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). Overall it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions, e.g., 'resolve authentication (401) errors, fix WebSocket connection drops, debug SDK configuration issues, handle 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' (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', '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 that is unlikely to conflict with other skills (e.g., a general Deepgram usage skill or a generic API debugging skill). | 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 troubleshooting reference with excellent actionability—every error has concrete, executable solutions. The main weaknesses are its length (could benefit from splitting into sub-files) and the lack of explicit diagnostic flow connecting Step 1 results to subsequent steps. Minor verbosity in meta-sections (Overview, Output, Prerequisites) could be trimmed.
Suggestions
Add explicit navigation from Step 1 diagnostic results to the relevant error section (e.g., 'If HTTP 401 → see Step 2 row for 401; if WebSocket error → see Step 3').
Split detailed sections (WebSocket errors, SDK errors, retry patterns) into separate referenced files to improve progressive disclosure and reduce the monolithic feel.
Remove the 'Output' section entirely—it just restates what the skill contains and adds no value. Trim the 'Overview' to one line or remove it.
| 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. Some comments in code blocks are slightly verbose but generally informative. | 2 / 3 |
Actionability | Excellent actionability with fully executable curl commands, TypeScript/Python code snippets, ffmpeg/ffprobe commands, and a complete retry pattern. Every error has a concrete solution, not just a description. | 3 / 3 |
Workflow Clarity | The steps are numbered and sequenced logically (diagnose → identify HTTP errors → check WebSocket → quality issues → SDK errors → retry), but there's no explicit validation/feedback loop tying the diagnostic steps together. The 'Step 1' diagnostic doesn't clearly connect to subsequent steps (e.g., 'if you get 401, go to Step 2 row for 401'). | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and tables, but it's a long monolithic file (~150 lines of dense content) that could benefit from splitting detailed sections (WebSocket errors, SDK errors, retry patterns) into separate referenced files. The Resources section provides external links but no internal file references for advanced topics. | 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
c8a915c
- 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.