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".
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/deepgram-pack/skills/deepgram-common-errors/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 term coverage and clear completeness, explicitly stating both what the skill does and when to use it. Its main weakness is that the capability description could be more specific about the concrete actions it performs (e.g., listing specific error types or resolution strategies). Overall, it would perform well in skill selection scenarios.
Suggestions
Add more specific concrete actions to improve specificity, e.g., 'Diagnose and fix common Deepgram errors including authentication failures (401), rate limiting (429), WebSocket connection drops, and malformed API requests.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Deepgram) and some actions ('diagnose and fix common errors'), but doesn't list specific concrete actions like 'resolve authentication errors, fix WebSocket connection issues, debug callback URLs'. The actions remain somewhat general. | 2 / 3 |
Completeness | Clearly answers both 'what' (diagnose and fix common Deepgram errors and issues) and 'when' (troubleshooting API errors, debugging transcription failures, resolving integration issues) with explicit trigger terms listed. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'deepgram error', 'deepgram not working', 'fix deepgram', 'deepgram troubleshoot', 'transcription failed', 'deepgram 401'. These are realistic user phrases covering multiple variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific product name 'Deepgram' and the troubleshooting focus. Very unlikely to conflict with other skills unless there's another Deepgram-specific skill. The trigger terms are product-specific and niche. | 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 troubleshooting reference with executable commands and real code examples covering the major Deepgram error categories. Its main weaknesses are that it's somewhat monolithic—all content lives in one file rather than being split into focused reference documents—and the workflow could better connect diagnostic results to specific resolution paths. Minor verbosity in the overview and output sections could be trimmed.
Suggestions
Add explicit decision-tree logic connecting Step 1 diagnostic results to subsequent steps (e.g., 'If HTTP 401 → see Step 2 row for 401; if WebSocket error → go to Step 3').
Split detailed reference tables (HTTP errors, WebSocket errors, SDK errors) into separate bundle files and keep SKILL.md as a concise overview with links to each.
Remove the 'Output' section which merely restates what the skill covers, and trim the 'Overview' to a single sentence.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and code blocks, but the 'Overview' section is somewhat padded, the 'Output' section restates what was already covered, and some comments in code blocks explain things Claude would already know. The 'Prerequisites' section is also somewhat obvious. | 2 / 3 |
Actionability | Highly actionable with executable curl commands, real TypeScript/Python code snippets, ffmpeg/ffprobe commands, and concrete solutions in every error table. The retry pattern is copy-paste ready with proper exponential backoff. | 3 / 3 |
Workflow Clarity | The steps are numbered and sequenced logically (diagnose → identify HTTP errors → check WebSocket → quality → SDK → retry), but there's no explicit validation/feedback loop between steps. The diagnostic step doesn't connect to subsequent steps with clear 'if you see X, go to step Y' guidance. | 2 / 3 |
Progressive Disclosure | Content is well-structured with clear headers and tables, but everything is inline in a single file with no bundle files to offload detailed reference material. The HTTP error table, WebSocket errors, SDK errors, and quality issues could each be separate reference files, keeping the SKILL.md as a concise overview with pointers. Resources section provides external links but no internal file references. | 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
3a2d27d
- 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.