Name: crawlbase
Rating: 54.400000000000006 (1 reviews)
Author: membranedev

crawlbase

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

Quality

61%

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/crawlbase/SKILL.md

Quality

Content

61%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 content is a well-structured, actionable Membrane-CLI walkthrough for Crawlbase, weakened mainly by a padded marketing intro and missing validation checkpoints around destructive bulk operations.

Suggestions

Add a validation step before destructive actions, e.g. list stored RIDs and confirm with the user before running delete-stored-results-bulk, then verify the deletion count afterward.

Trim or move the opening paragraph ('Crawlbase is a web crawling API...') to keep the file focused on integration steps Claude does not already know.

Consider extracting the full Popular actions table into a references file and keeping only a few representative examples inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient CLI guidance, but the opening marketing paragraph ('Crawlbase is a web crawling API that helps developers extract data from websites... used by data scientists, researchers, and businesses') is padded context Claude does not need.	3 / 5
Actionability	Concrete executable commands (npm install, membrane login, membrane connection ensure, membrane action run, membrane request) and a populated actions table give mostly copy-paste-ready guidance, with minor gaps around substituting CONNECTION_ID.	4 / 5
Workflow Clarity	The install→authenticate→connect→search→run sequence is present with state-polling, but destructive batch actions (delete-stored-results-bulk) appear without validation/verification steps, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	A single well-organized file with clear section headers and a tidy actions table; minor gaps since the popular-actions table and proxy options could live in a separate reference file.	4 / 5
	Total	14 / 20 Passed

Description

61%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 pairs an explicit Use-when trigger with a distinct Crawlbase niche, but the capability phrasing is generic and lacks the natural scraping/crawling vocabulary users actually say.

Suggestions

Replace 'Manage data, records, and automate workflows' with concrete capabilities such as 'Crawl URLs, retrieve and delete stored crawl results, and check account credits'.

Add natural trigger terms users would say, e.g. 'Use when the user wants to scrape or crawl web pages with Crawlbase, manage stored crawl results, or check Crawlbase credits.'

Tie the 'when' clause to the actual action families (crawling jobs vs. storage vs. account) so it reads as scenario-specific rather than 'interact with Crawlbase data'.

Dimension	Reasoning	Score
Specificity	Phrases 'Manage data, records, and automate workflows' name the domain but the actions are minimal and generic rather than concrete capabilities, matching the score-2 anchor better than score-3 which requires concrete actions.	2 / 5
Completeness	Both a 'what' ('Manage data, records, and automate workflows') and an explicit 'when' clause are present, though the 'what' is generic and the 'when' could name concrete scenarios like crawl jobs or stored results.	4 / 5
Trigger Term Quality	The trigger 'Use when the user wants to interact with Crawlbase data' surfaces the product keyword but misses natural synonyms users say like 'scrape', 'crawl', or 'web scraping'.	3 / 5
Distinctiveness Conflict Risk	'Crawlbase integration' plus a Crawlbase-specific trigger carves a clear product niche with minimal overlap risk against other skills.	5 / 5
	Total	14 / 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/crawlbase/SKILL.md
Commit: f484c82

Reviewed: ~15 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.