deepgram-ci-integration

Configure Deepgram CI/CD integration for automated testing and deployment. Use when setting up continuous integration pipelines, automated testing, or deployment workflows for Deepgram integrations. Trigger: "deepgram CI", "deepgram CD", "deepgram pipeline", "deepgram github actions", "deepgram automated testing".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

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 and clearly sequenced with real validation gates, but it is verbose: it inlines large complete files that duplicate the bundled references/implementation.md, and it never points to that reference file, leaving the progressive-disclosure structure underused.

Suggestions

Link references/implementation.md from the body (e.g., a '## Advanced / alternate setups' section pointing to it) so the bundle is discoverable rather than orphaned.

Move the full integration test suite and smoke-test script into the reference, keeping only a concise Quick-start snippet inline to reduce token weight and eliminate duplication.

Add a post-rotation verification step to the key-rotation workflow (e.g., a quick API call with the new key) since replacing a production secret is a destructive operation.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable code with little explanatory fluff, but it inlines large full files (a 6-case integration suite, a full smoke-test script, multiple workflows) that overlap heavily with the bundled references/implementation.md, so it could be tightened and is not fully token-efficient.	2 / 3
Actionability	Every step ships complete, copy-paste-ready artifacts — GitHub Actions YAML, a TypeScript integration suite, a smoke-test script, package.json scripts, and vitest config — matching the score-3 anchor for fully executable guidance.	3 / 3
Workflow Clarity	Steps 1–6 are clearly sequenced and the CI pipeline enforces explicit validation gates via job `needs:` dependencies and non-zero smoke-test exit codes, with an Error Handling table providing feedback for recovery.	3 / 3
Progressive Disclosure	A bundle file (references/implementation.md) exists but is never linked or signaled from the body, and content that belongs in that reference is instead inlined, so structure is present but the reference is orphaned and content is not appropriately split.	2 / 3
	Total	10 / 12 Passed

Description

90%

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-formed: it states a concrete purpose, includes an explicit 'Use when' trigger clause, and uses Deepgram-specific trigger phrases that keep it distinct from generic CI/CD skills. The only weakness is that the capability list is somewhat high-level rather than a rich enumeration of concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('Deepgram CI/CD integration') and a couple of actions ('automated testing and deployment'), but does not enumerate multiple concrete actions the way the score-3 anchor does, so it stops at 'domain and some actions'.	2 / 3
Completeness	It answers both 'what' (Configure Deepgram CI/CD integration for automated testing and deployment) and 'when' via an explicit 'Use when setting up continuous integration pipelines...' clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	An explicit Trigger clause lists natural phrases a user would say — 'deepgram CI', 'deepgram CD', 'deepgram pipeline', 'deepgram github actions', 'deepgram automated testing' — giving good coverage of likely utterances.	3 / 3
Distinctiveness Conflict Risk	The Deepgram-specific scope and branded trigger terms carve a clear niche unlikely to fire for unrelated CI/CD skills, satisfying the score-3 anchor.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 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
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	13 / 16 Passed

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

Reviewed: 5 days 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.