firecrawl-reference-architecture
Implement Firecrawl reference architecture with scrape/crawl/map/extract pipelines. Use when designing new Firecrawl integrations, reviewing project structure, or building content ingestion pipelines for AI/RAG applications. Trigger with phrases like "firecrawl architecture", "firecrawl project structure", "firecrawl pipeline", "firecrawl RAG", "firecrawl knowledge base".
67
82%
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 well-crafted skill description that clearly identifies its niche (Firecrawl reference architecture), lists specific capabilities (scrape/crawl/map/extract pipelines), and provides explicit trigger guidance with both 'Use when' and 'Trigger with' clauses. The description is concise, uses third-person voice, and would be easily distinguishable from other skills in a large skill library.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'scrape/crawl/map/extract pipelines', 'designing new Firecrawl integrations', 'reviewing project structure', 'building content ingestion pipelines for AI/RAG applications'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (implement Firecrawl reference architecture with scrape/crawl/map/extract pipelines) and 'when' (designing new integrations, reviewing project structure, building content ingestion pipelines) with explicit 'Use when' and 'Trigger with' clauses. | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger phrases: 'firecrawl architecture', 'firecrawl project structure', 'firecrawl pipeline', 'firecrawl RAG', 'firecrawl knowledge base'. These are terms users would naturally use when seeking this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific 'Firecrawl' domain focus and the combination of scrape/crawl/map/extract pipelines with RAG applications. The trigger terms are all Firecrawl-specific, making conflicts with other skills very unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, highly actionable skill with complete executable TypeScript implementations covering all four Firecrawl endpoints and realistic pipeline patterns. Its main weaknesses are the lack of validation checkpoints in the multi-step workflows (especially for batch/destructive operations like file writes) and the monolithic inline presentation of all implementation code that could benefit from being split across referenced files.
Suggestions
Add explicit validation checkpoints after crawl completion (e.g., check crawl status, verify page count, validate markdown output is non-empty) and a retry/feedback loop for failed scrapes.
Consider splitting the detailed implementation code (processor.ts, intelligent-scrape.ts, crawl-pipeline.ts) into bundle files and referencing them from SKILL.md, keeping only the service layer and usage examples inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with executable code examples, but includes some unnecessary elements like the architecture diagram that adds visual bulk without critical instructional value, and the overview section restates what the code already demonstrates. Some comments in code are helpful but the overall length could be tightened. | 2 / 3 |
Actionability | Fully executable TypeScript code with concrete implementations for all four Firecrawl endpoints. Functions are copy-paste ready with proper imports, types, and realistic configurations. The error handling table provides specific cause-solution pairs. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced (service layer → processing → intelligent scrape → crawl+store), but there are no explicit validation checkpoints or feedback loops. For a pipeline involving batch web scraping and file writes, there should be validation steps (e.g., verify crawl completion status, validate output files). The crawl pipeline writes files without checking success. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a resources section linking to external docs, but it's quite long (~180 lines of code) with all implementation details inline. The processing pipeline and chunking logic could be referenced as separate files. The 'Next Steps' reference to 'firecrawl-multi-env-setup' is good but no bundle files exist to support it. | 2 / 3 |
Total | 9 / 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.