universal-scraping-architect

Use for web scraping, crawling, document extraction, API parsing, or building validation-heavy data pipelines using Firecrawl or local Python scripts.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

88%Weight 40%Scale 1-5

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

A lean, highly actionable skill body with an explicit validated workflow and real runnable scripts. The main gap is that existing reference documents in ./references/ are not signposted from the overview.

Suggestions

Add a short 'References' or inline links pointing to the existing reference docs (firecrawl-technical-guide.md for Mode 1, local-extraction-patterns.md for Mode 2, scraping-ethics-security.md for etiquette) so the bundled detail files are discoverable.

Trim the opening editorializing tagline to a single declarative purpose line.

Consider noting where the local-extraction-patterns and ethics material applies within the relevant Modes/Anti-Patterns sections via one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — exact CLI commands and tables with no over-explanation of what scraping or libraries are — but the opening tagline ('intelligent routing, validation, and token-budget tracking — not brittle one-off scripts') is mild editorializing that could be trimmed.	4 / 5
Actionability	Fully executable guidance throughout: exact commands like 'python3 scripts/validate_extraction.py extracted_output.json --json', explicit exit-code semantics, '--sample' flags, and a concrete os.getenv rewrite, all pointing to real scripts.	5 / 5
Workflow Clarity	The numbered 'Extraction Pipeline' gives a clear sequence (Route → Track Budgets → Extract → Validate & Clean → Format) with an explicit validation checkpoint and a fix-and-re-extract feedback loop, matching the level-5 anchor.	5 / 5
Progressive Disclosure	Good section structure and the three scripts are referenced by exact path, but the three reference docs in ./references/ (firecrawl-technical-guide.md, local-extraction-patterns.md, scraping-ethics-security.md) are never linked from the body, a navigation gap that keeps it below the top anchor.	4 / 5
	Total	18 / 20 Passed

Description

75%Weight 40%Scale 1-5

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

A strong, trigger-led description that names concrete actions and explicit tooling. It would reach the top anchor by separating the 'what' from the 'when' and adding file-extension synonyms.

Suggestions

Split into a 'what' sentence and a separate 'Use when ...' clause with concrete user trigger phrases (e.g. 'Use when the user says scrape, crawl, or parse a site/API').

Add common synonyms and file extensions (e.g. spidering, .pdf, .csv, .xlsx) to broaden trigger-term coverage.

Narrow 'document extraction' and 'API parsing' toward the web-scraping niche to reduce overlap with general document/data skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'web scraping, crawling, document extraction, API parsing', and 'building validation-heavy data pipelines' — plus the Firecrawl/local-Python tooling, but does not enumerate output-format capabilities, leaving minor gaps.	4 / 5
Completeness	The 'Use for ...' clause provides explicit 'when' guidance and the action list supplies the 'what', but both are fused into a single clause rather than stated separately with concrete trigger phrases, falling short of the level-5 anchor.	4 / 5
Trigger Term Quality	Natural user-facing terms ('web scraping', 'crawling', 'document extraction', 'API parsing') map well to things users say, but file extensions and synonyms (e.g. spidering, .pdf, .csv) are absent.	4 / 5
Distinctiveness Conflict Risk	The Firecrawl-anchored scraping/pipeline niche is mostly distinct, though the broad 'document extraction' and 'API parsing' phrases create minor overlap risk with general data-handling skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: engineering/universal-scraping-architect/skills/universal-scraping-architect/SKILL.md
Commit: 19392f7

Reviewed: ~3 hours 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.