deepgram-security-basics

Apply Deepgram security best practices for API key management and data protection. Use when securing Deepgram integrations, implementing key rotation, or auditing security configurations. Trigger: "deepgram security", "deepgram API key security", "secure deepgram", "deepgram key rotation", "deepgram data protection", "deepgram PII redaction".

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-3

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 well-sequenced, validated workflows, but it is hurt by duplication against an orphaned reference file that is never linked from the SKILL.md. Linking implementation.md and trimming the duplicated inline detail would resolve the weakest dimensions.

Suggestions

Link references/implementation.md from the body (e.g., a '## Implementation details' section pointing to it) and move the duplicated rotation/SSRF/audit/scoped-key code out of SKILL.md into that reference, keeping only an overview inline.

Remove or compress the Output section, which restates capabilities already shown by the code examples, to improve token efficiency.

In the Resources section, surface implementation.md alongside the external links so the bundle is discoverable.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, executable code rather than concept explanations, but it duplicates material also present in references/implementation.md (rotation, SSRF validation, audit logging, scoped keys) and the Output section restates what the code already shows, so it could be tightened.	2 / 3
Actionability	Each step ships complete, executable TypeScript using the real @deepgram/sdk calls (scoped keys, redact option, temporary keys, rotation, URL validation, audit logging) plus a concrete error-handling table — copy-paste ready guidance.	3 / 3
Workflow Clarity	Steps 1–6 are clearly sequenced, the destructive key-rotation step has an explicit validate-then-abort checkpoint ("if (error) throw new Error('New key validation failed — aborting rotation')"), and the SSRF step validates URLs before transcription, with an overlap-period recovery note in the error table.	3 / 3
Progressive Disclosure	A bundle file references/implementation.md exists but is never linked or signaled from the body, and the detailed material it contains is instead duplicated inline rather than split out, matching the anchor for references present but not clearly signaled with content that should be separate kept inline.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 concise, third-person, and clearly answers both what the skill does and when to use it, with a strong explicit trigger list scoped to Deepgram. No significant weaknesses to address.

Dimension	Reasoning	Score
Specificity	Names concrete actions in the Deepgram security domain — "API key management and data protection", "securing Deepgram integrations, implementing key rotation, or auditing security configurations" — matching the anchor for listing multiple specific actions.	3 / 3
Completeness	It states what ("Apply Deepgram security best practices for API key management and data protection") and when ("Use when securing Deepgram integrations, implementing key rotation, or auditing security configurations") plus explicit trigger terms, clearly answering both what and when.	3 / 3
Trigger Term Quality	An explicit Trigger clause lists natural phrases a user would say ("deepgram security", "deepgram API key security", "secure deepgram", "deepgram key rotation", "deepgram data protection", "deepgram PII redaction"), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Every trigger and the description are scoped to Deepgram specifically, giving it a clear niche unlikely to fire 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
Path: plugins/saas-packs/deepgram-pack/skills/deepgram-security-basics/SKILL.md
Commit: 0540a62

Reviewed: about 19 hours 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.