deepgram-prod-checklist
Execute Deepgram production deployment checklist. Use when preparing for production launch, auditing production readiness, or verifying deployment configurations. Trigger: "deepgram production", "deploy deepgram", "deepgram prod checklist", "deepgram go-live", "production ready deepgram".
80
77%
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-prod-checklist/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 solid skill description with excellent trigger terms and clear 'when' guidance. Its main weakness is the lack of specificity about what concrete actions the checklist entails—it says 'execute checklist' but doesn't enumerate what the checklist covers. The Deepgram-specific focus makes it highly distinctive and unlikely to conflict with other skills.
Suggestions
Add 2-3 specific checklist items to improve specificity, e.g., 'Verifies API key configuration, rate limit settings, webhook endpoints, error handling, and logging setup for Deepgram deployments.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Deepgram production deployment) and a general action (execute checklist, audit readiness, verify configurations), but doesn't list specific concrete actions like 'check API key rotation, verify webhook endpoints, validate rate limits'. | 2 / 3 |
Completeness | Clearly answers both 'what' (execute Deepgram production deployment checklist) and 'when' (preparing for production launch, auditing production readiness, verifying deployment configurations) with explicit trigger terms listed. | 3 / 3 |
Trigger Term Quality | Includes explicit trigger terms that users would naturally say: 'deepgram production', 'deploy deepgram', 'deepgram prod checklist', 'deepgram go-live', 'production ready deepgram'. These cover common natural variations well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific product name 'Deepgram' combined with 'production deployment checklist'. Very unlikely to conflict with other skills unless there are multiple Deepgram-related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, highly actionable production checklist with executable code for every major component. Its main weaknesses are verbosity (all code inline in one file) and missing validation checkpoints between deployment steps. The checklist matrix and go-live timeline are strong additions, but the skill would benefit from splitting detailed code into referenced files and adding explicit verification gates.
Suggestions
Add explicit validation checkpoints between steps (e.g., 'Verify health check returns 200 before proceeding' or 'Confirm metrics appear at /metrics endpoint') to improve workflow clarity.
Move the detailed code blocks (Prometheus metrics, alert rules, error wrapper) into separate referenced files and keep only concise summaries in the main SKILL.md to improve progressive disclosure and conciseness.
Remove the Output section, which merely restates what the steps already deliver, to reduce redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~200 lines) with substantial code blocks. While most content is actionable, the overview section restates what the checklist already shows, and the Output section merely summarizes what was already provided in the steps. The production readiness matrix is useful but adds significant length. | 2 / 3 |
Actionability | Every step provides fully executable TypeScript code or complete YAML configuration. The code is copy-paste ready with proper imports, error handling, and realistic patterns like singleton clients, Prometheus metrics, and AlertManager rules. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced, and the go-live timeline provides a phased approach. However, there are no explicit validation checkpoints between steps (e.g., 'verify the health check returns 200 before proceeding to Step 3') and no feedback loops for error recovery during the deployment process itself. | 2 / 3 |
Progressive Disclosure | The content is mostly monolithic — all code examples are inline rather than referenced from separate files. The Resources section links to external docs, but the lengthy code blocks for metrics, alerts, and error handling could be split into referenced files to keep the main skill leaner. | 2 / 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
3e83543
- 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.