granola-observability
Monitor Granola adoption, meeting analytics, and build custom dashboards. Use when tracking team meeting patterns, measuring adoption, building analytics pipelines, or creating executive reports. Trigger: "granola analytics", "granola metrics", "granola monitoring", "granola adoption", "meeting insights".
61
73%
Does it follow best practices?
Impact
—
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-observability/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 with clear 'what' and 'when' clauses, explicit trigger terms, and strong distinctiveness through the product-specific 'Granola' scoping. The main weakness is that the specific capabilities listed are somewhat generic (e.g., 'build analytics pipelines', 'creating executive reports') and could benefit from more concrete action descriptions.
Suggestions
Add more concrete, specific actions such as 'query Granola API for meeting frequency data', 'generate adoption rate charts by team', or 'calculate meeting duration trends' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Granola adoption/meeting analytics) and some actions (monitor, build dashboards, track patterns, measure adoption, build pipelines, create reports), but the actions are somewhat generic and not deeply concrete—e.g., 'build analytics pipelines' and 'creating executive reports' are broad rather than specific operations. | 2 / 3 |
Completeness | The description clearly answers both 'what' (monitor adoption, meeting analytics, build dashboards) and 'when' (tracking team meeting patterns, measuring adoption, building analytics pipelines, creating executive reports), with an explicit 'Use when' clause and trigger terms. | 3 / 3 |
Trigger Term Quality | The description includes explicit trigger terms like 'granola analytics', 'granola metrics', 'granola monitoring', 'granola adoption', and 'meeting insights', which are natural phrases a user would say. The product-specific prefix 'granola' makes these highly targeted and useful for matching. | 3 / 3 |
Distinctiveness Conflict Risk | The skill is highly distinctive due to the product-specific term 'Granola' combined with analytics/monitoring context. It is unlikely to conflict with generic analytics or meeting skills because of the explicit product scoping. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability with concrete, executable code examples across SQL, YAML, and bash. However, it suffers from being a monolithic document that tries to cover too much in a single file — built-in analytics, custom pipelines, query libraries, automated reporting, and health monitoring all inline. Adding validation checkpoints between pipeline setup steps and splitting detailed content into referenced files would significantly improve this skill.
Suggestions
Split the SQL analytics queries, Zapier pipeline configurations, and BigQuery schema into separate referenced files (e.g., QUERIES.md, PIPELINE_SETUP.md) to improve progressive disclosure and reduce the main file's token footprint.
Add explicit validation checkpoints: after creating the BigQuery table verify it exists, after setting up the Zapier pipeline run a test trigger and confirm data appears in BigQuery before proceeding to build queries.
Trim the metrics definition table (Step 2) — Claude can infer reasonable targets; focus on the formulas and which metrics matter most rather than listing every possible metric with targets.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long with extensive SQL queries and Zapier configurations that are useful but could be tightened. The metrics tables are well-structured but the sheer volume of content (analytics queries, reporting, health monitoring) makes this quite heavy. Some sections like the efficiency rating query feel nice-to-have rather than essential. | 2 / 3 |
Actionability | The skill provides fully executable SQL queries, concrete Zapier pipeline configurations, a complete BigQuery schema, and a working bash command for status checking. The metrics tables include specific targets and formulas. This is highly actionable and copy-paste ready. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced from built-in analytics through custom pipelines to reporting and monitoring. However, there are no validation checkpoints — for instance, no step to verify the Zapier pipeline is working before building queries on top of it, no verification that BigQuery table was created correctly, and no feedback loop for the data pipeline setup which is a multi-step destructive/batch operation. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with no bundle files to offload detailed content. The SQL queries, Zapier configurations, and BigQuery schema could easily be split into separate reference files. Everything is inline in one large document with no references to supporting files for the detailed pipeline setup, query library, or alert configurations. | 1 / 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
d41e58e
- 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.