firecrawl-policy-guardrails
Implement Firecrawl scraping policy enforcement: domain blocklists, credit budgets, content filtering, and robots.txt compliance guardrails. Use when setting up scraping policies, enforcing crawl limits, or preventing accidental scraping of prohibited domains. Trigger with phrases like "firecrawl policy", "firecrawl guardrails", "firecrawl domain blocklist", "firecrawl scraping rules", "firecrawl compliance".
89
88%
Does it follow best practices?
Impact
—
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 articulates specific capabilities (domain blocklists, credit budgets, content filtering, robots.txt compliance), provides explicit 'Use when' guidance, and includes well-chosen trigger phrases. The description is concise, uses third-person voice, and occupies a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: domain blocklists, credit budgets, content filtering, and robots.txt compliance guardrails. These are clearly defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (implement Firecrawl scraping policy enforcement with specific sub-capabilities) and 'when' (explicit 'Use when' clause covering setting up policies, enforcing limits, preventing prohibited scraping, plus explicit trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes a rich set of natural trigger terms: 'firecrawl policy', 'firecrawl guardrails', 'firecrawl domain blocklist', 'firecrawl scraping rules', 'firecrawl compliance', plus contextual phrases like 'scraping policies', 'crawl limits', 'prohibited domains'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — focuses specifically on Firecrawl scraping policy enforcement, a narrow niche. The 'firecrawl' prefix on all trigger terms and the specific domain (policy/guardrails vs. general scraping) make conflicts with other skills very unlikely. | 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 fully executable TypeScript code covering domain blocklists, credit budgets, content quality gates, crawl limits, and rate limiting. The workflow is well-sequenced with clear validation checkpoints and a helpful summary table. The main weakness is that the content is somewhat monolithic—at ~180 lines of mostly code, it could benefit from splitting detailed implementations into separate files while keeping SKILL.md as a concise overview.
Suggestions
Consider splitting the detailed class implementations (Steps 1-5) into a separate reference file and keeping SKILL.md as a concise overview with the policy summary table and a brief usage example.
Remove explanatory comments that state the obvious (e.g., '// Meta ToS', '// 2 requests/second') and the overview paragraph explaining general web scraping risks—Claude already knows these concepts.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable code, but includes some unnecessary context in the overview (explaining what web scraping risks are) and comments that explain obvious things (e.g., '// Meta ToS', '// 2 requests/second'). The content is fairly long at ~180 lines but most of it is functional code. | 2 / 3 |
Actionability | All code examples are fully executable TypeScript with concrete implementations—domain validation, budget tracking, content quality gates, rate limiting, and a complete pipeline example. Every policy is implemented with copy-paste ready code, not pseudocode. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced from domain validation → budget check → content quality → crawl limits → rate limiting. Step 4 (policedCrawl) demonstrates the full validation pipeline with explicit checkpoints: validate URL, enforce limits, check budget, execute, record usage, filter quality. The policy summary table provides a clear overview of enforcement points and consequences. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections, summary tables, and a reference to 'firecrawl-architecture-variants' for next steps. However, the skill is quite long and monolithic—the detailed code implementations for each policy could be split into separate reference files, with SKILL.md serving as a concise overview. No bundle files exist to support this. | 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
a04d1a2
- 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.