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".
94
92%
Does it follow best practices?
Impact
Pending
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 clearly defines its scope (Deepgram Text Intelligence / Read API for text input), lists specific capabilities (sentiment, summarization, topic detection, intent recognition), provides explicit trigger terms, and proactively disambiguates from a related audio-focused skill. It uses proper third-person voice throughout and is both comprehensive and concise.
| 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 input types (`text` or `url`). | 3 / 3 |
Completeness | Clearly answers both 'what' (calls Deepgram Text Intelligence / Read for sentiment, summarization, topic detection, intent recognition) and 'when' (explicit 'Use when writing or reviewing Python code... that calls Deepgram Text Intelligence'). 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 with a clear niche (Deepgram Read/text intelligence API specifically for text input). Explicitly disambiguates from the audio intelligence skill (`deepgram-python-audio-intelligence`), reducing conflict risk significantly. | 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-crafted skill with strong actionability and good progressive disclosure. The main weakness is the repeated explanation of the `summarize` boolean-only constraint, which appears in the parameters table, gotchas section, and implicitly in the quick start comment — this redundancy consumes tokens without adding clarity. Otherwise, the skill is well-organized, provides executable code, and appropriately layers references.
Suggestions
Consolidate the `summarize` boolean-only explanation into a single location (gotchas) and keep only a brief note in the parameters table, reducing ~100 tokens of repetition.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some verbosity, particularly the lengthy explanation of the `summarize` parameter type alias appearing in both the parameters table and gotchas section (repeated three times total). The 'When to use this product' section and some explanatory notes could be tightened. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready code for both sync and async usage, a complete parameters table with types and notes, concrete response access patterns, and specific example file paths. The quick start example is immediately runnable. | 3 / 3 |
Workflow Clarity | This is a single-shot REST API call skill with no multi-step destructive operations, so complex workflow sequencing isn't needed. The authentication → quick start → response access flow is clear and unambiguous, and gotchas serve as effective validation guidance. | 3 / 3 |
Progressive Disclosure | Well-structured with a clear overview, quick start, then layered API references pointing to `reference.md`, OpenAPI spec, Context7, and product docs — all one level deep. The response shape is appropriately abridged with a pointer to the full reference. Cross-references to related skills (`deepgram-python-audio-intelligence`) are clearly signaled. | 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
16b9839
- 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.