exa-upgrade-migration
Upgrade exa-js SDK versions and handle breaking changes safely. Use when upgrading the Exa SDK, detecting deprecations, or migrating between exa-js versions. Trigger with phrases like "upgrade exa", "exa update", "exa breaking changes", "update exa-js", "exa new version".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 well-structured skill description with strong trigger terms and clear 'what/when' guidance. Its main weakness is that the capability description could be more specific about the concrete actions performed (e.g., updating imports, rewriting deprecated method calls, updating package.json). The explicit trigger phrase list is a notable strength for skill selection.
Suggestions
Add more specific concrete actions like 'updates import statements, rewrites deprecated API calls, modifies package.json dependencies' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (exa-js SDK upgrades) and some actions ('upgrade versions', 'handle breaking changes'), but doesn't list multiple concrete specific actions like detecting specific deprecation patterns, updating import statements, or migrating specific API calls. | 2 / 3 |
Completeness | Clearly answers both 'what' (upgrade exa-js SDK versions and handle breaking changes) and 'when' (explicit 'Use when...' clause plus 'Trigger with phrases like...' providing concrete trigger guidance). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'upgrade exa', 'exa update', 'exa breaking changes', 'update exa-js', 'exa new version', plus contextual terms like 'deprecations' and 'migrating between exa-js versions'. These are phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting the exa-js SDK specifically. The triggers are highly distinctive ('exa', 'exa-js') and unlikely to conflict with other skills unless there were multiple exa-related 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 solid upgrade skill with strong actionability and workflow clarity — the step-by-step process with validation checkpoints and rollback procedures is well-designed. The main weaknesses are moderate verbosity (especially the verification script and speculative breaking change patterns) and inline content that could be better split across files. The skill effectively handles the destructive/risky nature of upgrades with appropriate feedback loops.
Suggestions
Extract the lengthy Step 3 verification script to a separate file (e.g., `verify-exa-upgrade.ts`) and reference it inline to improve conciseness and progressive disclosure.
Remove speculative breaking change comments in Step 4 ('may be replaced', 'check changelog') — either document known breaking changes with version numbers or remove the section entirely.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The verification script in Step 3 is quite verbose with 4 separate try/catch blocks that could be condensed. Step 4's breaking change patterns are speculative ('may be replaced', 'check changelog') rather than definitive. The overview paragraph explains what the SDK import looks like, which is somewhat redundant given the code examples. | 2 / 3 |
Actionability | Provides fully executable bash commands and TypeScript code at each step. The upgrade verification script is copy-paste ready with concrete API calls, the rollback procedure has specific commands, and the checklist provides clear actionable items. | 3 / 3 |
Workflow Clarity | Clear 5-step sequence with explicit validation at multiple points: npm test after install, a dedicated verification script checking all API methods, a rollback procedure if tests fail, and a comprehensive checklist. The feedback loop (test → fail → rollback → verify) is well-defined. | 3 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections, but the verification script is quite long inline. The reference to 'exa-ci-integration' at the end is good progressive disclosure, but the main content could benefit from extracting the lengthy verification script to a separate file. The error handling table and checklist are well-organized. | 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.