deepgram-install-auth

Install and configure Deepgram SDK authentication. Use when setting up a new Deepgram integration, configuring API keys, or initializing Deepgram in your project. Trigger: "install deepgram", "setup deepgram", "deepgram auth", "configure deepgram API key", "deepgram credentials".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The body is highly actionable with executable code, a clear step sequence, and a verification step, but it is somewhat verbose and monolithic — all material is inline with no progressive disclosure to reference files. Tightening the Overview and splitting peripheral detail would raise both conciseness and progressive disclosure.

Suggestions

Trim the Overview's product-capability list (Nova-3/Nova-2/Aura-2/audio intelligence) to only what is needed for install/auth, and drop or condense one of the two full verify examples in Step 5.

Move the API Key Scopes table, Error Handling table, and Step 6 singleton pattern into a reference file (e.g. references/advanced.md) and link to it from SKILL.md to improve progressive disclosure.

Re-scope Step 6 (production singleton) out of the core install/auth flow, or label it explicitly as optional/advanced so the primary workflow stays lean.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete steps, but includes tightening opportunities: the Overview lists product capabilities (Nova-3/Nova-2/Aura-2/audio intelligence) tangential to install/auth, Step 5 duplicates full verify examples in both TS and Python, and the Step 6 singleton pattern exceeds the install/auth scope.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands and code (npm/pip install, env-var setup, TS/Python client init, verify functions) plus a concrete error-to-solution table.	3 / 3
Workflow Clarity	Steps 1–6 are clearly sequenced with an explicit verification checkpoint (Step 5) and an Error Handling table mapping failures to fixes, giving a usable validate-and-recover loop.	3 / 3
Progressive Disclosure	Well-sectioned but entirely self-contained with no bundle files and no one-level-deep references; content such as the scopes table, error handling, and singleton pattern is inline rather than split into supporting files.	2 / 3
	Total	10 / 12 Passed

Description

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.

The description is well-constructed: it states concrete capabilities, provides an explicit 'Use when' clause, and lists natural trigger phrases scoped to a distinct Deepgram-auth niche. No vague fluff or over-claims are present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Install and configure Deepgram SDK authentication', 'configuring API keys', 'initializing Deepgram in your project' — matching the anchor for several specific concrete actions.	3 / 3
Completeness	Clearly states what ('Install and configure Deepgram SDK authentication') and when ('Use when setting up a new Deepgram integration...') with explicit trigger guidance, satisfying both requirements.	3 / 3
Trigger Term Quality	Explicit trigger phrases ('install deepgram', 'setup deepgram', 'deepgram auth', 'configure deepgram API key', 'deepgram credentials') are natural terms a user would actually say, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	Scoped to a clear Deepgram-specific niche with distinct triggers, making it unlikely to activate for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 02d6341

Reviewed: about 1 hour ago

Table of Contents

Discovery Implementation Validation

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.