargon-heavy and omits common user synonyms for table features.

Suggestions

Add a clearer 'Use when ...' phrasing and include natural user terms like sorting, filtering, and pagination alongside the existing triggers.

Soften internal API jargon (e.g. 'getDisplayIndex', 'framework adapter choice') or pair it with the plain-language problem it solves.

Lead with the concrete capability (build/manage headless table state and row models) before the list of load scenarios.

Dimension	Reasoning	Score
Specificity	Names the domain ('TanStack Table v9 as a headless data-grid state and row-processing engine') and lists several specific load scenarios (first-table architecture, stable data and columns, row numbering with getDisplayIndex, framework adapter choice), with minor gaps where some items are abstract rather than concrete actions.	4 / 5
Completeness	It states a clear 'what' ('Use TanStack Table v9 as a headless data-grid state and row-processing engine') and provides equivalent explicit trigger guidance via 'Load for ...', but the 'when' reads more as a feature list than explicit user-trigger phrasing, so it sits just below the top anchor.	4 / 5
Trigger Term Quality	Relevant natural keywords appear ('TanStack Table', 'data-grid', 'row numbering') but the phrase leans on internal jargon ('getDisplayIndex', 'framework adapter choice', 'headless data-grid state and row-processing engine') and omits common synonyms users would say like sorting, filtering, or pagination.	3 / 5
Distinctiveness Conflict Risk	It names a specific library and version with a precise niche (headless data-grid state engine) and distinct triggers, giving it minimal overlap with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: TanStack/table
Path: packages/table-core/skills/core/SKILL.md
Commit: 9e523bc

Reviewed: 1 day ago

Table of Contents

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.