CtrlK
BlogDocsLog inGet started
Tessl Logo

web-scraping-olostep

Web scraping, crawling, and AI-powered answer extraction at scale

52

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/research-tools/capabilities/web-scraping-olostep/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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, mostly executable API reference but over-inlines the full parameter spec and lacks workflow checkpoints for its batch and async operations, with two broken curl examples. It would benefit from splitting the reference into a bundle file and adding status-polling guidance.

Suggestions

Move the per-endpoint parameter reference into a references/ file (e.g. REFERENCE.md) and keep SKILL.md as an overview with one-level-deep links.

Fix the Start Crawl and Start Batch curl examples so the JSON body is inside the -d '...' string and they are copy-paste executable.

Add an explicit workflow for async/batch operations: start crawl/batch/answer, poll the info endpoint until status is complete, then retrieve content — with a status-check loop.

DimensionReasoningScore

Conciseness

Largely avoids explaining concepts Claude already knows and gives a curl example per endpoint, but inlines a ~240-line parameter-by-parameter reference (e.g. the full remove_css_selectors default array and country list) that could be tightened or moved to a reference file.

3 / 5

Actionability

Most endpoints have concrete copy-paste curl examples with real env vars, but the Start Crawl and Start Batch examples have malformed JSON bodies broken outside the -d string, so they would not execute as written — more than a minor gap.

3 / 5

Workflow Clarity

Setup is sequenced, but batch and long-running async operations (crawls, answers, batches) lack explicit status-check/poll-then-retrieve checkpoints; per the guideline, missing validation for batch operations caps this at 3.

3 / 5

Progressive Disclosure

There is section structure (Setup, Capabilities, Usage, Use Cases, Discover More) and a discovery endpoint pointer, but the entire API reference is inlined in SKILL.md with no bundle files or one-level-deep references, fitting the anchor where content that should be separate is inline.

3 / 5

Total

12

/

20

Passed

Description

66%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 is specific and mostly distinctive, naming three concrete capabilities in a tight phrase. Its main weakness is the absence of any explicit "Use when" trigger guidance, which caps completeness at 3.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to scrape or crawl web pages, extract data from URLs, or get AI-synthesized answers from web sources."

Include natural synonyms users say (e.g. "extract data from a page", "get content from a website") alongside "web scraping" and "crawling".

Optionally surface a key capability like maps or batch scraping to round out comprehensive coverage.

DimensionReasoningScore

Specificity

Names three concrete actions ("Web scraping, crawling, and AI-powered answer extraction") but coverage is not fully comprehensive of the toolkit's surface (maps, batches, retrieve omitted), landing just above the 1-2-actions anchor.

4 / 5

Completeness

Provides a clear "what" but has no "Use when..." or equivalent explicit trigger clause, so completeness is capped at 3 per the judging guideline.

3 / 5

Trigger Term Quality

"Web scraping" and "crawling" are natural user phrases, but common synonyms and "at scale" leans slightly jargon-y, leaving a few natural terms missing per the anchor-4 example.

4 / 5

Distinctiveness Conflict Risk

The scraping/crawling/answer-extraction niche is mostly distinct with only minor overlap risk against other data-collection skills.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 missing, 1 suspicious

Warning

Total

14

/

16

Passed

Repository
gooseworks-ai/goose-skills
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.