CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deepgram-go-text-intelligence

Use when writing or reviewing Go code in this repo that sends text to Deepgram Read via the analyze client. Route speech/audio inputs to deepgram-go-speech-to-text or deepgram-go-audio-intelligence, and management/admin work to deepgram-go-management-api.

68

Quality

85%

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

75%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 well-built SDK-usage skill: a complete, copy-paste-ready Quick start, concrete authentication, a layered reference trail, and genuinely useful gotchas (the api wrapper vs base client distinction). It is consistently one notch from excellent due to a slightly vague parameter section, unshown FromFile/FromURL variants, and a 'When to use' section that duplicates the frontmatter description.

Suggestions

Replace the vague 'and other Read features exposed by the analyze client' in Key parameters with the actual AnalyzeOptions field names (e.g. Summarize, Sentiment, Topics) so the parameter list is concrete.

Add a one-line FromFile and FromURL example next to the FromStream quick start, since Gotcha 3 says these live on the api wrapper — showing the pattern prevents a likely misuse.

Trim or compress 'When to use this product' — the routing rules already appear verbatim in the frontmatter description, so the body could reduce them to a single line and save tokens.

DimensionReasoningScore

Conciseness

The body is efficient — no padding, no explanation of concepts Claude already knows, and a single complete code example. The 'When to use this product' section repeats the frontmatter's routing guidance almost verbatim, which is a minor instance of content that could be trimmed, keeping it below the 'every token earns its place' anchor.

4 / 5

Actionability

The Quick start is fully executable (imports, client construction, options, error handling) and the auth section gives a concrete command. 'Key parameters' is partly vague ('other Read features exposed by the analyze client') and the FromFile/FromURL helpers are named but not shown, so coverage of common cases has minor gaps.

4 / 5

Workflow Clarity

This is a simple single-purpose API-usage skill with no destructive or batch operations, and the sections run in a logical order (auth → quick start → parameters → gotchas) with error checking modeled in the code. It falls short of a 5 because sequencing and error-recovery guidance are implicit in section order rather than explicitly stated.

4 / 5

Progressive Disclosure

Sections are well organized with a clearly layered, one-level-deep reference list (in-repo files, OpenAPI/AsyncAPI specs, product docs) and pointers to example files and the central skills bundle — no nested references. There are no separate bundle files, and the inline quick start plus API reference list could arguably live in a reference file, so structure is good but not exemplary.

4 / 5

Total

16

/

20

Passed

Description

87%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 description with an explicit 'Use when' trigger, third-person voice, and excellent sibling-skill disambiguation. Its only weakness is that it describes routing rather than the product's concrete capabilities (summarization, sentiment), which slightly limits trigger-term coverage.

DimensionReasoningScore

Specificity

Names several concrete actions — 'writing or reviewing Go code... that sends text to Deepgram Read via the analyze client' plus explicit routing of speech/audio and management/admin work — but stops short of listing the product's actual capabilities (summarization, sentiment), so it fits the 'several specific actions; minor gaps' anchor rather than comprehensive coverage.

4 / 5

Completeness

It opens with an explicit 'Use when writing or reviewing Go code in this repo that sends text to Deepgram Read via the analyze client' trigger and simultaneously states what the skill covers, clearly and explicitly answering both what and when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases like 'Go code', 'speech/audio inputs', and 'management/admin work' map well to what a user would say, and the routing sentence names user-facing scenarios. It misses common synonyms such as 'summarization', 'sentiment', 'text intelligence', or 'analyze text', keeping it below comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (text/Read via the analyze client) and explicitly redirects the adjacent cases to three named sibling skills ('deepgram-go-speech-to-text', 'deepgram-go-audio-intelligence', 'deepgram-go-management-api'), minimizing wrong-skill triggering.

5 / 5

Total

18

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

deepgram/deepgram-go-sdk

Path

.agents/skills/deepgram-go-text-intelligence/SKILL.md

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.