CtrlK
BlogDocsLog inGet started
Tessl Logo

upgrading-expo

Guidelines for upgrading Expo SDK versions and fixing dependency issues

61

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/expo/skills/upgrading-expo/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

87%Weight 40%Scale 1-3

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 upgrade guide with excellent progressive disclosure through real reference files. Its main weakness is workflow clarity: validation/feedback loops around destructive operations are implicit rather than explicit fix-retry cycles.

Suggestions

Add an explicit feedback loop after `npx expo-doctor`, e.g. "If expo-doctor reports errors, fix each one and re-run until it passes before proceeding."

Integrate a post-prebuild validation step (e.g. re-run expo-doctor or a build smoke test) after the destructive `npx expo prebuild --clean`.

Consolidate the scattered checklists (Housekeeping, Metro, Postcss, Deprecated Packages) into the step-by-step sequence so the upgrade flow is a single tracked path.

DimensionReasoningScore

Conciseness

The body is lean and command/table/checklist dense (e.g. "npx expo install expo@latest", the deprecated-packages table) without explaining concepts Claude already knows; nearly every token earns its place.

3 / 3

Actionability

It provides fully executable commands (install, expo-doctor, prebuild --clean), exact app.json snippets, and a concrete old→new package replacement table that is copy-paste ready.

3 / 3

Workflow Clarity

A numbered upgrade process with an expo-doctor checkpoint and a CNG conditional guard exists, but there is no explicit fix→revalidate feedback loop around the destructive `npx expo prebuild --clean`, and the related checklists are scattered rather than integrated into the sequence.

2 / 3

Progressive Disclosure

A References section lists six real one-level-deep files (e.g. ./references/react-19.md, ./references/expo-av-to-audio.md) with brief annotations, and detailed migration content is appropriately split out of the overview.

3 / 3

Total

11

/

12

Passed

Description

57%Weight 40%Scale 1-3

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 identifies a clear niche and a couple of concrete actions but lacks an explicit use-when trigger clause and relies on somewhat generic phrasing. It is distinctive but not fully specific or trigger-complete.

Suggestions

Add an explicit trigger clause, e.g. "Use when upgrading an Expo SDK version or resolving dependency errors after an upgrade."

Replace the soft "Guidelines for" lead with concrete verbs, e.g. "Upgrades Expo SDK versions and fixes resulting dependency issues."

Include natural trigger variations users would say, such as "Expo SDK upgrade", "expo-doctor errors", or "dependency conflicts".

DimensionReasoningScore

Specificity

The description names the domain and two concrete actions ("upgrading Expo SDK versions" and "fixing dependency issues"), but the soft lead-in "Guidelines for" keeps it from listing multiple specific comprehensive actions.

2 / 3

Completeness

It answers "what" (upgrading SDK versions, fixing dependency issues) but provides no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2.

2 / 3

Trigger Term Quality

It includes some natural terms a user might say ("upgrade", "Expo SDK", "dependency issues") but misses common variations and explicit trigger phrasing.

2 / 3

Distinctiveness Conflict Risk

"Upgrading Expo SDK versions" is a clear, narrow niche with distinct triggers unlikely to overlap with unrelated skills.

3 / 3

Total

9

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
openai/plugins
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.