deepgram-sdk-patterns
Apply production-ready Deepgram SDK patterns for TypeScript and Python. Use when implementing Deepgram integrations, refactoring SDK usage, or establishing team coding standards for Deepgram. Trigger: "deepgram SDK patterns", "deepgram best practices", "deepgram code patterns", "idiomatic deepgram", "deepgram typescript".
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/deepgram-pack/skills/deepgram-sdk-patterns/SKILL.mdQuality
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 capabilities described are somewhat abstract — it mentions 'production-ready patterns' and 'integrations' without specifying concrete actions like transcription setup, WebSocket handling, or API configuration. The explicit trigger term list is a nice touch that aids skill selection.
Suggestions
Add more specific concrete actions, e.g., 'configure streaming/batch transcription, handle WebSocket connections, set up authentication, manage callbacks' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Deepgram SDK) and mentions some actions ('implementing integrations', 'refactoring SDK usage', 'establishing team coding standards'), but doesn't list concrete specific actions like 'configure streaming transcription', 'handle WebSocket connections', or 'set up authentication'. The actions remain somewhat abstract. | 2 / 3 |
Completeness | Clearly answers both 'what' (apply production-ready Deepgram SDK patterns for TypeScript and Python) and 'when' (implementing integrations, refactoring SDK usage, establishing coding standards) with explicit trigger terms listed separately. | 3 / 3 |
Trigger Term Quality | Includes explicit trigger terms that users would naturally say: 'deepgram SDK patterns', 'deepgram best practices', 'deepgram code patterns', 'idiomatic deepgram', 'deepgram typescript'. Also mentions Python and TypeScript as languages. Good coverage of natural search terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — Deepgram is a specific product/SDK, and the description is narrowly scoped to Deepgram SDK patterns in TypeScript and Python. Very unlikely to conflict with other skills unless there are multiple Deepgram-related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%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, actionable skill with production-ready code examples covering multiple Deepgram use cases across TypeScript and Python. Its main weaknesses are that it's too long for a single SKILL.md—several sections (Python patterns, typed helpers, migration notes) should be split into referenced files—and the 'steps' are really independent patterns without validation checkpoints between them. The error handling table is a nice touch but would benefit from being integrated into the workflow.
Suggestions
Split Python patterns, typed response helpers, and v5 migration notes into separate referenced files (e.g., PYTHON_PATTERNS.md, MIGRATION_V5.md) to keep SKILL.md as a lean overview with quick-start examples.
Add validation checkpoints: after creating the singleton client, verify connectivity (e.g., a health check call); after TTS, verify the output file is non-empty and playable; after transcription, check that the result has content.
Trim the Aura voice options comment block to just the model used in the example, with a link to the TTS Voices docs for the full list.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly efficient but includes some unnecessary verbosity—the voice options comment block, the full Python mimetype helper, and the typed response helpers section add bulk that could be trimmed or moved to a reference file. Some inline comments explain things Claude already knows. | 2 / 3 |
Actionability | All code examples are fully executable, copy-paste ready TypeScript and Python with concrete imports, real API calls, specific model names, and complete function implementations. The error handling table provides specific solutions for specific errors. | 3 / 3 |
Workflow Clarity | The steps are numbered but represent independent patterns rather than a sequential workflow. There are no validation checkpoints between steps—no guidance on verifying the client works, testing TTS output quality, or confirming transcription results before proceeding. The error handling table partially compensates but is disconnected from the workflow. | 2 / 3 |
Progressive Disclosure | The skill has a Resources section with external links and a Next Steps pointer, but the main content is a long monolithic file (~200 lines of code). The Python patterns, typed helpers, and v5 migration notes could be split into separate reference files to keep the SKILL.md as a concise overview. | 2 / 3 |
Total | 9 / 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.