deepgram-rate-limits

Implement Deepgram rate limiting and backoff strategies. Use when handling API quotas, implementing request throttling, or dealing with 429 rate limit errors. Trigger: "deepgram rate limit", "deepgram throttling", "429 error deepgram", "deepgram quota", "deepgram backoff", "deepgram concurrency".

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%Weight 40%Scale 1-3

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 with complete, runnable TypeScript for every step, but it underperforms on token efficiency and progressive disclosure: the full implementations are duplicated between the body and the unlinked implementation.md reference, and the batch workflow lacks an explicit validation checkpoint. Tightening the inline code and routing to the reference would lift the weaker dimensions.

Suggestions

Link to implementation.md from the body (e.g., in a References section) and keep only the combined ResilientDeepgramClient usage pattern inline, moving the standalone RateLimiter/CircuitBreaker/Backoff classes into the reference file to remove duplication.

Add an explicit validation checkpoint for batch transcription — e.g., after Promise.allSettled, inspect limiter.getStats() and the settled results (fulfilled vs rejected) before reporting success, and surface a retry plan for rejected items.

Drop the 'Key insight' restatement line since the concurrency-not-RPS model is already conveyed by the plan table and the Step 1 comment.

Dimension	Reasoning	Score
Conciseness	The ~260-line body is mostly code with little concept-explanation Claude already knows, but it embeds five full TypeScript implementations that are largely duplicated in implementation.md, plus a 'Key insight' line that restates the concurrency model already in the table. It is not a 3 because not every token earns its place given the inline duplication; not a 1 because it avoids generic tutorial padding.	2 / 3
Actionability	Each step ships complete, executable TypeScript with real imports ('import pLimit from \'p-limit\'', '@deepgram/sdk') and copy-paste-ready usage examples. It is not a 2 because the code is real and runnable rather than pseudocode or partial snippets.	3 / 3
Workflow Clarity	Steps 1–5 are clearly sequenced and an Error Handling table provides recovery guidance, but the batch transcription path ('hundreds more' URLs) has no explicit validation/verification checkpoint before declaring success. Per the rubric's batch-operation guidance this caps the score at 2; it is not a 1 because the sequence and per-step error handling are present.	2 / 3
Progressive Disclosure	The body is well-sectioned, but the provided bundle file implementation.md is never linked or signaled from the body, and its RateLimiter/CircuitBreaker/Backoff/Usage content is duplicated inline rather than split out. It is not a 3 because references are not clearly signaled and content that should live in the reference is inline; not a 1 because organization is reasonable and references are not deeply nested.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 strong across all dimensions: it states concrete capabilities, gives an explicit 'Use when' trigger clause plus a dedicated Trigger line of natural terms, and occupies a distinct Deepgram-specific niche. Third-person voice is maintained throughout, so no voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Implement Deepgram rate limiting and backoff strategies', 'handling API quotas, implementing request throttling, or dealing with 429 rate limit errors' — matching the 'Lists multiple specific concrete actions' anchor. It is not a 2 because it goes beyond naming a domain to enumerate several distinct capabilities.	3 / 3
Completeness	Clearly answers what ('Implement Deepgram rate limiting and backoff strategies') and when ('Use when handling API quotas, implementing request throttling, or dealing with 429 rate limit errors') plus an explicit Trigger clause. It is not a 2 because the 'when' is explicit, not merely implied.	3 / 3
Trigger Term Quality	The explicit Trigger line gives natural phrasings a user would say — 'deepgram rate limit', 'deepgram throttling', '429 error deepgram', 'deepgram quota', 'deepgram backoff', 'deepgram concurrency'. It is not a 2 because coverage spans the common variations rather than a single keyword.	3 / 3
Distinctiveness Conflict Risk	A clear Deepgram-specific niche with distinct triggers ('deepgram rate limit', 'deepgram concurrency') unlikely to fire for unrelated skills. It is not a 2 because the scope is tightly scoped to one vendor's rate-limiting concern rather than overlapping with general API 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
Path: plugins/saas-packs/deepgram-pack/skills/deepgram-rate-limits/SKILL.md
Commit: 0540a62

Reviewed: about 20 hours 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.