Name: proxycrawl
Rating: 55.2 (1 reviews)
Author: membranedev

proxycrawl

ProxyCrawl integration. Manage data, records, and automate workflows. Use when the user wants to interact with ProxyCrawl data.

Quality

62%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/proxycrawl/SKILL.md

Quality

Content

67%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.

The body delivers concrete, executable Membrane CLI commands with a real connection-state feedback loop and clear sectioning. Its main weakness is conciseness — marketing prose and explanatory asides pad otherwise lean operational guidance.

Suggestions

Cut the audience pitch ('used by data scientists, researchers, and businesses needing web data') and the 'auth plumbing' aside — Claude doesn't need the marketing framing.

Remove 'This is the fastest way to get a connection' and merge the overlapping 'Searching for actions' and 'Popular actions' sections to eliminate redundancy.

Replace the placeholder-only proxy example ('/path/to/endpoint') with one real ProxyCrawl endpoint so the section is concrete rather than abstract.

Dimension	Reasoning	Score
Conciseness	The bulk is lean commands and tables, but several asides pad the doc — 'used by data scientists, researchers, and businesses needing web data' and 'so you can focus on the integration logic rather than auth plumbing' — fitting score 3 (mostly efficient, some unnecessary explanation) more than 4.	3 / 5
Actionability	Concrete executable bash commands ('membrane connection ensure "https://proxycrawl.com/" --json', 'membrane action run <actionId> --connectionId=CONNECTION_ID --json') plus a flags table cover the main flows, but the thin 'Popular actions' section and the placeholder-only proxy example ('/path/to/endpoint') leave minor gaps, fitting score 4 rather than 5.	4 / 5
Workflow Clarity	The connection workflow has explicit state checkpoints (READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a poll-until-ready feedback loop ('After the user completes the action... poll again... to check if the state moved to READY'), but the dangling 'skip to Step 2' reference and lack of an end-to-end numbered checklist are minor gaps, fitting score 4 rather than 5.	4 / 5
Progressive Disclosure	The body is well-organized into clear sections ('## ProxyCrawl Overview', '### Connecting to ProxyCrawl', '## Best practices') with no nested references or monolithic wall, but everything is inlined in one ~164-line file with minor quirks (a '#### 1b.' without a '1a', a redundant 'Popular actions' section), fitting score 4 rather than 5.	4 / 5
	Total	15 / 20 Passed

Description

57%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.

The description names the ProxyCrawl product and includes an explicit 'Use when' trigger, but its action verbs are generic ('manage', 'automate') and it relies on the brand name alone for trigger terms. It is complete and distinct yet lacks concrete, specific capability language.

Suggestions

Replace the generic verbs ('Manage data, records, and automate workflows') with concrete ProxyCrawl actions such as 'scrape web pages, crawl sites, and extract structured data'.

Add natural trigger synonyms users would actually say — e.g. 'web scraping', 'crawling', or 'extracting data from websites' — not just the brand name.

Sharpen the 'when' clause to specific scenarios, e.g. 'Use when the user wants to scrape a website or extract data without being blocked by anti-bot defenses.'

Dimension	Reasoning	Score
Specificity	It names the ProxyCrawl domain but the action verbs 'Manage data, records, and automate workflows' are generic buzzwords rather than concrete capabilities (e.g. scrape/extract), fitting the score-2 anchor (minimal or generic actions) better than the score-3 anchor that requires concrete actions.	2 / 5
Completeness	It explicitly provides both a 'what' ('Manage data, records, and automate workflows') and a 'Use when the user wants to interact with ProxyCrawl data' trigger, but the 'when' is generic and the 'what' lacks concrete specifics, fitting score 4 (both present, 'when' could be more specific) rather than 5.	4 / 5
Trigger Term Quality	It includes the natural brand keyword a user would say ('ProxyCrawl data', 'interact with ProxyCrawl data') but misses common task synonyms like 'scrape', 'crawl', or 'web scraping', matching score 3 (relevant keywords, missing variations) rather than 4.	3 / 5
Distinctiveness Conflict Risk	It is anchored to a specific named product ('ProxyCrawl integration', 'interact with ProxyCrawl data') so conflict risk is low, but the generic 'manage data/automate workflows' phrasing leaves minor overlap risk with other data skills, matching score 4 rather than 5.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/proxycrawl/SKILL.md
Commit: f484c82

Reviewed: 5 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.