CtrlK
BlogDocsLog inGet started
Tessl Logo

sanity-studio-upgrade

Produces a tailored Sanity Studio upgrade plan by inspecting the repository's installed versions, config, and source, then reporting only the breaking changes that actually apply. Covers Studio v3 and later; v2 projects are identified and redirected, not planned. Use this skill whenever someone wants to upgrade, migrate, or modernize a Sanity Studio across one or more major versions from v3 onward, asks what will break if they bump the `sanity` package, asks why their Studio broke after an upgrade, or asks how far behind their Studio is. Triggers on "upgrade sanity studio", "migrate our studio to v6", "bump sanity", "what breaks if we upgrade", "our studio is on an old version", "sanity upgrade plan", "is our studio out of date", "we are several majors behind". DO NOT load for upgrading non-Sanity dependencies, for Content Lake `apiVersion` questions, for content or schema migrations that change documents, or for setting up a new Sanity project.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 strong, well-architected body for a complex multi-version upgrade planner: clear sequenced workflow with explicit validation, excellent progressive disclosure, and concrete inline commands. Slightly verbose in places and delegates much executable detail to reference files, which caps conciseness and actionability at 4.

Suggestions

Tighten the elaborative prose in the scope and judgment-call sections (e.g. 'The reason is not that v2 is hard. It is that...') to trim tokens without losing the guidance.

Inline a short, representative copy-paste command sequence for the most common single-major case so the body is executable without first opening a reference file.

The 'Judgment calls worth making explicitly' section could be condensed into a tighter bulleted checklist to reduce skimming cost.

DimensionReasoningScore

Conciseness

The body is information-dense craft guidance that avoids explaining basics Claude already knows, but several passages (e.g. 'The reason is not that v2 is hard. It is that...') elaborate beyond what is strictly needed and could be tightened. Not a 5 because not every token earns its place; not a 3 because there is no padding about general concepts.

4 / 5

Actionability

Provides concrete inline commands ('npm view', 'npm pack', 'pnpm install --lockfile-only', 'grep -r "data-slate"'), a 7-step procedure, and the R1–R7 verification table, but much of the executable detail is delegated to reference files rather than copy-paste ready in the body itself. Not a 3 because what is inline is specific and executable; not a 5 because the body alone is not fully copy-paste ready.

4 / 5

Workflow Clarity

A clear 7-step sequence (Steps 1–7 plus 6b) with explicit validation checkpoints and stop conditions (no Studio found → stop; resolved major below floor → stop), and the R1–R7 rules table functions as a verification checklist. The destructive/batch cap is inapplicable since the skill is explicitly read-only.

5 / 5

Progressive Disclosure

The body is an overview that points to a well-signaled, one-level-deep reference layer, capped by a 'Reference files' table mapping each file to when it should be read; load-only-the-boundaries-you-cross keeps context lean, and all referenced files (detect, version-lookup, boundaries, boundary.v4/v5/v6, deprecations, package-coupling, plugins, report-template) are present in ./references/.

5 / 5

Total

18

/

20

Passed

Description

100%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.

An exemplary description: concrete capabilities, comprehensive natural triggers, explicit what/when guidance, and clear boundary-setting via DO-NOT-load clauses. Third-person voice is used correctly throughout.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'inspecting the repository's installed versions, config, and source', 'reporting only the breaking changes that actually apply', 'v2 projects are identified and redirected' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (produces a tailored upgrade plan by inspecting versions/config/source and reporting only applicable breaking changes) and 'when' ('Use this skill whenever someone wants to upgrade, migrate, or modernize...'), with concrete trigger phrases and explicit DO-NOT-load exclusions.

5 / 5

Trigger Term Quality

Includes a comprehensive set of natural trigger phrases users would actually say — 'upgrade sanity studio', 'migrate our studio to v6', 'bump sanity', 'what breaks if we upgrade', 'our studio is on an old version', 'sanity upgrade plan' — plus paraphrased question forms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Sanity Studio upgrades from v3 onward) with distinct triggers and explicit exclusions for non-Sanity dependencies, Content Lake apiVersion questions, content/schema migrations, and new project setup, keeping conflict risk minimal.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
sanity-io/agent-toolkit
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.