deepgram-upgrade-migration
Plan and execute Deepgram SDK upgrades and model migrations. Use when upgrading SDK versions (v3 to v4 to 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".
71
88%
Does it follow best practices?
Impact
—
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 strong skill description that clearly defines its scope around Deepgram SDK upgrades and model migrations with specific version references. It includes an explicit 'Use when' clause and a dedicated trigger term list, making it easy for Claude to select appropriately. The description is concise, uses third-person voice, and is highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: SDK upgrades (with version numbers v3/v4/v5), model migrations (Nova-2 to Nova-3), and API version transitions. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (plan and execute Deepgram SDK upgrades and model migrations) and 'when' (explicit 'Use when' clause covering SDK version upgrades, model migrations, and API version transitions). Both are well-articulated with explicit triggers. | 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, and the explicit Trigger list adds strong keyword coverage. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific product (Deepgram) with specific version numbers (v3-v5, Nova-2, Nova-3). Extremely unlikely to conflict with other skills due to the narrow, product-specific niche. | 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 from assessment through rollback. The main weakness is that it's somewhat long for a single SKILL.md file — the validation suite and A/B testing script could be extracted into bundle files for better progressive disclosure. Minor verbosity in model comparison commentary could be trimmed.
Suggestions
Extract the validation test suite (Step 5) and A/B testing script (Step 4) into separate bundle files (e.g., tests/deepgram-validation.test.ts and scripts/compare-models.ts) and reference them from SKILL.md.
Trim the Nova-3 improvement bullet list — Claude doesn't need marketing copy; just state 'Nova-3 is a drop-in replacement: change model parameter only.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of side-by-side code comparisons, but includes some unnecessary commentary (e.g., 'Nova-3 improvements over Nova-2' bullet list with marketing-style claims, and the A/B test similarity calculation is verbose). The version history table and migration map are well-structured, though the overall length (~200 lines) could be tightened. | 2 / 3 |
Actionability | Provides fully executable TypeScript code for every migration path (client creation, STT, TTS, live streaming, error handling), a complete vitest validation suite with real sample URLs, concrete bash commands for version checking and rollback, and a working A/B comparison function. All code is copy-paste ready. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced: identify version → review migration map → migrate model → A/B test → validate with automated tests → rollback if needed. Includes explicit validation (Step 5 test suite), a feedback loop (rollback procedure in Step 6 with re-validation), and the error handling table provides troubleshooting for common failure modes. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a summary table, but it's a monolithic file with no bundle files to offload detailed content. The A/B testing script and validation suite could reasonably be separate referenced files. External resource links are provided but all substantive content is inline, making it quite long for a SKILL.md 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
a04d1a2
- 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.