CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

expo-deployment

Deploy Expo apps to production

Quality

56%

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/antigravity-bundle-expo-react-native/skills/expo-deployment/SKILL.md

The canonical home for this skill is expo-deployment in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

46%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 well-organized and free of concept over-explanation, but it operates entirely at the outline level: no commands, code, or concrete procedures anywhere, and production deployment lacks validation checkpoints. Duplicated framing sections (Overview / When to Use / Instructions) waste tokens that concrete EAS commands and pre-submit verification steps should occupy.

Suggestions

Replace abstract steps with executable commands, e.g. `eas build --platform all --profile production`, `eas submit`, `eas update --channel production`, and a minimal eas.json production profile example.

Add explicit validation checkpoints before outward-facing actions, e.g. verify the build passes `eas build --auto-submit` dry-run checks, confirm version/bump and release notes before `eas submit`, and monitor then roll back OTA updates with `eas update --republish`/channel rollback.

Delete the 'Instructions' section (a duplicate of 'When to Use This Skill') and the redundant opening trigger line to cut ~10 lines of padding.

DimensionReasoningScore

Conciseness

The body never explains concepts Claude already knows, and the workflow steps are terse one-liners, but it contains real padding: the 'Instructions' section re-lists the same five areas as 'When to Use This Skill', the opening line "Use this skill when you need to deploy Expo apps to production" duplicates the first bullet, and the Overview restates the frontmatter description. This fits 'mostly efficient but includes some unnecessary... padding that could be tightened' rather than score 2, since the redundancy is confined to one duplicated section plus a couple of lines rather than several padded explanations.

3 / 5

Actionability

Every step is abstract direction with no executable content — no commands (e.g. eas build/submit/update), no code, no config examples; even the most concrete items ("Use EAS Build", "App Store Connect / Google Play Console") only name tools and platforms without how to use them. This matches 'Minimal concrete guidance; high-level hints but missing the specific steps to execute'; it avoids score 1 only because tools and platforms are at least named and a rough ordering is given.

2 / 5

Workflow Clarity

A rough sequence exists (Pre-Deployment, App Store Deployment, OTA Updates) but validation checkpoints are absent or implicit — "Ensure all tests pass" is the only check, there is no verify step before submission or rollout, and "Handle rollbacks if needed" names error recovery without any loop. Because production deployment is a batch/outward-facing operation, the rubric caps workflow clarity at 3 for missing validation, which this content hits exactly ('steps listed but validation gaps').

3 / 5

Progressive Disclosure

The skill has no bundle files (no references/, scripts/, or assets/ directories exist), and the ~60-line body is cleanly sectioned with headers, so nothing is buried or nested. This earns 'good structure; most content appropriately placed; minor organization gaps' rather than 5 because the body exceeds the under-50-line simple-skill threshold and covers three substantial sub-domains (store submission, OTA, release management) whose detail would be better split into one-level-deep reference files.

4 / 5

Total

12

/

20

Passed

Description

48%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 correctly identifies a clear, distinct niche (Expo deployment) but is too sparse: it names only one generic action and provides no 'Use when...' trigger guidance, which caps completeness and limits trigger-term coverage. Adding explicit triggers and 1-2 concrete actions (app store submission, OTA updates, EAS) would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when deploying or releasing an Expo/React Native app, publishing to the App Store or Google Play, or pushing OTA updates with EAS."

Name 1-2 concrete capabilities in the 'what' portion, e.g. "Build and submit production binaries to app stores and publish over-the-air (OTA) updates" instead of the generic "deploy".

Include natural user synonyms and tool names (EAS, app store, publish, release, OTA) to improve trigger-term coverage without adding length.

DimensionReasoningScore

Specificity

The description is "Deploy Expo apps to production" — it names the domain (Expo deployment) but the single action verb "deploy" is generic, with no concrete actions like submitting to app stores or publishing OTA updates. This matches the anchor 'Names the domain but actions are minimal or generic' (cf. 'Processes PDF files'), and falls short of score 3, which requires 1-2 concrete named actions.

2 / 5

Completeness

The 'what' is stated clearly (deploy Expo apps to production), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guidelines. It is not score 2 because the 'what' is clear and domain-specific rather than vague, and not score 4 because the 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

"Deploy" and "Expo" are natural terms a user would say, but the description omits common variations and synonyms users actually use: "app store", "publish", "release", "EAS", "OTA update". This fits 'Some relevant keywords but missing common variations or synonyms' ('Works with PDF files') rather than score 4's 'good keyword coverage with only a few natural terms missing'.

3 / 5

Distinctiveness Conflict Risk

"Expo" carves out a clear niche with minimal conflict risk against unrelated skills, matching 'Mostly distinct; minor overlap risk'. It falls short of score 5 because the bare action "deploy ... to production" leaves minor overlap with generic deployment or React Native release skills, and the anchor-5 pattern pairs the niche with distinct explicit trigger phrases, which this description lacks.

4 / 5

Total

12

/

20

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.

Validation — 15 / 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

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/antigravity-bundle-expo-react-native/skills/expo-deployment/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.