deepgram-hello-world
Create a minimal working Deepgram transcription example. Use when starting a new Deepgram integration, testing your setup, or learning basic Deepgram API patterns. Trigger: "deepgram hello world", "deepgram example", "deepgram quick start", "simple transcription", "transcribe audio".
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/deepgram-pack/skills/deepgram-hello-world/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 description with explicit 'Use when' and 'Trigger' clauses, providing clear guidance for skill selection. Its main weakness is that the capability description is somewhat thin — it describes creating an example but doesn't enumerate the specific actions or components involved. The trigger terms are well-chosen and cover natural user language.
Suggestions
Add more specific concrete actions to the capability description, e.g., 'Sets up API authentication, sends audio to Deepgram's speech-to-text endpoint, and parses the JSON transcript response.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Deepgram transcription) and one action (create a minimal working example), but doesn't list multiple concrete actions like 'configure API keys, send audio to endpoint, parse transcript response'. | 2 / 3 |
Completeness | Clearly answers both what ('Create a minimal working Deepgram transcription example') and when ('Use when starting a new Deepgram integration, testing your setup, or learning basic Deepgram API patterns') with explicit trigger terms. | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger terms users would say: 'deepgram hello world', 'deepgram example', 'deepgram quick start', 'simple transcription', 'transcribe audio'. Good coverage of variations. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche — Deepgram transcription quickstart examples. The 'simple transcription' and 'transcribe audio' triggers could overlap with other transcription skills, but the Deepgram-specific terms make it clearly distinguishable. | 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, highly actionable skill with excellent executable code examples and good error handling coverage. However, it tries to do too much for a 'hello world' skill — including Python equivalents, feature additions, and model comparison tables that expand it well beyond minimal. The step numbering implies a sequential workflow but the content is really a collection of independent examples.
Suggestions
Trim to a true 'hello world' by keeping only Step 1 (URL transcription) and Step 6 (run it) inline, moving Python equivalents, local file transcription, features, and model options to referenced files.
Restructure the numbered steps — either make them a true sequential workflow or use section headers without step numbering since these are independent examples.
Move the model options table and feature additions to a separate reference file (e.g., MODELS.md or FEATURES.md) and link from the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary bulk — the Python equivalent section adds significant length for what is essentially a 'hello world' skill, and the model options table and features section expand scope beyond minimal. The error handling table and resources are useful but push this beyond lean. | 2 / 3 |
Actionability | All code examples are fully executable and copy-paste ready with real URLs, proper imports, and complete function bodies. The run commands are specific, and error handling provides concrete solutions for each error type. | 3 / 3 |
Workflow Clarity | Steps are labeled sequentially but they aren't really a workflow — they're independent examples (URL transcription, local file, Python, features, models). There's no validation checkpoint between steps, and the 'steps' framing is misleading since each is a standalone example rather than a sequential process. | 2 / 3 |
Progressive Disclosure | The skill references next steps and external resources, but inlines a lot of content that could be split out (Python equivalent, feature additions, model comparison table). The core hello world could be much shorter with advanced features and Python examples linked to separate files. | 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.