deepgram-deploy-integration

Deploy Deepgram integrations to production environments. Use when deploying to cloud platforms, configuring containers, or setting up Deepgram in Docker/Kubernetes/serverless. Trigger: "deploy deepgram", "deepgram docker", "deepgram kubernetes", "deepgram production deploy", "deepgram cloud run", "deepgram lambda".

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/deepgram-pack/skills/deepgram-deploy-integration/SKILL.md

Quality

Content

65%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.

A highly actionable, code-complete deployment skill, but it is monolithic: it dumps full manifests inline while a duplicate reference file sits unlinked, and only the k8s path carries real validation checkpoints. Splitting detail into the reference and adding post-deploy verification for the serverless paths would materially improve it.

Suggestions

Link references/implementation.md from the body and move the full inline Dockerfile/compose/manifests there, keeping SKILL.md as a concise overview that points to the reference instead of duplicating it.

Add explicit validation/smoke-test checkpoints to the AWS Lambda and Google Cloud Run paths (e.g., invoke the endpoint and assert a 200/healthy status after deploy), mirroring the k8s smoke test.

Add a short decision section at the top of Instructions guiding the user to the right platform path (Docker vs K8s vs Lambda vs Cloud Run) so the six steps read as a sequenced workflow rather than a flat menu.

Dimension	Reasoning	Score
Conciseness	The body inlines ~360 lines of complete config files (Dockerfile, compose, k8s manifests, handlers, deploy script) and a 234-line near-duplicate references/implementation.md exists alongside it, signaling duplication and bloat that could be tightened by offloading detail to the reference.	2 / 3
Actionability	Every step provides fully executable, copy-paste-ready code or commands — a real multi-stage Dockerfile, k8s manifests, a TypeScript Lambda handler, a Cloud Run server, and a working deploy.sh — with concrete commands rather than pseudocode.	3 / 3
Workflow Clarity	The k8s/deploy.sh path is well-sequenced with validation (npm test, rollout status, smoke test), but the Lambda and Cloud Run paths are standalone recipes with no validation or post-deploy verification checkpoint, leaving gaps for a destructive production-deploy skill.	2 / 3
Progressive Disclosure	Sections are organized, but all six deployment recipes are inlined monolithically and the provided references/implementation.md bundle is never linked or signaled from the body, so content that should be split out stays inline with poor navigation.	2 / 3
	Total	9 / 12 Passed

Description

90%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.

A strong, third-person description with an explicit 'Use when' clause and a well-chosen set of natural trigger phrases scoped tightly to Deepgram deployment. The only weakness is that the capability verbs are somewhat generic (deploy/configure/set up) rather than enumerating concrete deployment actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('Deploy Deepgram integrations to production environments') and several platforms ('Docker/Kubernetes/serverless', 'configuring containers'), but the action verbs are limited to deploy/configure/set-up rather than a comprehensive list of concrete actions.	2 / 3
Completeness	It states what the skill does ('Deploy Deepgram integrations to production environments') and explicitly when to use it ('Use when deploying to cloud platforms...') plus a dedicated Trigger list, answering both what and when.	3 / 3
Trigger Term Quality	The explicit Trigger list ('deploy deepgram', 'deepgram docker', 'deepgram kubernetes', 'deepgram production deploy', 'deepgram cloud run', 'deepgram lambda') gives good coverage of natural phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The Deepgram-specific trigger phrases ('deepgram docker', 'deepgram lambda', 'deepgram cloud run') carve a clear niche that is unlikely to conflict with non-Deepgram deployment skills.	3 / 3
	Total	11 / 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-deploy-integration/SKILL.md
Commit: 0540a62

Reviewed: 1 day 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.