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".
68
83%
Does it follow best practices?
Impact
—
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 strong trigger terms, explicit 'Use when' guidance, and a clear niche around Granola incident response. Its main weakness is that it describes triggering conditions thoroughly but is less specific about what concrete actions or procedures the skill actually performs (e.g., diagnostic steps, escalation procedures, workarounds).
Suggestions
Add specific concrete actions the skill performs, e.g., 'Diagnoses root causes, provides workarounds for mid-meeting failures, guides escalation procedures, and documents incident timelines' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Granola meeting capture) and describes some actions/scenarios (failures, outages, recording issues, transcription failures, integration sync issues), but doesn't list specific concrete remediation actions the skill performs—it focuses more on the triggering conditions than the capabilities. | 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 'Trigger' list). Both dimensions are well-covered. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'granola incident', 'granola outage', 'granola down', 'granola not recording', 'granola emergency', plus natural phrases like 'meetings aren't recording', 'transcription fails', and 'integrations stop syncing'. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive—targets a very specific product (Granola) and a specific use case (incident response for meeting capture failures). The trigger terms are product-specific 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 that it packs a lot of content into a single file without leveraging bundle files for progressive disclosure, and some sections could be tightened (e.g., the overview, some explanatory text). Overall it would serve Claude well in an incident response scenario.
Suggestions
Split incident-type remediation sections into separate referenced files (e.g., incidents/not-recording.md, incidents/outage.md) to reduce the main file length and improve progressive disclosure.
Trim the overview paragraph — it restates the skill description and prerequisites could be more concise (e.g., 'Requires: Granola admin access, status.granola.ai bookmarked, internal Slack channel').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity — the overview paragraph restates what the description already conveys, the severity table is somewhat padded, and some sections (like the post-incident report template) are lengthy for a skill file. However, most content is operational and earns its place. | 2 / 3 |
Actionability | Highly actionable throughout: includes executable bash commands for status checks, specific CLI commands (pgrep, pkill), concrete checklists for root cause investigation, exact Slack message templates, and specific integration fix steps with tables. Nearly everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear four-step sequence (Triage → Remediation → Escalation → Post-Incident Review) with explicit validation checkpoints: severity assessment questions, status page checks before proceeding, time-boxed waits ('wait 15 minutes', 'after 30 minutes'), and a structured escalation path with time expectations. The feedback loop of 'fix → re-validate → escalate if still broken' is present in each incident type. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear headers and incident-type sections, but it's a long monolithic file (~180 lines of content) with no bundle files to offload detail into. The integration troubleshooting table, post-incident template, and individual incident types could be split into separate referenced files. The single reference to 'granola-data-handling' at the end is good but insufficient for the volume of inline content. | 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
a04d1a2
- 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.