CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

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

92%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.

An efficient, highly actionable skill body anchored by a runnable quick-start example and well-signaled one-level-deep references. The only minor slack is a slightly verbose 'When to use' section and full boilerplate in the example that could be trimmed.

DimensionReasoningScore

Conciseness

Lean, sectioned body that assumes competence (no preamble on what Go/Deepgram/summarization are); not a 5 because the full main()/log.Fatal wrapper and the lightly redundant 'When to use' list (which echoes the description) could be trimmed.

4 / 5

Actionability

Provides a complete, copy-paste-runnable Go example (imports, NewWithDefaults, FromStream, AnalyzeOptions, response handling) plus a concrete env-var command and exact helper/constructor signatures covering the common case.

5 / 5

Workflow Clarity

Single-purpose skill whose quick start gives an unambiguous sequence (set key -> construct client -> call helper -> read response); the Gotchas section surfaces real failure modes, and no destructive/batch operation triggers the cap-3 rule.

5 / 5

Progressive Disclosure

Well-organized sections with one-level-deep navigation (layered API reference list pointing to README/docs.go/source/OpenAPI/product docs, and a pointer to deepgram/skills for cross-language knowledge) instead of inlining everything; no bundle files exist, and the structure is clean.

5 / 5

Total

19

/

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, well-scoped description that states a concrete capability, opens with an explicit 'Use when' trigger, and actively disambiguates from sibling skills via routing guidance. Its only weakness is product-domain natural-language synonyms (summarization, sentiment, text analysis) that a user might say.

Suggestions

Weave in natural product-domain trigger terms a user would say, e.g. 'Use when summarizing text or running sentiment analysis on plain text from Go'.

Name the concrete analysis actions (summarization, sentiment) in the description so the 'what' is comprehensive, not just routing.

Keep the explicit routing to sibling skills — that distinctiveness guidance is the description's strongest asset.

DimensionReasoningScore

Specificity

Names the domain (Go + Deepgram text/Read) and several concrete routing actions ('writing or reviewing Go code', 'sends text to Deepgram Read via the analyze client', 'Route speech/audio inputs'), with minor gaps since it does not enumerate the analysis actions themselves (summarize/sentiment).

4 / 5

Completeness

Explicitly answers both what ('sends text to Deepgram Read via the analyze client') and when ('Use when writing or reviewing Go code in this repo...') with concrete trigger phrases, matching the top anchor rather than the weaker 'when' of a 4.

5 / 5

Trigger Term Quality

Includes a 'Use when...' clause and natural terms ('writing or reviewing Go code', 'speech/audio inputs', 'Deepgram Read'), with good coverage; not a 5 because natural product-domain synonyms a user would say ('text analysis', 'summarization', 'sentiment') are absent.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche (text/Read only) and explicitly routes away to three sibling skills (speech-to-text, audio-intelligence, management-api), giving distinct triggers with minimal conflict risk.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
deepgram/deepgram-go-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.