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".
80
77%
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-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 solid skill description that clearly identifies its niche (Granola-specific analytics and adoption monitoring), provides explicit trigger terms, and answers both what and when. The main weakness is that the capability descriptions are somewhat high-level—terms like 'build custom dashboards' and 'analytics pipelines' could be more concrete with specific operations or outputs.
Suggestions
Add more concrete action verbs and specific outputs, e.g., 'track per-user meeting frequency, generate adoption trend charts, compute meeting duration statistics' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Granola adoption/meeting analytics) and some actions (monitor, build dashboards, track patterns, measure adoption), but the actions are somewhat generic and not deeply concrete—e.g., 'build custom dashboards' and 'creating executive reports' are broad rather than listing specific operations like 'query meeting duration trends' or 'export adoption CSV reports'. | 2 / 3 |
Completeness | Clearly answers both 'what' (monitor Granola adoption, meeting analytics, build custom 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 | Includes explicit trigger terms that users would naturally say: 'granola analytics', 'granola metrics', 'granola monitoring', 'granola adoption', 'meeting insights'. These are natural, specific, and cover multiple variations of how a user might phrase their request. | 3 / 3 |
Distinctiveness Conflict Risk | The description is highly specific to Granola as a product and its analytics/adoption monitoring, making it very unlikely to conflict with other skills. The 'granola' prefix on all trigger terms creates a clear niche. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive and highly actionable skill with concrete, executable code examples across multiple technologies (SQL, Zapier, bash). Its main weaknesses are length — several sections could be condensed or split into referenced files — and the lack of validation checkpoints in the multi-step pipeline setup workflow, which is important given that misconfigured data pipelines can produce silent data quality issues.
Suggestions
Add validation checkpoints after Step 3 (e.g., 'Verify pipeline: trigger a test meeting note and confirm the row appears in BigQuery within 5 minutes') to create a feedback loop for the data pipeline setup.
Move the four SQL analytics queries and the BigQuery schema into a separate reference file (e.g., GRANOLA_ANALYTICS_QUERIES.md) and link to it from the main skill to improve progressive disclosure and reduce token usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long with some sections that could be tightened (e.g., the metrics table in Step 2 includes targets and formulas that are somewhat generic, and four separate SQL queries are provided when two would suffice as examples). However, most content is substantive and not explaining concepts Claude already knows. | 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 code is copy-paste ready with specific table names, fields, and query logic. | 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 correctly before relying on it, no data validation after BigQuery inserts, and no feedback loop for fixing pipeline issues during setup. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and tables, but it's quite long (~180 lines of substantive content) with inline SQL queries and pipeline configs that could be split into referenced files. The 'Next Steps' reference to granola-incident-runbook is good, but the main body could benefit from offloading the SQL queries and Zapier configs to separate reference files. | 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
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.