deepgram-common-errors

Diagnose and fix common Deepgram errors and issues. Use when troubleshooting Deepgram API errors, debugging transcription failures, or resolving integration issues. Trigger: "deepgram error", "deepgram not working", "fix deepgram", "deepgram troubleshoot", "transcription failed", "deepgram 401".

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 a strong, actionable debugging reference with executable commands and code, but it functions more as a catalog than a guided workflow and fails to surface its existing references/implementation.md bundle file.

Suggestions

Add explicit navigation to references/implementation.md (e.g., a '## Implementation details' section linking to it) so the bundle file is discoverable from the body.

Introduce feedback-loop checkpoints in the diagnostic flow (e.g., 'If Step 1 returns 401, regenerate the API key in Console > API Keys and re-run') to move workflow clarity from a catalog to a guided process.

Trim generic material Claude already knows (the full exponential-backoff retry function and the CORS-explanation row) to lean summaries, keeping only the Deepgram-specific retryable-status logic.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean (tables, curl/ffprobe commands, terse inline comments) but carries some content Claude already knows, such as a generic exponential-backoff retry function and a CORS explanation, so it could be tightened.	2 / 3
Actionability	Highly executable throughout: real curl endpoints with headers, ffprobe/ffmpeg commands with specific flags, version-specific SDK fixes, and error-to-solution tables that are copy-paste ready.	3 / 3
Workflow Clarity	Steps are sequenced (Step 1 diagnostic through Step 6 retry) but read as a reference catalog with only implicit checkpoints; there are no explicit validation/feedback loops such as 'if HTTP 401, regenerate key then re-run Step 1'.	2 / 3
Progressive Disclosure	A bundle file references/implementation.md exists with substantial content, yet the SKILL.md body never links to or signals it, and the inline HTTP/WebSocket error tables could partially live in that separate file.	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.

The description is concise, third-person, and answers both what the skill does and when to use it with explicit natural-language triggers. It is distinctively scoped to Deepgram and free of fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Diagnose and fix common Deepgram errors and issues') within a clearly bounded domain, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states both what it does ('Diagnose and fix common Deepgram errors') and when to use it ('Use when troubleshooting Deepgram API errors, debugging transcription failures, or resolving integration issues').	3 / 3
Trigger Term Quality	An explicit Trigger block provides six natural phrases a user would actually say ('deepgram error', 'deepgram not working', 'fix deepgram', 'deepgram troubleshoot', 'transcription failed', 'deepgram 401'), giving good coverage.	3 / 3
Distinctiveness Conflict Risk	The Deepgram-specific niche and brand-named triggers (e.g. 'deepgram 401') make it unlikely to fire for unrelated skills.	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: 6e3a65f

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.