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 well-structured skill description with strong trigger terms and clear completeness. Its main weakness is that the capability description could be more specific about what kinds of errors and fixes it covers (e.g., authentication errors, WebSocket issues, SDK configuration). The explicit trigger list is a notable strength that aids skill selection.
Suggestions
Add more specific concrete actions like 'resolve authentication (401) errors, debug WebSocket connection failures, fix SDK configuration issues, troubleshoot rate limiting' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Deepgram errors) and some actions (diagnose, fix, troubleshoot, debug), but doesn't list specific concrete actions like 'resolve authentication errors, fix WebSocket connection issues, handle rate limiting'. The actions remain somewhat general. | 2 / 3 |
Completeness | Clearly answers both 'what' (diagnose and fix common Deepgram errors) and 'when' (explicit 'Use when' clause plus a dedicated 'Trigger' section with specific phrases). Both components are well-articulated. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'deepgram error', 'deepgram not working', 'fix deepgram', 'transcription failed', 'deepgram 401'. These are realistic phrases a user would type when encountering issues. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — 'Deepgram' is a specific product/API, and the focus on error diagnosis and troubleshooting creates a clear niche. Unlikely to conflict with general transcription skills or other API skills. | 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 real executable commands, comprehensive error tables, and practical code patterns. Its main weaknesses are the lack of explicit diagnostic flow (connecting symptoms to the right section) and the monolithic structure that could benefit from splitting detailed sections into separate files. Minor verbosity in meta-sections (Overview, Output, Prerequisites) could be trimmed.
Suggestions
Add a diagnostic flowchart or decision tree at the top: 'Getting 4xx? → Step 2. WebSocket issues? → Step 3. Poor transcription? → Step 4.' to improve workflow clarity.
Split the HTTP error reference table and WebSocket error patterns into separate referenced files (e.g., HTTP_ERRORS.md, WEBSOCKET.md) to improve progressive disclosure.
Remove the 'Output' section entirely — it just restates what the skill contains and adds no actionable value.
Add a validation checkpoint after Step 1: 'If HTTP 200, your key works — proceed to the section matching your error. If not, fix auth first before debugging anything else.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with useful tables and executable code, but the 'Overview' section and 'Output' section add unnecessary meta-description. The 'Prerequisites' section states obvious things like 'Access to application logs'. Some comments in code blocks are slightly verbose but generally informative. | 2 / 3 |
Actionability | Excellent actionability throughout — real curl commands for diagnostics, executable TypeScript and Python code, specific ffmpeg/ffprobe commands, concrete error codes with specific solutions, and a complete retry pattern with exponential backoff. All code is copy-paste ready. | 3 / 3 |
Workflow Clarity | The steps are numbered and sequenced logically (diagnose → identify HTTP errors → check WebSocket → quality issues → SDK errors → retry), but there are no explicit validation checkpoints or feedback loops between steps. The diagnostic step doesn't connect to subsequent steps with 'if you see X, go to step Y' guidance. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and tables, but it's a long monolithic file (~150+ lines of detailed content) that could benefit from splitting the HTTP error reference, WebSocket patterns, and audio debugging into separate referenced files. The Resources section provides external links but no internal file references for deeper content. | 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
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.