fireflies-incident-runbook
Execute Fireflies.ai incident response with triage, remediation, and postmortem. Use when responding to Fireflies.ai API outages, auth failures, or webhook delivery problems. Trigger with phrases like "fireflies incident", "fireflies outage", "fireflies down", "fireflies on-call", "fireflies emergency", "fireflies broken".
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 strong skill description that clearly defines its scope (Fireflies.ai incident response), lists concrete actions (triage, remediation, postmortem), specifies when to use it (API outages, auth failures, webhook delivery problems), and provides excellent trigger phrases. It uses proper third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'triage, remediation, and postmortem' and names specific failure types: 'API outages, auth failures, webhook delivery problems'. | 3 / 3 |
Completeness | Clearly answers both 'what' (execute incident response with triage, remediation, and postmortem) and 'when' (API outages, auth failures, webhook delivery problems) with an explicit 'Use when' clause and additional trigger phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'fireflies incident', 'fireflies outage', 'fireflies down', 'fireflies on-call', 'fireflies emergency', 'fireflies broken'. These are highly natural phrases someone would use in an incident scenario. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific product name 'Fireflies.ai' combined with incident response context. Very unlikely to conflict with other skills given the narrow, well-defined niche. | 3 / 3 |
Total | 12 / 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 incident response runbook with excellent actionability — executable triage scripts, a clear decision tree, and specific remediation steps per error type. The main weakness is moderate verbosity: communication templates and postmortem boilerplate are generic content Claude can generate on demand, and they inflate the token cost without adding Fireflies-specific value. Progressive disclosure could be improved by extracting templates and detailed remediation into referenced files.
Suggestions
Move the communication templates and postmortem template to a separate file (e.g., `fireflies-incident-templates.md`) and reference it, since these are generic formats Claude already knows how to produce.
Remove the 'Output' section — it restates what the workflow already makes obvious and adds no actionable guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with actionable scripts and tables, but includes some unnecessary elements like the communication templates and postmortem template which are generic boilerplate Claude already knows how to produce. The 'Output' section restates what's obvious from the workflow. | 2 / 3 |
Actionability | Provides fully executable bash scripts for triage and each error type, specific curl commands with proper GraphQL queries, TypeScript code for webhook debugging, and concrete steps for secret rotation across multiple platforms. Copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear decision tree for triage, explicit severity-based sequencing, the 'Run First' triage script establishes a diagnostic baseline before remediation, and the error handling table addresses edge cases. The workflow naturally validates (check error → identify type → apply fix → verify). | 3 / 3 |
Progressive Disclosure | The skill is well-structured with clear sections and a reference to `fireflies-data-handling` and external docs, but the communication templates and postmortem template could be split into a separate file. The content is somewhat long for a single SKILL.md, with inline content that could benefit from being referenced separately. | 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
4dee593
- 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.