firecrawl-architecture-variants
Choose and implement Firecrawl architecture patterns for different scales and use cases. Use when designing new Firecrawl integrations, choosing between on-demand/scheduled/pipeline architectures, or planning scraping infrastructure. Trigger with phrases like "firecrawl architecture", "firecrawl blueprint", "how to structure firecrawl", "firecrawl at scale", "firecrawl pipeline design".
83
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
89%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-structured skill description with strong completeness and distinctiveness. It clearly defines when to use the skill and provides explicit trigger phrases. The main weakness is that the capability description could be more specific about what concrete actions or outputs the skill produces beyond 'choose and implement patterns'.
Suggestions
Add more specific concrete actions/outputs, e.g., 'generates architecture diagrams, configures queue systems, sets up rate limiting, implements error handling strategies' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Firecrawl architecture patterns) and some actions (choose, implement, design integrations, plan scraping infrastructure), but doesn't list multiple concrete specific actions like 'configure rate limiting, set up queue workers, implement retry logic'. The actions remain somewhat high-level. | 2 / 3 |
Completeness | Clearly answers both 'what' (choose and implement Firecrawl architecture patterns for different scales and use cases) and 'when' (designing new integrations, choosing between architectures, planning scraping infrastructure) with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Includes explicit trigger phrases that users would naturally say: 'firecrawl architecture', 'firecrawl blueprint', 'how to structure firecrawl', 'firecrawl at scale', 'firecrawl pipeline design'. Also includes natural terms like 'on-demand/scheduled/pipeline architectures' and 'scraping infrastructure'. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Firecrawl architecture patterns specifically. The trigger terms are highly distinctive ('firecrawl architecture', 'firecrawl blueprint') and unlikely to conflict with general web scraping skills or other integration skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured architectural guide with strong actionability—all three patterns include executable TypeScript code with real SDK calls. The decision matrix and ASCII diagrams effectively guide architecture selection. The main weakness is the lack of explicit validation checkpoints and error recovery loops within the multi-step workflows, and the code examples are somewhat lengthy for a skill file.
Suggestions
Add explicit validation/retry steps in Architectures 2 and 3 (e.g., check crawl status for errors before indexing, retry failed batch scrapes) to create proper feedback loops.
Tighten the on-demand architecture by combining the two endpoint examples into one with a comment showing the extract variant, saving ~15 lines.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of tables and diagrams, but some sections like the full class implementation in Architecture 3 are quite lengthy. The decision matrix and ASCII flow diagrams are well-done, but the overall length (~150+ lines of code) could be tightened—e.g., the on-demand architecture's two endpoint examples could be consolidated. | 2 / 3 |
Actionability | All three architectures provide fully executable TypeScript code with real API calls, concrete configuration options, and copy-paste ready examples. The code uses actual Firecrawl SDK methods with realistic parameters, and includes practical details like credit budgeting, content validation filters, and cron expressions. | 3 / 3 |
Workflow Clarity | Each architecture has a clear ASCII flow diagram showing the pipeline stages, and the decision tree at the end helps with selection. However, there are no explicit validation checkpoints or feedback loops within the workflows—e.g., Architecture 2 doesn't validate crawl results before indexing, and Architecture 3's content validation is inline but lacks a retry/fix loop for failed scrapes. | 2 / 3 |
Progressive Disclosure | The skill is well-structured with a clear overview, decision matrix up front, three distinct architecture sections, a decision tree for selection, an error handling table, and external references to API docs and a related skill for pitfalls. Content is appropriately organized with one-level-deep references. | 3 / 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
70e9fa4
- 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.