firecrawl-advanced-troubleshooting
Debug hard-to-diagnose Firecrawl issues with systematic isolation and evidence collection. Use when standard troubleshooting fails, investigating why scrapes return empty content, crawl jobs hang, or webhooks don't fire. Trigger with phrases like "firecrawl hard bug", "firecrawl mystery error", "firecrawl impossible to debug", "firecrawl deep debug", "firecrawl not scraping".
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 strong skill description that clearly defines its niche as advanced Firecrawl debugging, distinguishes itself from standard troubleshooting, and provides excellent trigger coverage. It uses proper third-person voice, lists concrete failure scenarios, and explicitly states both what it does and when to use it. The explicit trigger phrases further strengthen discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and scenarios: 'systematic isolation and evidence collection', 'scrapes return empty content', 'crawl jobs hang', 'webhooks don't fire'. These are concrete, actionable problem types. | 3 / 3 |
Completeness | Clearly answers both 'what' (debug hard-to-diagnose Firecrawl issues with systematic isolation and evidence collection) and 'when' (when standard troubleshooting fails, with specific scenarios and explicit trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including both user-phrased queries ('firecrawl hard bug', 'firecrawl mystery error', 'firecrawl not scraping') and technical scenarios ('empty content', 'crawl jobs hang', 'webhooks don't fire'). The explicit trigger phrases are natural and varied. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive - targets a specific tool (Firecrawl) and a specific niche within that tool (hard-to-diagnose issues vs. standard troubleshooting). The 'when standard troubleshooting fails' clause clearly differentiates it from a general Firecrawl usage skill. | 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 well-structured advanced troubleshooting skill with strong actionability—every diagnostic step has executable code with concrete pass/fail criteria. The workflow is logically sequenced with proper validation. The main weakness is that the extensive inline code makes it somewhat verbose for a SKILL.md overview, and some code comments explain things Claude would already understand.
Suggestions
Extract the longer diagnostic functions (diagnose(), debugEmptyScrape(), etc.) into a referenced helper file to reduce SKILL.md length and improve progressive disclosure.
Trim explanatory comments in code like '// Strip everything down to the simplest failing case' and '// Can we scrape at all?' that describe what's already obvious from the code structure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable code, but includes some unnecessary verbosity—console.log labels, comments explaining obvious things ('Can we scrape at all?'), and the code blocks are longer than needed. The diagnostic functions could be more compact while preserving clarity. | 2 / 3 |
Actionability | Fully executable TypeScript code throughout with copy-paste ready diagnostic functions, specific API calls, concrete error detection patterns (regex for bot detection, content length thresholds), and a structured error handling table with specific solutions. | 3 / 3 |
Workflow Clarity | Clear 5-step sequential workflow with explicit layer-by-layer isolation (API connectivity → target accessibility → content quality → URL discovery). Each step builds on the previous, includes validation checks (pass/fail with detail), and the diagnose() function has an early return if connectivity fails. The error table provides clear feedback loops. | 3 / 3 |
Progressive Disclosure | The skill has reasonable structure with clear sections and a resources section pointing to external docs, but the inline code is quite lengthy (~150+ lines). The diagnostic functions and debug helpers could be referenced as separate files rather than fully inlined, and the single reference to 'firecrawl-load-scale' is minimal. | 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.