granola-debug-bundle
Create diagnostic bundles for Granola support requests. Use when preparing support tickets, collecting system/audio/network info, or diagnosing complex issues that require Granola support team assistance. Trigger: "granola debug", "granola diagnostics", "granola support bundle", "granola logs", "granola system info".
89
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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 defines its purpose, scope, and activation triggers. It specifies concrete actions (diagnostic bundles, system/audio/network info collection), provides explicit 'Use when' guidance, and includes natural trigger terms. The Granola-specific focus makes it highly distinctive and unlikely to conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: creating diagnostic bundles, preparing support tickets, collecting system/audio/network info, and diagnosing complex issues. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (create diagnostic bundles, collect system/audio/network info) and 'when' (preparing support tickets, diagnosing complex issues requiring Granola support team assistance), with explicit trigger terms listed. | 3 / 3 |
Trigger Term Quality | Includes explicit trigger terms that users would naturally say: 'granola debug', 'granola diagnostics', 'granola support bundle', 'granola logs', 'granola system info'. These are natural, varied, and well-targeted keywords. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped specifically to 'Granola' diagnostic bundles and support requests. The product-specific trigger terms ('granola debug', 'granola logs') make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable diagnostic skill with executable commands specific to Granola's actual infrastructure (API endpoints, cache paths, TCC database queries). The workflow is well-sequenced and includes both automated collection and manual verification steps. Minor weaknesses include some verbosity (the Current State preamble, obvious prerequisites) and the monolithic structure that could benefit from splitting platform-specific instructions into separate files.
Suggestions
Remove the 'Current State' section with inline shell commands — this is unusual for a SKILL.md and the version/OS info is already collected in Step 2.
Consider splitting macOS and Windows instructions into separate referenced files (e.g., MACOS.md, WINDOWS.md) to reduce the main file length and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable code blocks, but includes some unnecessary elements: the 'Current State' section with shell commands at the top is unusual, the Prerequisites section states obvious things ('Terminal access'), and the Privacy section, while useful, adds bulk. The self-diagnosis checklist is valuable but could be more compact. | 2 / 3 |
Actionability | Every step contains fully executable, copy-paste-ready bash/PowerShell commands with proper error handling (set -euo pipefail). Commands are specific to Granola's actual paths, endpoints, and configuration files. The error handling table provides concrete fixes for specific failure modes. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with logical progression (create dir → collect info → check permissions → network → cache → package). Each step builds on the previous one. The self-diagnosis checklist serves as a pre-flight validation checkpoint, and the error handling table provides recovery paths for common failures. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, but it's a long monolithic file (~150+ lines of substantive content) with no bundle files to offload detail into. The Windows PowerShell section, error handling table, and self-diagnosis checklist could potentially be separate referenced files. However, for a single-purpose diagnostic skill, the inline approach is reasonable. | 2 / 3 |
Total | 10 / 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.