CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

73

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable SDK skill with copy-paste code, a useful parameters table, and genuinely non-obvious gotchas. The main weakness is the triple repetition of the `summarize` boolean-only caveat plus a promotional 'central skills' block that inflate tokens, and the absence of any bundled reference file despite naming `reference.md`.

Suggestions

State the `summarize` boolean-only caveat once in the Gotchas section and reference it from the quick-start comment and the parameters table instead of repeating the full SDK type-alias/docstring explanation three times.

Remove or shrink the promotional 'Central product skills' / `npx skills add deepgram/skills` block, which does not advance the skill's task.

Either bundle a `reference.md` with the full Read V1 Text response shape and link to it, or relabel the `reference.md` mention as an external repo file so the progressive-disclosure layer is honest about what is in-skill vs. in-repo.

DimensionReasoningScore

Conciseness

Mostly lean and high-signal (tight quick-start, abridged response shape, focused gotchas), but the `summarize` boolean-only gotcha is repeated three times (quick-start comment, the long parameters-table cell quoting the SDK type alias and docstring, and Gotcha #3 verbatim), and the 'Central product skills' block is promotional padding — clear trim opportunities that keep it just below the top anchor.

4 / 5

Actionability

Provides copy-paste-ready executable code for the common case (text input with all analytics on), an async equivalent, the text-vs-url body variants, and a concrete parameters table with types — fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

This is a single-shot REST call skill with no fragile multi-step pipeline, so the simple-skill exception applies; the single action is unambiguous and the gotchas act as explicit pre-flight guardrails (Token auth, English-only, required language, summarize boolean-only), with no destructive/batch operation triggering the validation cap.

5 / 5

Progressive Disclosure

Well-organized sections and the API reference is properly layered (in-repo reference -> OpenAPI -> Context7 -> product docs) rather than inlined, but the skill bundle contains no actual reference files (no references/scripts/assets dirs), so the named `reference.md` is an external repo path, not a resolvable one-level-deep bundled reference the top anchor requires.

4 / 5

Total

18

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states capabilities, gives an explicit 'Use when' trigger with concrete trigger phrases, and actively disambiguates from the sibling audio skill. The only gap is trigger-term breadth — a few natural synonyms and a file extension would push trigger_term_quality to the top anchor.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete actions (sentiment, summarization, topic detection, intent recognition) plus the exact SDK call `client.read.v1.text.analyze(...)` with both `text` and `url` body variants — comprehensive coverage matching the anchor-5 example.

5 / 5

Completeness

Explicitly answers both what (the four analytics via `/v1/read` and the analyze call) and when ("Use when writing or reviewing Python code in this repo that calls...") with concrete trigger phrases, matching the anchor-5 example.

5 / 5

Trigger Term Quality

Includes an explicit trigger list ("read API", "text intelligence", "analyze text", "sentiment", "summarize text", "topics", "intents", "read.v1") with good natural + technical coverage, but a few natural synonyms (e.g., "summarization", "text analysis") and any file extension are missing, fitting the anchor-4 'good coverage, a few terms missing'.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Text Intelligence on text input) and explicitly disambiguates with "Use `deepgram-python-audio-intelligence` when the source is audio instead of text", giving distinct triggers with minimal conflict risk.

5 / 5

Total

19

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
deepgram/deepgram-python-sdk
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.