granola-install-auth
Install and configure Granola AI meeting notes with calendar and audio permissions. Use when setting up Granola for the first time, connecting Google/Outlook calendars, granting macOS Screen Recording permission, or configuring Windows audio capture. Trigger: "install granola", "setup granola", "granola calendar", "granola permissions".
89
88%
Does it follow best practices?
Impact
Pending
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 an excellent skill description that hits all the marks. It provides specific concrete actions, includes explicit 'Use when' triggers with natural keywords, and targets a clearly distinct niche (Granola AI setup). The description is concise yet comprehensive, covering both platforms (macOS and Windows) and multiple configuration scenarios.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: install, configure, connect Google/Outlook calendars, grant macOS Screen Recording permission, configure Windows audio capture. These are all concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (install and configure Granola AI meeting notes with calendar and audio permissions) and 'when' (explicit 'Use when' clause covering first-time setup, calendar connection, and permission granting scenarios, plus explicit trigger terms). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'install granola', 'setup granola', 'granola calendar', 'granola permissions', plus platform-specific terms like 'macOS Screen Recording', 'Windows audio capture', 'Google/Outlook calendars'. Good coverage of natural variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — 'Granola AI' is a specific product name, and the description targets a very clear niche (Granola setup/configuration). Extremely 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 well-structured installation skill with strong actionability and clear workflow sequencing including verification steps. Its main weakness is verbosity — the architecture diagram, product description in the overview, and explanatory asides (e.g., explaining why Screen Recording permission is needed) add tokens without adding actionable value. Trimming the overview and architecture sections would significantly improve token efficiency.
Suggestions
Remove the 'Granola Architecture (How It Works)' section entirely — it's informational context that doesn't help Claude perform the installation task.
Trim the Overview to just the essential context needed for installation (e.g., remove the feature list about GPT-4o/Claude, supported platforms, and how it works without a bot).
Move the detailed error handling table to a separate troubleshooting reference file and keep only the most critical error (missing Screen Recording permission) inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The architecture diagram and explanation of how Granola works (audio capture, no bot joins, etc.) is unnecessary context that Claude doesn't need to perform the installation. The overview also explains what Granola is, which is descriptive rather than instructional. However, the core steps are reasonably tight. | 2 / 3 |
Actionability | Provides concrete executable commands (brew install, pgrep, defaults read, xattr), specific UI navigation paths for permissions and calendar setup, and a clear error handling table with exact fixes. The guidance is copy-paste ready and specific. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced from install through verification, with Step 5 serving as an explicit validation checkpoint (verify audio capture and live transcription). The error handling table provides feedback loops for common failure modes. The workflow is logical and complete. | 3 / 3 |
Progressive Disclosure | The skill includes inline content that could be separated (architecture diagram, detailed error table) making it longer than necessary for a SKILL.md overview. However, it does link to external resources and a next-steps skill. The architecture section in particular bloats what should be a focused setup guide. | 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
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.