deepgram-upgrade-migration
Plan and execute Deepgram SDK upgrades and model migrations. Use when upgrading SDK versions (v3->v4->v5), migrating models (Nova-2 to Nova-3), or planning API version transitions. Trigger: "upgrade deepgram", "deepgram migration", "update deepgram SDK", "deepgram version upgrade", "nova-3 migration".
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%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-crafted skill description that clearly defines its scope around Deepgram SDK upgrades and model migrations. It excels in all dimensions by providing specific actions, explicit trigger guidance with natural user terms, and a highly distinctive niche. The use of third person voice and structured format with separate 'Use when' and 'Trigger' sections makes it easy for Claude to match appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: SDK upgrades with version paths (v3->v4->v5), model migrations (Nova-2 to Nova-3), and API version transitions. These are clearly defined, actionable tasks. | 3 / 3 |
Completeness | Clearly answers both 'what' (plan and execute Deepgram SDK upgrades and model migrations) and 'when' (explicit 'Use when' clause with specific scenarios plus a dedicated 'Trigger' section with natural language terms). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'upgrade deepgram', 'deepgram migration', 'update deepgram SDK', 'deepgram version upgrade', 'nova-3 migration'. These are terms users would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around Deepgram-specific SDK upgrades and model migrations. The specific product names (Deepgram, Nova-2, Nova-3) and version paths make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 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 migration guide with executable code for every step and a clear workflow including validation and rollback. Its main weakness is length — the inline code examples are comprehensive but could be split into referenced files for better progressive disclosure. Minor verbosity in explanatory comments could be trimmed.
Suggestions
Consider moving the A/B testing script and validation suite into separate referenced files (e.g., AB_TEST.md, VALIDATION.md) to reduce the main skill's token footprint.
Remove explanatory comments that Claude already knows (e.g., 'Nova-3 improvements over Nova-2' bullet list, the Overview paragraph) to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with useful migration maps and code examples, but includes some unnecessary commentary (e.g., Nova-3 improvement bullet points Claude would know, the 'Overview' paragraph restating what the skill does). The A/B testing script and validation suite are quite lengthy and could be more compact. | 2 / 3 |
Actionability | Provides fully executable TypeScript code for every migration path, concrete bash commands for version checking and rollback, a complete vitest validation suite, and a working A/B comparison function. All code is copy-paste ready with real API endpoints and sample URLs. | 3 / 3 |
Workflow Clarity | Clear 6-step sequential workflow from identification through validation to rollback. Includes explicit validation steps (Step 5 test suite), A/B testing before committing (Step 4), and a rollback procedure with verification (Step 6). 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 summary table, but it's quite long (~200 lines of code) and could benefit from splitting the A/B testing script, validation suite, and migration map into separate referenced files. External resources are linked but internal content is monolithic. | 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
c8a915c
- 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.