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
—
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 clearly identifies the specific product (Granola AI), lists concrete setup actions across platforms, and provides explicit trigger guidance with both a 'Use when' clause and explicit trigger terms. It is concise, uses third-person voice, and would be easily distinguishable from other skills in a large collection.
| 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). | 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 — targets a specific product (Granola AI) with specific setup tasks. Very unlikely to conflict with other skills given the unique product name and specific permission/calendar integration triggers. | 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 solid, actionable installation guide with clear step sequencing and good error handling. Its main weakness is verbosity — the architecture section, product explanation in the overview, and some explanatory asides (e.g., explaining why Screen Recording permission is needed) add tokens without aiding task execution. Trimming the 'how it works' section and tightening the overview would significantly improve token efficiency.
Suggestions
Remove the 'Granola Architecture (How It Works)' section entirely — it explains product internals irrelevant to installation and wastes ~15 lines of context.
Trim the Overview to just the essential context (e.g., 'AI notepad that captures meeting audio via system audio — no bot joins calls') and drop the list of supported platforms and AI models.
Move the error handling table and preferences table to a separate troubleshooting/reference file to keep the main skill focused on the install workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The architecture diagram and explanation of how Granola works (audio capture, no bot, etc.) is unnecessary context for an installation skill — Claude doesn't need to understand the product's internal architecture to install it. The overview paragraph also explains what Granola is, which is filler. The core install steps are reasonably tight, but the surrounding content adds bloat. | 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 verification step. The error handling table gives specific fixes with exact commands and settings paths. | 3 / 3 |
Workflow Clarity | The six steps are clearly sequenced in logical order (install → auth → permissions → calendar → verify → configure). Step 5 serves as an explicit verification checkpoint, and the error handling table provides feedback loops for common failure modes. The macOS permission step correctly flags both permissions as critical. | 3 / 3 |
Progressive Disclosure | The skill is well-structured with clear sections, but the architecture diagram, detailed error handling table, and preferences table could be split into separate reference files to keep the main skill leaner. The Resources section links to external docs, but the inline content is heavier than needed for a single SKILL.md with no bundle files. | 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.