CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

migrate-v8-to-v9

Audit and migrate Table v8 to v9. Inventory affected APIs, follow the shared checklist, and read only the required architecture, state, feature, and TypeScript mappings.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 excellent migration skill body: lean and fully actionable, with an audit-driven routing table that delegates details to verified one-level-deep reference files and explicit validation framing the procedure. The only gap is the absence of an explicit failure/retry step in the Procedure.

Suggestions

Add an explicit error-recovery step to the Procedure, e.g. 'If the type-check or an interaction test fails, map the failure back to its checklist item, re-apply the corresponding reference mapping, and re-verify before proceeding.'

DimensionReasoningScore

Conciseness

The body is dense checklist-style directives with zero padding: it assumes Claude's competence by naming v8 APIs ('getCoreRowModel()', 'sortingFns', 'onStateChange', 'useLegacyTable') without explaining what they are, and every line is an actionable migration instruction. Matches the 'lean and efficient; every token earns its place' anchor; nothing explains concepts Claude already knows.

5 / 5

Actionability

Concrete, executable guidance throughout: exact commands ('intent load <package>#migrate-v8-to-v9'), exact entrypoints ('@tanstack/react-table/legacy', 'node_modules/@tanstack/table-core/dist/index.d.ts'), and exact rename/registration targets ('create*RowModel() feature slots', 'AggregationFnDef', 'TFeatures', 'columnSizingFeature before columnResizingFeature'). As an instruction-only skill its guidance is fully specific, and detailed mappings are carried by the reference files, so there are no real gaps.

5 / 5

Workflow Clarity

A clear 4-step Procedure with explicit validation at both ends ('Establish passing tests for the existing table' as baseline; 'Type-check, exercise every enabled interaction and client/server stage') plus a completion-checks section and a full audit checklist. It falls short of the anchor-5 exemplar only because there is no explicit error-recovery loop (e.g., 'if the type-check or an interaction test fails, revisit the corresponding checklist item and re-verify'), unlike the anchor's 'If errors: fix and re-validate'; it is clearly above anchor 3 since checkpoints are explicit, not implicit.

4 / 5

Progressive Disclosure

The 'Read mappings for affected code' table routes specific audit findings to four well-signaled, one-level-deep references (references/architecture.md, state.md, feature-apis.md, typescript.md), all of which exist and hold the detailed v8-to-v9 mappings. The body stays a genuine overview and navigation is trivial, matching the top anchor exactly.

5 / 5

Total

19

/

20

Passed

Description

75%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 strong, highly specific description of a version-migration skill with concrete actions and a distinct, low-conflict niche. Its main weaknesses are the complete absence of explicit 'use when' trigger guidance and missing common synonyms like 'upgrade' or 'TanStack'.

Suggestions

Add an explicit trigger clause, e.g. 'Use when migrating a TanStack Table v8 codebase to v9, or when the user mentions upgrading table-core, table v9, or v8-to-v9 table migration.'

Include natural synonyms users would say — 'upgrade', 'TanStack Table', and adapter names (React, Preact, Solid, Svelte, Vue, Angular, Lit) — to strengthen trigger matching.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Audit and migrate Table v8 to v9', 'Inventory affected APIs', 'follow the shared checklist', and read the named 'architecture, state, feature, and TypeScript mappings' — comprehensively covering what the skill does. It exceeds anchor 4 ('minor gaps in coverage') because every phase of the skill's work is named explicitly.

5 / 5

Completeness

The 'what' is clear (audit and migrate Table v8 to v9, inventory affected APIs, follow the shared checklist, read the required mappings), but there is no 'Use when...' clause or equivalent explicit trigger guidance; per the judging guidelines a missing trigger clause caps completeness at 3, and the 'when' is only weakly implied for a user already mid-migration.

3 / 5

Trigger Term Quality

It contains the core natural phrases a user would say ('migrate', 'Table v8 to v9', 'audit'), giving good keyword coverage, but misses common synonyms and variations such as 'upgrade', 'TanStack Table', or adapter/framework names. Short of anchor 5's synonym-and-extension comprehensiveness but clearly above anchor 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

'Audit and migrate Table v8 to v9' pins a specific library-version niche with distinct triggers, so overlap with other skills is minimal — it would not fire for generic table, migration, or document work.

5 / 5

Total

17

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

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/migrate-v8-to-v9/SKILL.md

Reviewed

Table of Contents

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.