deepgram-migration-deep-dive
Deep dive into migrating to Deepgram from other transcription providers. Use when migrating from AWS Transcribe, Google Cloud STT, Azure Speech, OpenAI Whisper, AssemblyAI, or Rev.ai to Deepgram. Trigger: "deepgram migration", "switch to deepgram", "migrate transcription", "deepgram from AWS", "deepgram from Google", "replace whisper with deepgram".
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.
The description excels at trigger term coverage and completeness, with explicit 'Use when' and 'Trigger' clauses that enumerate specific providers and natural user phrases. Its main weakness is the vagueness of the actual capabilities — 'deep dive into migrating' doesn't convey specific actions the skill performs. Adding concrete actions like mapping API parameters, converting code snippets, or comparing feature parity would strengthen it.
Suggestions
Replace 'Deep dive into migrating' with specific concrete actions, e.g., 'Maps API parameters, converts request/response formats, and provides code migration examples for switching to Deepgram from other transcription providers.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (migrating to Deepgram from other transcription providers) and lists specific source providers, but the actual actions are vague — 'deep dive into migrating' doesn't describe concrete actions like 'maps API parameters', 'converts configuration files', or 'provides code migration examples'. | 2 / 3 |
Completeness | Clearly answers both 'what' (migrating to Deepgram from other transcription providers) and 'when' (explicit 'Use when' clause listing specific providers, plus a 'Trigger' section with natural phrases). Both components are explicitly stated. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including explicit phrases like 'deepgram migration', 'switch to deepgram', 'migrate transcription', and provider-specific variations like 'deepgram from AWS', 'replace whisper with deepgram'. These closely match what users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the combination of Deepgram as the target platform plus specific competing providers creates a very clear niche that is unlikely to conflict with other skills. The trigger terms are uniquely tied to this migration scenario. | 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 highly actionable migration skill with excellent feature mapping tables and complete, executable code. The workflow is well-structured with clear phases, validation checkpoints, and rollback mechanisms. However, the skill is overly long for a SKILL.md file — the full adapter implementations should be referenced rather than inlined, and some code (like the AWS legacy adapter) adds significant bulk that could be summarized or linked.
Suggestions
Move full adapter implementations to separate referenced files (e.g., adapters/deepgram.ts, adapters/aws.ts) and keep only the interface and a brief usage example in SKILL.md
Trim the AWS legacy adapter code — Claude can generate polling logic from a brief description; focus the inline code on the Deepgram-specific parts that are novel
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The feature mapping tables are efficient and valuable, but the full adapter implementations (especially the AWS legacy adapter and validation function) are quite verbose. The migration router code could be more concise since Claude can infer boilerplate patterns. The overall length (~250 lines of code) is heavy for a skill file. | 2 / 3 |
Actionability | Excellent actionability — fully executable TypeScript code with complete adapter implementations, a working migration router, and a concrete validation function with Jaccard similarity. The feature mapping tables provide specific parameter-to-parameter translations that are immediately usable. | 3 / 3 |
Workflow Clarity | Clear 6-step sequential workflow from adapter pattern setup through validation, with explicit validation checkpoints (Step 5 parallel running with similarity thresholds), rollback mechanism (setDeepgramPercent(0)), and a phased rollout checklist with durations. The feedback loop of validate -> fix -> re-validate is implicit but the quality gate (minSimilarity) is explicit. | 3 / 3 |
Progressive Disclosure | The content is largely monolithic — all adapter implementations are inline rather than referenced from separate files. The feature mapping tables, full code implementations, and migration checklist could benefit from being split into referenced documents. The Resources section at the end provides external links but internal progressive disclosure is lacking. | 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.