apollo-ci-integration
Configure Apollo.io CI/CD integration. Use when setting up automated testing, continuous integration, or deployment pipelines for Apollo integrations. Trigger with phrases like "apollo ci", "apollo github actions", "apollo pipeline", "apollo ci/cd", "apollo automated tests".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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 description that clearly defines its niche (Apollo.io CI/CD) and provides explicit trigger terms and use-when guidance. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., schema checks, rover CLI setup, GitHub Actions configuration). Overall it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions like 'configure GitHub Actions for schema checks', 'set up rover CLI in pipelines', or 'add Apollo schema validation steps' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Apollo.io CI/CD integration) and mentions some actions (automated testing, continuous integration, deployment pipelines), but doesn't list specific concrete actions like 'configure GitHub Actions workflows', 'set up schema checks', or 'add deployment steps'. The actions remain somewhat high-level. | 2 / 3 |
Completeness | Clearly answers both 'what' (configure Apollo.io CI/CD integration) and 'when' (setting up automated testing, CI, or deployment pipelines for Apollo integrations), with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger phrases like 'apollo ci', 'apollo github actions', 'apollo pipeline', 'apollo ci/cd', 'apollo automated tests'. These are terms users would naturally say when needing this skill, and the coverage of variations is good. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'Apollo.io' with 'CI/CD' creates a very specific niche. The trigger terms are all Apollo-prefixed, making it unlikely to conflict with generic CI/CD skills or other Apollo-unrelated skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with complete, executable code and a well-sequenced workflow including validation steps and error recovery guidance. Its main weakness is token efficiency — the full test files and workflow YAML are quite long and could be referenced rather than inlined, as Claude could generate much of this boilerplate from a more concise specification. The error handling table and gating strategy are excellent additions.
Suggestions
Move the full MSW test file and integration test file to separate referenced files (e.g., APOLLO_TESTS.md) and keep only a brief example or key patterns inline in SKILL.md.
Trim the GitHub Actions YAML to show only the novel/Apollo-specific parts (health check, secret scan, gating logic) rather than the full boilerplate workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some verbosity — the full MSW test file and integration test file are quite long and could be trimmed. The overview and error handling table are well-written, but the sheer volume of code (much of which is boilerplate Claude could generate) inflates the token cost. | 2 / 3 |
Actionability | Fully executable code throughout: complete GitHub Actions YAML, working MSW test setup, live integration tests, and concrete CLI commands for secret management. Everything is copy-paste ready with real endpoints and realistic mock data. | 3 / 3 |
Workflow Clarity | Clear 4-step sequence with explicit validation checkpoints: health check before integration tests, secret scanning as a separate job, MSW mocks for safe PR testing, and integration tests gated to main branch only. The error handling table provides a feedback loop for common failure modes. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a resources section with external links, plus a 'Next Steps' pointer. However, the lengthy code examples (especially the full test files) could be split into referenced files rather than inlined, making the SKILL.md more of an overview. | 2 / 3 |
Total | 10 / 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 | |
- Commit
70e9fa4
- 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.