deepgram-python-text-intelligence
Use when writing or reviewing Python code in this repo that calls Deepgram Text Intelligence / Read (`/v1/read`) for sentiment, summarization, topic detection, and intent recognition on text input. Covers `client.read.v1.text.analyze(...)` with body `text` or `url`. Use `deepgram-python-audio-intelligence` when the source is audio instead of text. Triggers include "read API", "text intelligence", "analyze text", "sentiment", "summarize text", "topics", "intents", "read.v1".
75
92%
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 an excellent skill description that is specific, well-triggered, complete, and distinctive. It names concrete capabilities, provides an explicit 'Use when' clause with natural trigger terms, specifies the exact API and SDK method, and even disambiguates from a related skill for audio input. It serves as a strong example of a high-quality skill description.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: sentiment analysis, summarization, topic detection, intent recognition, and specifies the exact API endpoint (`/v1/read`) and method (`client.read.v1.text.analyze(...)` with `text` or `url` body). | 3 / 3 |
Completeness | Clearly answers both 'what' (calls Deepgram Text Intelligence/Read for sentiment, summarization, topic detection, intent recognition) and 'when' (explicit 'Use when' clause at the start, plus explicit trigger terms listed). Also includes a disambiguation clause pointing to a sibling skill for audio sources. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'read API', 'text intelligence', 'analyze text', 'sentiment', 'summarize text', 'topics', 'intents', 'read.v1'. These are terms a developer would naturally use when working with this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive: scoped to a specific API (`/v1/read`), a specific SDK method, and text-only input. Explicitly disambiguates from the audio intelligence skill (`deepgram-python-audio-intelligence`), minimizing conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, actionable skill with executable code examples, a clear parameters table, and good progressive disclosure to external references. Its main weakness is redundancy around the `summarize` boolean-only constraint, which is stated three separate times across different sections, consuming unnecessary tokens. Overall it's a strong skill that effectively teaches the Deepgram Read API usage pattern.
Suggestions
Consolidate the `summarize` boolean-only explanation into a single location (the Gotchas section) and reference it briefly elsewhere, rather than repeating the full explanation three times.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some redundancy — the `summarize` boolean-only gotcha is explained three times (in the parameters table, gotchas section, and inline comment in quick start). The 'When to use this product' section and the central product skills section add moderate overhead. Some explanations could be tightened. | 2 / 3 |
Actionability | Provides fully executable, copy-paste-ready code for both sync and async usage, a complete parameters table, concrete response access patterns, and specific file references. The quick start example is immediately runnable. | 3 / 3 |
Workflow Clarity | This is a single-shot REST API call skill — there's no multi-step destructive workflow requiring validation checkpoints. The single action is unambiguous: authenticate, call analyze, read response fields. The gotchas section effectively serves as a pre-flight checklist for common pitfalls. | 3 / 3 |
Progressive Disclosure | Clear layered structure: quick start up front, then async variant, parameters table, response shape, and a well-organized 'API reference (layered)' section pointing to reference.md, OpenAPI spec, Context7, and product docs — all one level deep with clear signals. Example files are referenced for deeper exploration. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- deepgram/deepgram-python-sdk
- Commit
e169f63
- 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.