granola-sdk-patterns
Zapier automation patterns and Enterprise API integration for Granola. Use when building automated workflows, connecting Granola to 8,000+ apps via Zapier, or querying the Enterprise API for notes and transcripts. Trigger: "granola zapier", "granola automation", "granola API", "granola SDK".
74
70%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/granola-pack/skills/granola-sdk-patterns/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 solid skill description that clearly identifies its niche (Granola + Zapier/API integration) with explicit trigger terms and a clear 'Use when' clause. Its main weakness is that the specific capabilities could be more granular—listing concrete actions like creating zaps, setting up triggers/actions, or specific API operations would strengthen it. Overall it performs well for skill selection purposes due to its distinctive domain.
Suggestions
Add more concrete actions to improve specificity, e.g., 'Create Zapier triggers for new notes, set up multi-step zaps, authenticate API keys, fetch transcripts by date range'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Zapier automation, Enterprise API, Granola) and mentions some actions like 'building automated workflows', 'connecting Granola to 8,000+ apps', and 'querying the Enterprise API for notes and transcripts', but doesn't list multiple concrete specific actions (e.g., creating zaps, handling webhooks, specific API endpoints). | 2 / 3 |
Completeness | Clearly answers both 'what' (Zapier automation patterns and Enterprise API integration for Granola) and 'when' (Use when building automated workflows, connecting Granola to apps via Zapier, or querying the Enterprise API). Includes explicit trigger terms as well. | 3 / 3 |
Trigger Term Quality | Includes explicit trigger terms ('granola zapier', 'granola automation', 'granola API', 'granola SDK') and natural keywords like 'automated workflows', 'Zapier', '8,000+ apps', 'notes and transcripts'. These are terms users would naturally use when seeking this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific combination of Granola + Zapier + Enterprise API. The trigger terms are very specific ('granola zapier', 'granola API') and unlikely to conflict with other 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 skill provides a comprehensive overview of Granola integration patterns with good structural organization and useful reference tables. However, the Zapier patterns are descriptive pseudocode rather than truly actionable configurations, and the content is too long for a single SKILL.md without splitting detailed patterns into separate files. Adding validation checkpoints within the multi-step workflows and making the guidance more directly executable would significantly improve quality.
Suggestions
Convert Zapier pattern descriptions into step-by-step UI instructions (e.g., 'In Zapier, click New Zap → Search for Granola → Select "Note Added to Folder" trigger → Configure folder name to "Sales Calls"') since YAML pseudocode isn't executable in Zapier's interface.
Add validation checkpoints to workflows, e.g., 'Test trigger: Share a test note to the configured folder and verify the Zap fires within 60 seconds before adding downstream actions.'
Split detailed Zap patterns and API reference into separate files (e.g., ZAP_PATTERNS.md, ENTERPRISE_API.md) and keep SKILL.md as a concise overview with links.
Remove the 'Output' section which adds no actionable value and just restates what was covered in the instructions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary sections like the 'Output' section which just restates what was already covered, and the multi-step automation chain in Step 4 is largely a verbose restatement of patterns already shown. The overview explaining what Granola is and the three channels is borderline unnecessary padding. | 2 / 3 |
Actionability | The Zapier patterns use YAML-like pseudocode rather than actual executable configurations—Zapier doesn't accept YAML configs, so these are descriptive rather than copy-paste ready. The API curl commands are concrete and executable, but the Zapier workflows (the bulk of the content) are illustrative descriptions of UI steps, not directly actionable. | 2 / 3 |
Workflow Clarity | Steps are sequenced logically (understand triggers → build patterns → use API → chain automations → organize folders), but there are no validation checkpoints. For multi-step automation chains involving external services, there's no guidance on testing individual steps, verifying data flow between steps, or handling partial failures in the chain. The error handling table at the end partially compensates but is disconnected from the workflow steps. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and tables, but it's quite long (~150+ lines of substantive content) with the Zapier patterns, API details, and routing strategies all inline. The API section and the detailed Zap patterns could be split into separate reference files. The Resources section and link to granola-common-errors show some awareness of progressive disclosure. | 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
3e83543
- 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.