granola-incident-runbook
Incident response procedures for Granola meeting capture failures and outages. Use when meetings aren't recording, transcription fails mid-meeting, integrations stop syncing, or the Granola service is down. Trigger: "granola incident", "granola outage", "granola down", "granola not recording", "granola emergency".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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 excellent trigger coverage and clear 'when' guidance. Its main weakness is that the 'what' portion is somewhat abstract—it says 'incident response procedures' without detailing the specific actions or steps the skill provides. The distinctiveness is excellent due to the specific product name and incident context.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Diagnoses recording failures, provides troubleshooting steps for transcription issues, guides integration reconnection, and escalates service outages.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Granola meeting capture) and some actions (incident response procedures), but doesn't list specific concrete actions like 'restart recording', 'check integration status', or 'escalate to support'. The description focuses more on trigger scenarios than on what the skill actually does. | 2 / 3 |
Completeness | Clearly answers both 'what' (incident response procedures for Granola meeting capture failures and outages) and 'when' (explicit 'Use when...' clause with multiple scenarios plus a dedicated 'Trigger:' list). Both dimensions are well-covered. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'granola not recording', 'granola down', 'granola outage', 'transcription fails', 'integrations stop syncing', and explicit trigger phrases. These are terms users would naturally say when experiencing these issues. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with the specific product name 'Granola' combined with incident response context. The trigger terms are very specific ('granola incident', 'granola outage') and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable incident runbook with excellent workflow clarity and concrete, executable guidance for each incident type. Its main weakness is length — the comprehensive coverage of all incident types in a single file makes it verbose for the context window, and some content (like the post-incident template and detailed integration tables) could be split into referenced files. The actionability is the standout strength, with copy-paste commands, Slack messages, and specific UI instructions throughout.
Suggestions
Split individual incident types into separate referenced files (e.g., granola-recording-failure.md, granola-outage.md) and keep SKILL.md as a triage overview that routes to the appropriate sub-file.
Trim the overview section — the description and prerequisites could be condensed since the YAML frontmatter already provides context about when this skill triggers.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity — the overview section explains what the runbook covers which is already clear from context, and some sections like the post-incident report template are quite lengthy. The severity table and scope assessment questions add value but could be tighter. | 2 / 3 |
Actionability | Highly actionable throughout — includes executable bash commands for status checking, specific UI paths ('right-click menu bar icon > Restart Granola'), concrete checklists for root cause investigation, copy-paste Slack messages for communication, and specific commands like 'pgrep -l Granola' and 'pkill -9 Granola'. Each incident type has clear, numbered immediate actions. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing: triage → remediation → escalation → post-incident review. Each incident type has ordered steps with validation checkpoints (e.g., 'wait 15 minutes', 'if still failing after 30 minutes'). The escalation path has clear time-boxed levels, and the post-incident template provides a feedback loop for prevention. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear headers and incident-type sections, but the skill is quite long (~180 lines of content) and could benefit from splitting incident types into separate referenced files. The resources section at the end provides good external references, but the monolithic structure means all incident types must be loaded even when only one is relevant. | 2 / 3 |
Total | 10 / 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
c8a915c
- 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.