granola-core-workflow-b
Post-meeting note processing, sharing, and follow-up workflows in Granola. Use when enhancing notes after meetings, sharing to Slack/Notion/CRM, drafting follow-up emails, or processing action items. Trigger: "granola post-meeting", "share granola notes", "granola follow-up", "granola enhance", "granola share".
83
81%
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 a strong skill description that clearly defines its scope around Granola post-meeting workflows, lists concrete actions, provides explicit trigger guidance with a 'Use when' clause and dedicated trigger terms, and occupies a distinct niche. The description is concise yet comprehensive, covering both capabilities and activation conditions effectively.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: enhancing notes after meetings, sharing to Slack/Notion/CRM, drafting follow-up emails, and processing action items. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (post-meeting note processing, sharing, follow-up workflows) and 'when' (explicit 'Use when' clause with specific triggers, plus a dedicated Trigger line with example phrases). | 3 / 3 |
Trigger Term Quality | Includes natural keywords like 'share granola notes', 'granola follow-up', 'granola enhance', plus mentions specific platforms (Slack, Notion, CRM) and actions (follow-up emails, action items) that users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific product name 'Granola', the post-meeting context, and the combination of specific platforms (Slack/Notion/CRM). Unlikely to conflict with other skills given the narrow niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%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 GUI workflow skill with clear sequencing and good error handling, but it's somewhat verbose for what Claude needs. The content describes UI interactions in a third-party application that Claude cannot directly execute, which limits actionability. The skill would benefit from trimming explanatory content about internal features and splitting integration-specific details into separate files.
Suggestions
Trim explanatory content about what the Enhance step does internally (GPT-4o/Claude processing details) and what the CRM tracks — Claude doesn't need feature marketing copy.
Split integration-specific sharing instructions (Slack, Notion, HubSpot) into separate reference files to reduce the monolithic nature and improve progressive disclosure.
Clarify Claude's role more explicitly — is Claude guiding a user through these steps, or is Claude performing actions via an API? The current framing is ambiguous about what Claude can actually do versus what requires human UI interaction.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some unnecessary explanation (e.g., explaining what the Enhance step does internally with GPT-4o/Claude, describing what the People & Companies CRM tracks). Some sections like the folder organization table and CRM feature descriptions add bulk that Claude doesn't need explained. | 2 / 3 |
Actionability | The skill provides step-by-step UI instructions (click Share > Slack, etc.) which are concrete for a GUI-based workflow, and includes a useful chat example. However, since this is a GUI application skill, there's no executable code or commands — the guidance is specific but ultimately describes UI clicks that Claude cannot directly perform, reducing true actionability. | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced (Steps 1-6) with a review/validation checkpoint in Step 2 that includes a checklist before sharing. The error handling table provides a feedback loop for common failures. The review checklist explicitly guards against sharing hallucinated or sensitive content, which is appropriate for this type of operation. | 3 / 3 |
Progressive Disclosure | The skill references other skills (`granola-core-workflow-a`, `granola-sdk-patterns`) and external documentation links, which is good. However, the content is quite long and monolithic — the integration-specific details (Slack, Notion, HubSpot) and the People & Companies CRM section could be split into separate reference files. No bundle files exist to support progressive disclosure. | 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
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.