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".
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 well-crafted skill description that clearly defines its scope around Firecrawl monitoring, provides explicit trigger guidance with natural user phrases, and is highly distinctive. It covers the what, when, and trigger terms comprehensively while remaining concise and focused.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: monitoring pipelines, metrics tracking, credit tracking, quality alerts, setting up dashboards, and configuring alerting for scrape failures and credit consumption. | 3 / 3 |
Completeness | Clearly answers both 'what' (monitor Firecrawl scraping pipelines with metrics, credit tracking, quality alerts) and 'when' (explicit 'Use when' clause for implementing monitoring, setting up dashboards, configuring alerting, plus explicit trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes a dedicated trigger phrase list with natural variations users would say: 'firecrawl monitoring', 'firecrawl metrics', 'firecrawl observability', 'monitor firecrawl', 'firecrawl alerts'. Also includes contextual terms like 'dashboards', 'scrape failures', 'credit consumption'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific 'Firecrawl' product focus combined with monitoring/observability niche. The trigger terms are very specific and unlikely to conflict with general monitoring or general web scraping skills. | 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, actionable skill with executable TypeScript code, concrete Prometheus alert rules, and clear dashboard queries. The 5-step workflow is well-sequenced with appropriate validation (credit thresholds, quality evaluation, progress polling). The main weakness is that the inline code volume is substantial and could benefit from being split into referenced files for better progressive disclosure.
Suggestions
Consider moving the full TypeScript implementations into a separate reference file (e.g., FIRECRAWL_MONITORING_CODE.md) and keeping only the key patterns and emit() signature inline in SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with executable code and useful tables, but some sections are slightly verbose — the overview restates what the metrics table already conveys, and the emit() wrapper explanation could be tighter. The error handling table and resources section add value without bloat. | 2 / 3 |
Actionability | Fully executable TypeScript code with concrete implementations for scraping, credit monitoring, crawl tracking, and Prometheus alert rules. The dashboard panel section provides copy-paste-ready PromQL queries. All code is complete and runnable. | 3 / 3 |
Workflow Clarity | Clear 5-step sequence from instrumented wrapper → credit monitoring → crawl tracking → alerting → dashboards. Each step builds on the previous. The credit health check includes threshold-based alerting (warning/critical), and the crawl monitor includes polling with progress metrics — these serve as validation checkpoints. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a table of contents-like flow, but the skill is quite long (~150+ lines of code inline) and could benefit from splitting the code examples into separate reference files. The 'Next Steps' reference to firecrawl-incident-runbook is good but the main content is monolithic. | 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
c8a915c
- 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.