cell-selection

Select, add, and subtract rectangular cell ranges with cellSelectionFeature: ordered include/exclude operations keyed by row and column id, modifier dragging, final positive bounds, selection edges, render-order resolution under pinning, and autoResetCellSelection. Load for spreadsheet-style selection, “select all except” behavior, unexpected range changes after sorting or reordering, drag performance, or copy-to-clipboard.

Quality

91%

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.

A dense, executable skill body that respects token budget and gives concrete wrong/correct guidance. It loses a little on workflow clarity (no explicit validation loops for destructive selection/reset operations) and progressive disclosure (everything inline, no split reference files).

Suggestions

Add an explicit validation/recovery step for destructive or batch selection operations (e.g., verify bounds after resetCellSelection on data change) to satisfy the workflow-clarity feedback-loop expectation.

Move the API Discovery surface into a dedicated references file and link to it one level deep, keeping SKILL.md as a concise overview.

Soften the trigger phrasing in the description with a couple of colloquial synonyms users might actually say (e.g., "multi-cell select", "unselect cells").

Dimension	Reasoning	Score
Conciseness	Lean body that assumes Claude knows TypeScript and table libraries; every section earns its place with executable snippets and no padded conceptual explanation.	5 / 5
Actionability	Copy-paste-ready handler bindings, programmatic range calls, and read APIs with concrete arguments, plus a Common Mistakes section pairing wrong vs correct code.	5 / 5
Workflow Clarity	Setup, core patterns, and mistakes are clearly sequenced, but destructive/batch operations (selecting, clipboard, reset on data change) lack explicit validate-then-proceed checkpoints.	4 / 5
Progressive Disclosure	Well-organized sections with a one-level API Discovery pointer to node_modules, but there are no separate reference files; the inline API surface could be split out.	4 / 5
	Total	18 / 20 Passed

Description

92%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 high-quality, specific description with explicit what-and-when guidance and minimal conflict risk. Trigger phrasing is strong but slightly technical, leaving a little room for more colloquial synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions keyed by specific mechanisms — ordered include/exclude operations, modifier dragging, render-order resolution under pinning — giving comprehensive coverage of the feature's capabilities.	5 / 5
Completeness	Clearly states what the feature does and provides an explicit "Load for..." trigger clause covering several concrete scenarios, answering both what and when.	5 / 5
Trigger Term Quality	Strong natural triggers like "select all except", "drag performance", and "copy-to-clipboard", but lacks common synonyms/extension variants a user might say and leans technical rather than colloquial.	4 / 5
Distinctiveness Conflict Risk	A tightly scoped TanStack cell-selection sub-skill with feature-specific triggers is clearly distinguishable from sibling skills and unlikely to fire for the wrong one.	5 / 5
	Total	19 / 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/cell-selection/SKILL.md
Commit: 21d713f

Reviewed: 5 hours 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.