firecrawl-data-handling

Process, validate, and store Firecrawl scraped content with deduplication and chunking. Use when handling scraped markdown, implementing content pipelines, building RAG knowledge bases, or processing crawl results for downstream consumption. Trigger with phrases like "firecrawl data", "firecrawl content processing", "firecrawl markdown cleaning", "firecrawl storage", "firecrawl RAG pipeline".

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

80%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is lean, code-forward, and highly actionable with executable TypeScript for every step. Its weaknesses are a batch storage pipeline lacking validation feedback loops and a monolithic structure with no reference-file split for a 240-line skill.

Suggestions

Add a validation checkpoint to the crawl-and-store pipeline (Step 5): verify the crawl returned the expected page count and confirm files were written before reporting success, with a retry-on-failure loop.

Split the full pipeline code and/or examples into a references/ file (e.g., references/pipelines.md) and keep SKILL.md as a concise overview pointing to it, improving progressive disclosure.

For batch operations, add an explicit validate→fix→re-run feedback loop in the Error Handling section rather than only a static troubleshooting table.

Dimension	Reasoning	Score
Conciseness	The body is code-forward with minimal prose — the Overview is a single sentence and inline comments like "// strips nav, footer, sidebar" earn their place — with no explanation of concepts Claude already knows; not 2 because there is no padded or unnecessary explanation.	3 / 3
Actionability	Each step ships complete, executable TypeScript functions (scrapeClean, chunkForRAG, crawlAndStore) plus a concrete error-handling table, making it copy-paste ready; not 2 because the code is fully executable rather than pseudocode.	3 / 3
Workflow Clarity	Five steps are clearly sequenced and extraction includes Zod validation (ArticleSchema.parse), but the batch crawl-and-store pipeline writes files without a validation checkpoint or validate→fix→retry loop, which the rubric caps at 2 for batch operations; not 3 because of that missing feedback loop, and not 1 because the sequence is explicit.	2 / 3
Progressive Disclosure	Sections are well organized (Overview, Steps, Error Handling, Examples), but the ~240-line body is a monolith with all pipeline code inline — content that could live in reference files is not split out and no bundle files exist to disclose into; not 3 because the overview is not kept separate from the detail, and not 1 because navigation is clear and references are only one level deep.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description states concrete capabilities, provides explicit use-when triggers, and occupies a distinct Firecrawl-scoped niche in third person. It is concise and complete across all four dimensions.

Dimension	Reasoning	Score
Specificity	"Process, validate, and store Firecrawl scraped content with deduplication and chunking" lists multiple concrete actions (process, validate, store, deduplicate, chunk), matching the multiple-specific-actions anchor; not 2 because it goes beyond naming only a domain.	3 / 3
Completeness	It answers both what ("Process, validate, and store...") and when ("Use when handling scraped markdown, implementing content pipelines, building RAG knowledge bases...") with explicit triggers; not 2 because the when-clause is explicit rather than only implied.	3 / 3
Trigger Term Quality	Trigger phrases like "firecrawl data", "firecrawl RAG pipeline", and "firecrawl storage" are natural terms a user would say when needing this skill, giving good coverage; not 2 because common variations are well represented.	3 / 3
Distinctiveness Conflict Risk	The Firecrawl-specific niche with distinct "firecrawl" triggers makes it unlikely to fire for the wrong skill; not 2 because the scope is clearly bounded to scraped-content handling.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/firecrawl-pack/skills/firecrawl-data-handling/SKILL.md
Commit: 4c47e33

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.