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".
82
80%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/deepgram-pack/skills/deepgram-ci-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 completeness and distinctiveness. It clearly identifies both what the skill does and when to use it, with explicit trigger terms. The main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., generating pipeline configs, setting up test suites, configuring deployment scripts).
Suggestions
Add more specific concrete actions to the capability description, e.g., 'generate GitHub Actions workflows, configure test suites, manage API key secrets, set up deployment scripts' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Deepgram CI/CD integration) and mentions some actions (automated testing, deployment), but doesn't list multiple specific concrete actions like configuring pipeline YAML files, setting up test stages, managing secrets, or defining deployment targets. | 2 / 3 |
Completeness | The description clearly answers both 'what' (configure Deepgram CI/CD integration for automated testing and deployment) and 'when' (setting up CI pipelines, automated testing, or deployment workflows), with explicit trigger terms listed. | 3 / 3 |
Trigger Term Quality | The description includes explicit trigger terms that users would naturally say: 'deepgram CI', 'deepgram CD', 'deepgram pipeline', 'deepgram github actions', 'deepgram automated testing'. These cover common variations of how users would phrase their needs. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'Deepgram' with 'CI/CD' creates a very specific niche. The explicit trigger terms are highly distinctive and unlikely to conflict with general CI/CD skills or general Deepgram skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
70%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 fully executable, well-structured CI/CD code and a clear multi-stage pipeline workflow with proper dependency gates and error handling. However, it suffers from being a monolithic wall of code (~250 lines) that would benefit greatly from splitting into referenced files, and there is notable redundancy between the integration test suite and smoke test script. The referenced `scripts/rotate-key.ts` is missing entirely.
Suggestions
Split the integration test suite, smoke test script, vitest config, and key rotation workflow into separate bundle files, keeping SKILL.md as a concise overview with navigation links to each.
Provide the missing `scripts/rotate-key.ts` that is referenced in the key rotation workflow.
Reduce redundancy between the integration test suite and smoke test — either differentiate their purposes more clearly or consolidate overlapping test logic.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill provides substantial executable code which is valuable, but there's significant redundancy between the integration test suite and the smoke test script (both test authentication, transcription, and TTS with the same sample URL). The overview and prerequisites sections are reasonably lean, but the overall content is quite long and could be tightened by eliminating duplication. | 2 / 3 |
Actionability | Excellent actionability — every step provides fully executable, copy-paste ready code: complete GitHub Actions YAML workflows, TypeScript test suites, vitest configuration, and package.json scripts. The code is concrete, uses real SDK methods, and includes specific model names, URLs, and configuration values. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced with explicit dependency chains (unit-tests → integration-tests → smoke-test via `needs`), validation gates (fork PR detection with the `if` condition to skip integration tests), timeout constraints, and the error handling table serves as a troubleshooting checklist. The pipeline structure itself embodies validation checkpoints. | 3 / 3 |
Progressive Disclosure | All content is inlined in a single monolithic file with no bundle files to support it. The rotate-key script is referenced (`scripts/rotate-key.ts`) but never provided. The integration tests, smoke tests, vitest config, and key rotation workflow could all be separate referenced files, keeping the SKILL.md as a concise overview with navigation pointers. | 1 / 3 |
Total | 9 / 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.