deepgram-observability
Set up comprehensive observability for Deepgram integrations. Use when implementing monitoring, setting up dashboards, or configuring alerting for Deepgram integration health. Trigger: "deepgram monitoring", "deepgram metrics", "deepgram observability", "monitor deepgram", "deepgram alerts", "deepgram dashboard".
77
73%
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-observability/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 completeness. Its main weakness is that the capability description is somewhat generic in terms of specific actions — it describes observability setup at a high level without detailing specific metrics, tools, or concrete deliverables. The Deepgram-specific focus gives it strong distinctiveness.
Suggestions
Add more specific concrete actions beyond generic observability terms, e.g., 'Track transcription latency, error rates, and API usage; configure Prometheus/Grafana dashboards; set up webhook failure alerts'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Deepgram observability) and mentions some actions like 'implementing monitoring', 'setting up dashboards', and 'configuring alerting', but these are fairly generic observability concepts rather than deeply specific concrete actions (e.g., no mention of specific metrics tracked, specific tools used, or specific integration patterns). | 2 / 3 |
Completeness | The description clearly answers both 'what' (set up comprehensive observability for Deepgram integrations) and 'when' (explicit 'Use when' clause with triggers for monitoring, dashboards, alerting, plus explicit trigger terms). Both components are present and explicit. | 3 / 3 |
Trigger Term Quality | The description explicitly lists natural trigger terms like 'deepgram monitoring', 'deepgram metrics', 'deepgram observability', 'monitor deepgram', 'deepgram alerts', 'deepgram dashboard' — these are terms users would naturally say and cover good variations of the concept. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'Deepgram' + 'observability/monitoring/dashboards/alerting' creates a very specific niche that is unlikely to conflict with other skills. The Deepgram-specific qualifier makes it clearly distinguishable from generic monitoring or other integration 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 provides highly actionable, executable code covering a comprehensive Deepgram observability stack, which is its primary strength. However, it suffers from being a monolithic document with ~250 lines of inline code that would be better split across reference files, and it lacks validation checkpoints between the multi-step setup process. The error handling table at the end is a nice touch but doesn't compensate for the missing verification steps within the workflow.
Suggestions
Split the six major code blocks into separate reference files (e.g., metrics.md, tracing.md, alerting.md) and keep SKILL.md as a concise overview with links to each component.
Add validation checkpoints after key steps, such as 'curl localhost:PORT/metrics to verify metrics are being collected' after Step 1-2, and 'check OTEL collector logs for incoming traces' after Step 3.
Remove the Output section's bullet list which merely restates what the steps already cover, and trim the overview to avoid redundancy with the Four Pillars table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~250 lines of code) and includes some content Claude could infer (e.g., basic Pino setup, standard Express metrics endpoint). The cost-per-minute rates are useful domain knowledge, but the overall volume is heavy for a skill file that could reference separate files for the full implementations. | 2 / 3 |
Actionability | All code examples are fully executable TypeScript with correct imports, proper types, and real library APIs. The Prometheus metrics, OpenTelemetry setup, Grafana dashboard JSON, and AlertManager YAML are all copy-paste ready with specific, concrete configurations. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered 1-6 with a logical progression, but there are no validation checkpoints between steps. For a complex multi-component observability setup, there should be verification steps (e.g., 'verify metrics endpoint returns data', 'confirm traces appear in collector') to catch configuration errors. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of code with all implementation details inline. The six substantial code blocks (metrics definition, instrumented client, OTel tracing, Pino logging, Grafana dashboard, AlertManager rules) should be split into separate reference files, with SKILL.md providing an overview and links. The Resources section links to external docs but doesn't reference any companion 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
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.