Use when debugging CI failures, understanding the build pipeline, modifying the GitHub Actions workflow, working with artifact caching, or troubleshooting why a build succeeded locally but fails in CI
88
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
72%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 description excels at trigger term coverage and distinctiveness, providing excellent 'when to use' guidance with natural developer language. However, it's structurally incomplete - it only describes when to use the skill without explaining what the skill actually does or what concrete actions it can perform.
Suggestions
Add a 'what it does' clause before the 'Use when' section, e.g., 'Analyzes GitHub Actions workflow files, diagnoses build failures, optimizes caching strategies, and compares local vs CI environments.'
Include specific concrete actions the skill performs, such as 'reads workflow YAML files', 'parses CI logs', or 'identifies environment differences'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (CI/GitHub Actions) and mentions several activities like 'debugging CI failures', 'modifying the GitHub Actions workflow', and 'working with artifact caching', but doesn't list concrete actions the skill performs (e.g., 'analyzes workflow logs', 'identifies cache misconfigurations'). | 2 / 3 |
Completeness | The description is entirely a 'Use when...' clause answering when to use it, but lacks the 'what does this do' component. It doesn't explain what capabilities or actions the skill provides, only when it should be triggered. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'CI failures', 'build pipeline', 'GitHub Actions', 'artifact caching', 'build succeeded locally but fails in CI' - these are all phrases developers naturally use when seeking help with CI issues. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused specifically on GitHub Actions CI/CD workflows. The specific triggers like 'GitHub Actions workflow', 'artifact caching', and 'build succeeded locally but fails in CI' create a distinct identity unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent CI pipeline skill that provides comprehensive, actionable documentation. The content is highly specific to the project's infrastructure (Blacksmith sticky disks, R2 preseed, GNOME CAS) without wasting tokens on generic CI concepts. The debugging section with symptom/cause/fix tables and a clear debugging workflow makes this immediately useful for troubleshooting.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is dense with project-specific information that Claude wouldn't know. Every table, list, and section provides actionable CI-specific details without explaining basic concepts like what GitHub Actions or containers are. | 3 / 3 |
Actionability | Provides concrete workflow steps, specific commands (`just bst build oci/bluefin.bst`), exact file paths, configuration values with rationale, and a detailed debugging workflow with specific log locations and troubleshooting steps. | 3 / 3 |
Workflow Clarity | The 16-step workflow table clearly sequences the entire CI pipeline with notes on each step. The debugging section provides an explicit 5-step workflow with validation checkpoints ('Check sticky disk mount' -> 'Check preseed status' -> etc.). | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections (Overview, Quick Reference, Workflow Steps, Caching Architecture, Debugging). Cross-references to related skills are clearly signaled at the end with a 'When to use' column for navigation. | 3 / 3 |
Total | 12 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
f062bf8
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.