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".
77
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/deepgram-pack/skills/deepgram-deploy-integration/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured skill description with strong trigger terms and clear 'what/when' guidance. Its main weakness is that the capability description could be more specific about the concrete actions performed (e.g., generating Dockerfiles, configuring environment variables, writing deployment manifests). Overall it would serve well for skill selection among many options.
Suggestions
Add more specific concrete actions such as 'generates Dockerfiles, writes Kubernetes manifests, configures environment variables, sets up health checks' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Deepgram deployment) and mentions some actions like deploying to cloud platforms, configuring containers, and setting up in Docker/Kubernetes/serverless, but doesn't list multiple concrete granular actions (e.g., writing Dockerfiles, configuring environment variables, setting up health checks). | 2 / 3 |
Completeness | Clearly answers both 'what' (deploy Deepgram integrations to production environments) and 'when' (deploying to cloud platforms, configuring containers, Docker/Kubernetes/serverless) with explicit trigger terms listed. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'deploy deepgram', 'deepgram docker', 'deepgram kubernetes', 'deepgram cloud run', 'deepgram lambda', and 'deepgram production deploy' — these are terms users would naturally use when seeking deployment help for Deepgram. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the combination of 'Deepgram' with specific deployment contexts (Docker, Kubernetes, serverless, Cloud Run, Lambda) creates a clear niche that is unlikely to conflict with other skills, whether general deployment skills or other Deepgram skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability with complete, production-ready code for multiple deployment targets. However, it suffers from being a monolithic wall of deployment configurations that would benefit greatly from being split into separate files (e.g., k8s/, lambda/, cloudrun/). The workflow lacks explicit validation checkpoints between build and deploy steps, and the sheer volume of inline code hurts token efficiency.
Suggestions
Split deployment targets into separate referenced files (e.g., DOCKER.md, K8S.md, LAMBDA.md, CLOUD_RUN.md) with SKILL.md serving as a concise overview and router.
Add explicit validation steps between building and deploying: e.g., 'Run container locally and verify /health endpoint responds before pushing to registry.'
Remove the Resources section with generic external links—Claude already knows where Docker and K8s docs are.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~300 lines) covering 5 deployment targets. While each section is individually lean, the breadth creates a large token footprint. Some content (Docker Compose redis service, the Resources section with basic links) adds marginal value. However, there's minimal explanatory fluff—most tokens are in executable code. | 2 / 3 |
Actionability | Every section provides complete, copy-paste-ready code: a full multi-stage Dockerfile, complete K8s manifests with HPA, a working Lambda handler, a Cloud Run server with deploy command, and a deploy script. All code is executable, not pseudocode, with specific commands and configurations. | 3 / 3 |
Workflow Clarity | Steps are numbered and sequenced, and the deploy script includes a post-deploy smoke test. However, there's no explicit validation checkpoint between building the container and deploying it (e.g., running the container locally first, verifying the image works). The steps read more like independent deployment options than a sequential workflow with feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | All content is monolithically inlined in a single file with no bundle files. The Dockerfile, Docker Compose, K8s manifests, Lambda handler, Cloud Run server, and deploy script should each be separate referenced files. The Resources section links to external docs but doesn't organize the skill's own content across files. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.