CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

expo-cicd-workflows

Helps understand and write EAS workflow YAML files for Expo projects. Use this skill when the user asks about CI/CD or workflows in an Expo or EAS context, mentions .eas/workflows/, or wants help with EAS build pipelines or deployment automation.

Quality

78%

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/AI-Agents-Safe-Coding-Skills/skills/expo-cicd-workflows/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 content is well-organized and appropriately brief, delegating the volatile details (job types, enums, expression contexts) to the live schema rather than duplicating them. Its main defect is that the fetch and validate workflows hinge on scripts referenced at {baseDir}/scripts/ that are not present in the skill bundle, making the core executable guidance and file navigation non-functional as shipped.

Suggestions

Ship the referenced scripts/fetch.js and scripts/validate.js (plus a package.json for the npm install step) in the skill's scripts/ directory, or replace them with self-contained commands (e.g., curl the schema URL directly) so the fetch and validate steps are executable as delivered.

Make the validation feedback loop explicit: after fixing reported errors, re-run the validator and only consider the workflow complete once it passes cleanly.

Consolidate the repeated 'fetch the schema instead of relying on memorized values' guidance, which appears in the Reference Documentation, Generating Workflows, and Answering Questions sections, into a single canonical statement.

DimensionReasoningScore

Conciseness

The body is lean with well-sectioned, non-padded guidance and no explanations of concepts Claude already knows. It is not 5 because the "fetch the schema rather than relying on memorized values" directive is repeated across three sections ("Do not rely on memorized values", "Fetch the schema to get current job types", "fetch the schema and derive the answer"), which could be consolidated.

4 / 5

Actionability

Commands are concrete in form ("node {baseDir}/scripts/fetch.js <url>", "npm install --prefix {baseDir}/scripts", "node {baseDir}/scripts/validate.js <workflow.yml>") but the referenced scripts/fetch.js and scripts/validate.js do not exist in the bundle (no scripts/ directory is present), so the primary fetch and validate commands cannot actually execute — a larger gap than the "minor gaps" of the 4 anchor. It is not 2 because the URL list, file locations, structure overview, and generation checklist are specific and directly usable.

3 / 5

Workflow Clarity

There is a clear sequence — fetch schema, generate via a 5-step checklist (validate required fields, verify job references, check expressions), then validate with an explicit command and "Fix any reported errors before considering the workflow complete". It is not 5 because re-validation after fixes is implied rather than an explicit fix-and-rerun step, and the checkpoint depends on the missing validate.js; not 3 because the validation step is explicit with a command, not merely implicit.

4 / 5

Progressive Disclosure

The body is a well-sectioned overview pointing to external URLs instead of inlining bulky content, but its in-bundle file references (scripts/fetch.js, scripts/validate.js, scripts/node_modules) point to files absent from the bundle, leaving navigation to those resources broken. It is not 4 because broken referenced paths are more than a minor organization gap, and not 2 because the body itself is clearly structured with well-signaled one-level references.

3 / 5

Total

14

/

20

Passed

Description

86%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 description: explicit what and when, comprehensive natural trigger terms including the .eas/workflows/ path pattern, and a clearly distinct Expo/EAS niche. The only weaknesses are the thin action list (just understand/write) and slight overlap risk with generic CI/CD tooling questions in an Expo context.

DimensionReasoningScore

Specificity

"Helps understand and write EAS workflow YAML files for Expo projects" names the domain precisely and exactly two actions ("understand", "write"), matching the anchor for 1-2 concrete actions without comprehensive coverage. It is not 4 because it does not list several distinct concrete actions (e.g., validate, debug, migrate), and not 2 because the domain and actions are specific rather than generic.

3 / 5

Completeness

It explicitly answers both questions: what ("Helps understand and write EAS workflow YAML files for Expo projects") and when ("Use this skill when the user asks about CI/CD or workflows in an Expo or EAS context, mentions .eas/workflows/, or wants help with EAS build pipelines or deployment automation"), mirroring the top anchor's what-plus-concrete-trigger-phrases pattern. Neither neighbor anchor fits better.

5 / 5

Trigger Term Quality

The description covers natural trigger terms comprehensively: "CI/CD", "workflows", "Expo", "EAS", ".eas/workflows/", "EAS build pipelines", and "deployment automation", including a concrete path pattern users would mention. It is not 4 because both synonyms and a file-path-style trigger are present, leaving no commonly used variation missing.

5 / 5

Distinctiveness Conflict Risk

The Expo/EAS niche is distinct and the ".eas/workflows/" trigger is unambiguous, but "CI/CD or workflows in an Expo or EAS context" could also match a user asking about generic CI/CD (e.g., GitHub Actions) for an Expo project, a minor overlap with closely related CI/CD skills. It is not 5 because of that residual ambiguity, and not 3 because triggers are gated on Expo/EAS context so overlap risk is small.

4 / 5

Total

17

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/expo-cicd-workflows/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.