CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

69

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The runbook is well-structured, concise, and easy to navigate, with a strong triage script and decision tree. It loses points because some remediation steps are non-executable guidance and the workflow lacks an explicit verify-after-fix checkpoint for destructive changes like key regeneration.

Suggestions

Replace comment-only remediation (e.g. 429 'Check application logs', 'reduce request rate') with concrete commands such as a curl-based rate probe or a grep/awk log query.

Add an explicit 'Verify resolution' step after each remediation — e.g. re-run the Quick Triage script and confirm a 200/no-error before declaring mitigated.

Make the webhook-firing test side-effect-free (note it triggers a real uploadAudio) or guard it behind a flag so it does not create test data during incident triage.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no explanations of what GraphQL or webhooks are, and every section (triage, decision tree, templates) earns its place.

3 / 3

Actionability

The triage script and decision tree are executable, but several remediation sections are comment-only guidance ('Check application logs for request volume', 'reduce request rate') rather than commands, and the webhook test fires a real uploadAudio mutation as a side effect rather than a safe dry-run.

2 / 3

Workflow Clarity

There is a clear sequence (triage first, then decision tree, then remediation), but no explicit validation/verify checkpoint after applying a fix — 'verified resolved' appears only inside the postmortem template, not as a workflow step, and key/secret regeneration is a destructive change without a verify step.

2 / 3

Progressive Disclosure

It is a single well-organized file with clear sections and one-level-deep external links (Fireflies docs, sibling skills); no bundle files exist to mis-structure, so the simple-skill guidance applies.

3 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and uses third-person voice with an explicit 'Use when' clause and natural trigger phrases. It is a strong, well-distinguished description.

DimensionReasoningScore

Specificity

Names three concrete actions — 'triage, remediation, and postmortem' — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers what ('Execute...triage, remediation, and postmortem') and when ('Use when responding to...'), plus an explicit trigger-phrase clause.

3 / 3

Trigger Term Quality

Lists six natural phrases users would say ('fireflies incident', 'outage', 'down', 'on-call', 'emergency', 'broken'), giving good coverage.

3 / 3

Distinctiveness Conflict Risk

Scoped to Fireflies.ai incidents with product-specific triggers, making overlap with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.