granola-core-workflow-a
Meeting preparation and template setup in Granola — templates, recipes, and pre-meeting workflows. Use when configuring note templates for 1:1s, standups, discovery calls, or sprint planning, creating custom recipes, or preparing agenda notes before important meetings. Trigger: "granola template", "granola meeting prep", "granola recipe", "granola agenda".
74
70%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/granola-pack/skills/granola-core-workflow-a/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 that clearly identifies its niche (Granola meeting prep), provides explicit trigger guidance, and distinguishes itself from generic meeting or note-taking skills. The main weakness is that the specific capabilities could be more concrete—listing exact actions like 'create template fields', 'configure recurring agenda items', or 'set up automated recipe steps' would strengthen specificity.
Suggestions
Add more concrete action verbs describing what the skill actually does with templates and recipes, e.g., 'define template sections and fields, configure recipe automation rules, set default agenda structures'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Granola meeting preparation) and some actions (configuring note templates, creating custom recipes, preparing agenda notes), but the actions are somewhat general and could be more concrete—e.g., it doesn't specify what 'template setup' or 'recipe creation' entails in detail. | 2 / 3 |
Completeness | Clearly answers both 'what' (meeting preparation and template setup in Granola—templates, recipes, pre-meeting workflows) and 'when' (explicit 'Use when' clause with specific scenarios, plus explicit trigger terms). Both dimensions are well-addressed. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms like 'granola template', 'granola meeting prep', 'granola recipe', 'granola agenda', plus contextual terms like '1:1s', 'standups', 'discovery calls', 'sprint planning' that users would naturally mention. Good coverage of variations. | 3 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Granola-specific meeting preparation features (templates, recipes, agenda notes). The 'granola' prefix on all trigger terms and the specific product context make it highly unlikely to conflict with generic meeting or note-taking skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%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-organized guide for Granola meeting preparation that provides useful concrete examples (template markdown, recipe prompts, configuration tables). Its main weaknesses are the lack of validation/verification steps in the workflow, some verbosity in explanatory text that Claude doesn't need, and the monolithic structure that could benefit from splitting detailed reference tables into separate files. The actionability is inherently limited since Granola is a GUI application.
Suggestions
Add validation checkpoints: e.g., 'After creating a custom template, test it on a past meeting by re-enhancing notes to verify sections populate correctly' and 'Test auto-trigger conditions by checking the next 3 calendar events match expectations'.
Trim explanatory prose that Claude already knows—remove the Prerequisites section, the 'Templates tell the AI how to structure...' sentence, and the Output section which just restates what the steps accomplish.
Split the large reference tables (built-in templates, recipes, workspace defaults, error handling) into a separate REFERENCE.md file, keeping only 2-3 key examples inline.
Add a brief note about the inherent limitation that Claude can only advise users on these GUI steps rather than execute them directly, to set appropriate expectations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity. The 'Prerequisites' section and explanatory sentences like 'Templates tell the AI how to structure the enhanced output' explain things Claude can infer. The tables are efficient, but the overall document could be tightened—the 'Output' section is redundant, and some explanatory prose doesn't add value. | 2 / 3 |
Actionability | The skill provides concrete UI navigation paths (Settings > Templates, Settings > Recipes) and example markdown templates, which is helpful. However, since Granola is a GUI application, Claude cannot actually click buttons or navigate settings—the instructions describe UI workflows that Claude can only advise on, not execute. The recipe prompts and template examples are concrete and useful for advising users, but there's no executable code or commands. | 2 / 3 |
Workflow Clarity | The 5-step sequence is clearly laid out and logically ordered (choose template → create custom → create recipes → pre-meeting prep → set defaults). However, there are no validation checkpoints—no step to verify a template works correctly, no feedback loop for testing a recipe before relying on it, and no verification that auto-trigger conditions match correctly before a real meeting. | 2 / 3 |
Progressive Disclosure | The content references external docs and a follow-up skill (granola-core-workflow-b), which is good. However, the document is quite long with all content inline—the 9-row built-in template table, 6-row recipe table, error handling table, and best practices could be split into referenced files. No bundle files exist to support progressive disclosure despite the content length warranting it. | 2 / 3 |
Total | 8 / 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.