granola-common-errors
Troubleshoot common Granola errors — audio capture failures, transcription issues, calendar sync problems, and integration errors. Platform-specific fixes for macOS and Windows. Trigger: "granola error", "granola not working", "granola not recording", "fix granola", "granola troubleshoot".
84
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is a strong skill description that clearly identifies the target application (Granola), lists specific problem categories it addresses, and provides explicit trigger terms. It uses third-person voice appropriately and covers both platform-specific context and natural user language. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: troubleshooting audio capture failures, transcription issues, calendar sync problems, and integration errors, with platform-specific fixes for macOS and Windows. | 3 / 3 |
Completeness | Clearly answers both 'what' (troubleshoot common Granola errors including audio capture, transcription, calendar sync, and integration errors) and 'when' (explicit trigger terms listed). The 'Trigger:' clause serves as an explicit 'Use when' equivalent. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would actually say: 'granola error', 'granola not working', 'granola not recording', 'fix granola', 'granola troubleshoot'. These cover common variations of how users would phrase their problems. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific application (Granola) with specific error categories. The product name 'Granola' combined with specific problem domains makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 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 skill with highly actionable, platform-specific fixes and good structural organization via headers and tables. Its main weaknesses are the lack of explicit verification steps after applying fixes (especially for destructive operations like cache clearing and preference deletion) and the monolithic structure that could benefit from splitting detailed sections into referenced files. Some content explains things Claude would already know, slightly reducing token efficiency.
Suggestions
Add explicit verification steps after each fix (e.g., 'Verify: run `pgrep -l Granola` and test with a short meeting to confirm audio capture works')
Add a confirmation prompt or backup step before destructive operations like `defaults delete ai.granola.app` and `rm -rf ~/Library/Caches/Granola`
Consider splitting integration-specific troubleshooting (Slack, Notion, HubSpot, Zapier) into a separate INTEGRATIONS.md file to reduce the main file's length
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and structured lists, but includes some unnecessary framing (e.g., the Overview paragraph explaining how Granola captures audio, the 'Output' section restating obvious outcomes). Some sections like 'Poor Transcription Quality' include advice Claude already knows (e.g., 'use a quiet room', 'one person speaks at a time'). | 2 / 3 |
Actionability | Provides concrete, executable bash commands for diagnostics, specific UI navigation paths (System Settings > Privacy & Security > Screen & System Audio Recording), exact Slack commands (/invite @Granola), and precise file paths for cache clearing. Nearly every fix is copy-paste ready or has explicit step-by-step instructions. | 3 / 3 |
Workflow Clarity | The initial diagnostic steps (Step 1, Step 2) provide a reasonable triage flow, and individual fixes are clearly sequenced. However, there are no explicit validation/verification steps after applying fixes — for example, after granting audio permissions and restarting Granola, there's no 'verify by running X command' or 'confirm by checking Y'. The destructive operations (clearing caches, deleting preferences) lack confirmation checkpoints. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear headers and a quick reference table, but it's quite long (~150+ lines of detailed content) and could benefit from splitting integration-specific troubleshooting or platform-specific fixes into separate files. The reference to 'granola-debug-bundle' in Next Steps is good, but the main body is somewhat monolithic. | 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.