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.
89
87%
Does it follow best practices?
Impact
96%
1.26xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description with excellent trigger terms and completeness. The explicit 'Use this skill when...' clause with multiple natural trigger conditions is well done, and the domain is clearly scoped to EAS/Expo workflows. The main weakness is that the 'what' portion could be more specific about the concrete actions beyond 'understand and write'.
Suggestions
Expand the capability list with more specific actions, e.g., 'Helps understand, write, and debug EAS workflow YAML files for Expo projects, including configuring build steps, triggers, environment variables, and deployment targets.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (EAS workflow YAML files for Expo projects) and mentions some actions ('understand and write'), but doesn't list multiple specific concrete actions like validating syntax, adding build steps, configuring triggers, or managing deployment stages. | 2 / 3 |
Completeness | Clearly answers both 'what' (understand and write EAS workflow YAML files for Expo projects) and 'when' (explicit 'Use this skill when...' clause with multiple trigger conditions including CI/CD, workflows, .eas/workflows/ path, build pipelines, deployment automation). | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'CI/CD', 'workflows', 'Expo', 'EAS', '.eas/workflows/', 'build pipelines', 'deployment automation', 'YAML files'. These are terms users would naturally use when seeking help in this domain. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche targeting EAS/Expo workflow YAML files specifically. The combination of 'EAS', 'Expo', '.eas/workflows/', and 'YAML' makes it very unlikely to conflict with generic CI/CD or general YAML editing skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that provides clear, actionable guidance for working with EAS workflow files. Its strongest aspects are the concrete validation workflow with feedback loops and the progressive disclosure pattern of fetching authoritative external resources rather than inlining them. Minor conciseness improvements could be made by trimming sections that duplicate what the fetched schema already provides (e.g., the Expressions context list).
Suggestions
Remove or significantly trim the 'Expressions' section since the available contexts are already defined in the fetched schema, reducing token usage without losing information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary explanation (e.g., the 'Expressions' section lists contexts Claude could derive from the schema, and some instructions like 'Do not rely on memorized values' are slightly verbose). The content could be tightened by removing information that the fetched schema already provides. | 2 / 3 |
Actionability | Provides concrete, executable commands for fetching resources, validating workflows, and installing dependencies. The fetch and validate scripts are clearly specified with exact command-line syntax, and the workflow generation steps are specific and actionable. | 3 / 3 |
Workflow Clarity | The workflow for generating/editing is clearly sequenced (fetch schema → validate fields → verify references → check expressions → validate constraints), and there's an explicit validation step with a concrete command and instruction to fix errors before considering work complete. This constitutes a proper feedback loop. | 3 / 3 |
Progressive Disclosure | The skill acts as a clear overview that points to external resources (JSON schema, syntax docs, pre-packaged jobs docs) as the source of truth, with a fetch mechanism to retrieve them. Content is well-organized into logical sections without being monolithic, and references are one level deep. | 3 / 3 |
Total | 11 / 12 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 — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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 | 9 / 11 Passed | |
8f26555
Table of Contents
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.