firecrawl-observability

Monitor Firecrawl scraping pipelines with metrics, credit tracking, and quality alerts. Use when implementing monitoring for Firecrawl operations, setting up dashboards, or configuring alerting for scrape failures and credit consumption. Trigger with phrases like "firecrawl monitoring", "firecrawl metrics", "firecrawl observability", "monitor firecrawl", "firecrawl alerts".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

80%

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

The content is highly actionable and concise, dominated by executable code with no conceptual padding. Its weaknesses are in workflow clarity (the batch crawl step lacks failure-recovery validation) and progressive disclosure (a dangling runbook reference plus all content kept inline).

Suggestions

Add explicit validation checkpoints and a failure-recovery feedback loop for the batch crawl in Step 3 — handle a 'failed' crawl status and add a step verifying metrics are actually flowing before relying on alerts.

Resolve the dangling 'firecrawl-incident-runbook' reference in Next Steps: either create that bundle file under references/ or remove the reference, since no such file exists in any bundle directory.

Move the full code implementations and the Prometheus alert rules into reference files (e.g. references/alert-rules.yaml, references/instrumented-wrapper.ts) so the ~180-line SKILL.md serves as a lean overview with one-level-deep references.

Dimension	Reasoning	Score
Conciseness	The body is lean and code-dominated (executable TypeScript, YAML alert rules, concrete PromQL queries) with no explanations of concepts Claude already knows — it does not explain what Firecrawl, Prometheus, counters, or histograms are — so every token earns its place per anchor 3 rather than the padded anchor 1 or the could-be-tightened anchor 2.	3 / 3
Actionability	Provides fully executable code with real imports ('@mendable/firecrawl-js'), real API calls, concrete Prometheus alert rules, and copy-paste PromQL dashboard queries, matching anchor 3's fully-executable/copy-paste-ready bar rather than the pseudocode of anchor 2.	3 / 3
Workflow Clarity	The five numbered steps are clearly sequenced, but validation checkpoints are missing or implicit — the batch crawl operation in Step 3 polls status yet never handles a 'failed' state and lacks a validate->fix->retry feedback loop, so per the rubric's batch-operation guideline workflow clarity is capped at anchor 2 rather than reaching anchor 3's explicit-validation bar.	2 / 3
Progressive Disclosure	Section organization is good and external resource links are well-signaled, but 'Next Steps' references 'firecrawl-incident-runbook' which does not exist in references/scripts/assets (a dangling reference), and all substantial code is kept inline in a ~180-line skill rather than split into bundle files — fitting anchor 2's 'content that should be separate is inline' rather than anchor 3's appropriately-split structure.	2 / 3
	Total	10 / 12 Passed

Description

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.

The description is strong across all dimensions: it states concrete capabilities, includes natural trigger phrases, explicitly covers both what and when, and is tightly scoped to Firecrawl with low conflict risk. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Monitor Firecrawl scraping pipelines with metrics, credit tracking, and quality alerts' plus 'setting up dashboards, or configuring alerting for scrape failures and credit consumption' — matching the anchor for several specific concrete actions rather than the vague anchor 1 or partial anchor 2.	3 / 3
Completeness	Clearly answers what ('Monitor Firecrawl scraping pipelines...') and when via an explicit 'Use when implementing monitoring for Firecrawl operations...' clause plus trigger phrases, matching anchor 3's requirement for both what and when with explicit triggers; not the anchor 2 case where 'when' is only implied.	3 / 3
Trigger Term Quality	Explicit trigger phrases — 'firecrawl monitoring', 'firecrawl metrics', 'firecrawl observability', 'monitor firecrawl', 'firecrawl alerts' — are natural terms a user would actually say, giving good coverage as required by anchor 3.	3 / 3
Distinctiveness Conflict Risk	The skill is tightly scoped to a specific SaaS (Firecrawl) and every trigger contains 'firecrawl', making it a clear niche with distinct triggers unlikely to conflict with other skills, matching anchor 3.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 50ab626

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.