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".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable — dense, copy-paste-ready code across all four observability pillars in a clear six-step sequence — but it is let down by token efficiency and structure: the full implementation is inlined while a parallel, divergent reference file goes unlinked. Adding explicit validation checkpoints and splitting detail into the signaled reference would lift the weaker dimensions.

Suggestions

Move the full Grafana dashboard JSON and AlertManager rules into references/implementation.md and link to it from SKILL.md, keeping the body a lean overview — this resolves both the conciseness duplication and the un-signaled reference.

Reconcile the divergent metric names between the body (deepgram_requests_total) and references/implementation.md (deepgram_transcription_requests_total) so the two files share one source of truth.

Add explicit validation checkpoints to the workflow, e.g. after Step 1 run `curl localhost:9090/metrics | grep deepgram_` and after Step 6 confirm an alert fires with `amtool check-alert`, gating later steps on success.

Dimension	Reasoning	Score
Conciseness	Prose is lean with no concept explanations Claude already knows, but the ~387-line body inlines the full Grafana dashboard JSON, AlertManager YAML, and instrumented client — duplicating content already in references/implementation.md (with divergent metric names), so it could be tightened by offloading detail to the reference; not a 1 because there is no fluff or concept padding, not a 3 because the inline bulk and duplication mean not every token earns its place.	2 / 3
Actionability	Steps 1–6 are overwhelmingly fully executable TypeScript/JSON/YAML — Prometheus metric definitions, an instrumented Deepgram client, OTel SDK setup, Pino config, Grafana panels, and AlertManager rules — copy-paste ready; not a 2 because real executable code is provided rather than pseudocode with missing details.	3 / 3
Workflow Clarity	Steps 1–6 give a clear sequence and a trailing Error Handling table offers cause/solution pairs, but there are no explicit in-line validation checkpoints (e.g., "curl /metrics to confirm scrape" before continuing); not a 1 because the sequence is present and organized, not a 3 because validation checkpoints are missing/implicit rather than explicit feedback loops.	2 / 3
Progressive Disclosure	references/implementation.md exists but is never linked or signaled from the body and duplicates the inline implementation with divergent metric names (deepgram_requests_total vs deepgram_transcription_requests_total); the body is well-sectioned (not a monolithic wall), so not a 1, but content that belongs in the reference is inline and the reference is undiscoverable, so not a 3.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, well-formed description: it states a concrete capability, gives an explicit "Use when" clause, lists natural trigger phrases, and occupies a clear Deepgram-specific niche unlikely to conflict with other skills. The only minor blemish is the mild buzzword "comprehensive", which does not materially weaken it.

Dimension	Reasoning	Score
Specificity	"Set up comprehensive observability for Deepgram integrations" then names multiple concrete actions — "implementing monitoring, setting up dashboards, or configuring alerting" — matching the multiple-specific-actions anchor; not a 2 because the actions are concrete and enumerated rather than a single domain mention.	3 / 3
Completeness	Explicitly answers both what ("Set up comprehensive observability for Deepgram integrations") and when ("Use when implementing monitoring, setting up dashboards, or configuring alerting…") plus explicit Trigger terms; the "Use when…" clause and triggers satisfy the 3 anchor, avoiding the cap-at-2 penalty.	3 / 3
Trigger Term Quality	The Trigger line lists natural user phrases — "deepgram monitoring", "deepgram metrics", "monitor deepgram", "deepgram alerts", "deepgram dashboard" — giving good coverage of phrasings a user would actually say; not a 2 because common variations are present, not just one keyword.	3 / 3
Distinctiveness Conflict Risk	Targets a clear Deepgram-specific niche with triggers all prefixed by "deepgram", making overlap with non-Deepgram observability skills unlikely; not a 2 because the domain and triggers are distinct, not merely "somewhat specific".	3 / 3
	Total	12 / 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
Commit: 02d6341

Reviewed: 4 days 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.