CtrlK
BlogDocsLog inGet started
Tessl Logo

firecrawl-incident-runbook

Execute Firecrawl incident response procedures with triage, mitigation, and postmortem. Use when responding to Firecrawl-related outages, investigating scrape/crawl failures, or running post-incident reviews for Firecrawl integration issues. Trigger with phrases like "firecrawl incident", "firecrawl outage", "firecrawl down", "firecrawl on-call", "firecrawl emergency", "firecrawl broken".

67

Quality

82%

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

65%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.

A highly actionable incident runbook with executable commands and a clear decision tree, but it is somewhat verbose in its generic templates, lacks explicit post-mitigation verification steps, and relies on a broken cross-reference instead of real progressive disclosure.

Suggestions

Add an explicit verification/feedback step after each mitigation (e.g., re-run the Quick Triage block to confirm the error clears) to turn the workflow into a validate→fix→retry loop.

Trim or externalize the generic incident-response boilerplate (severity table, Slack comms template, postmortem template) into a references/ file so the body stays lean.

Fix or remove the dead 'see firecrawl-data-handling' pointer — either create that bundled skill file or drop the reference so navigation is not broken.

DimensionReasoningScore

Conciseness

Mostly efficient — concrete commands and code with no basic-concept explanations — but the severity table and fill-in communication/postmortem templates are generic incident-response patterns Claude already knows and could be trimmed; not lean enough that every token earns its place (3).

2 / 3

Actionability

Copy-paste-ready curl and kubectl commands, concrete TypeScript snippets, and a per-error-code decision tree give fully executable guidance; it is not pseudocode or missing key details (2).

3 / 3

Workflow Clarity

A clear triage→decision-tree→per-error-action sequence exists, but there is no explicit post-mitigation verification/feedback loop (e.g., re-run triage after a key rotation), and impactful actions like API-key rotation cap workflow clarity at 2 per the rubric's destructive-operations note.

2 / 3

Progressive Disclosure

Sections are well organized (not a wall of text, no deep nesting), but the >50-line runbook is monolithic with no bundle split, and the single cross-reference ('see firecrawl-data-handling') is a dead pointer to a non-existent file rather than a clearly signaled one-level reference (3).

2 / 3

Total

9

/

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.

A strong, third-person description that clearly states capabilities, gives explicit 'Use when' guidance, and supplies natural trigger phrases scoped to a distinct Firecrawl niche. It avoids fluff, over-claims, and first/second-person voice.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'triage, mitigation, and postmortem' plus 'investigating scrape/crawl failures' and 'running post-incident reviews' — matching the multiple-specific-actions anchor; it is not merely naming a domain with some actions (2).

3 / 3

Completeness

Explicitly answers both what ('Execute Firecrawl incident response procedures with triage, mitigation, and postmortem') and when ('Use when responding to Firecrawl-related outages...') with explicit trigger guidance, so it is not capped at 2.

3 / 3

Trigger Term Quality

Natural on-call phrases a user would actually say — 'firecrawl incident', 'firecrawl outage', 'firecrawl down', 'firecrawl on-call', 'firecrawl emergency', 'firecrawl broken' — give good coverage; not jargon-only or missing common variations (2).

3 / 3

Distinctiveness Conflict Risk

A clear niche (Firecrawl incident response) with all triggers prefixed by 'firecrawl', making it unlikely to fire for unrelated skills; it is not merely 'somewhat specific' with overlap risk (2).

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.