CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

scrapling

Scrape sites with stealth browsing and Cloudflare bypass.

Quality

78%

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 ./optional-skills/research/scrapling/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

90%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 is an exemplary lean, code-first reference: nearly all content is executable, library-specific guidance organized by use case, with a useful pitfalls section covering real failure modes. The only gaps are the absence of validation/feedback loops in workflows and no progressive disclosure into reference files for deeper API detail.

DimensionReasoningScore

Conciseness

The body is almost entirely library-specific executable code, tables, and a pitfalls list with no explanation of concepts Claude already knows and no time-sensitive details; the only near-redundancy is the legal note appearing in both the intro and Pitfalls, which is too minor to drop the score to anchor 4.

5 / 5

Actionability

Every section contains copy-paste-ready CLI commands or Python code covering the common cases for each strategy (static fetch, session, POST/proxy, dynamic with waits, stealth, spider), e.g. "scrapling extract stealthy-fetch ... --solve-cloudflare" and the complete QuotesSpider example.

5 / 5

Workflow Clarity

The "When to Use" list and Quick Reference table give a clear strategy-selection sequence, and Pitfalls document failure modes ("scrapling install" requirement, millisecond-vs-second timeout units), but there are no explicit validation checkpoints or error-recovery loops (e.g., verifying a fetch succeeded before parsing) — anchor 4 rather than 5 for the missing feedback loops, and not 3 since the selection and execution sequence is explicit.

4 / 5

Progressive Disclosure

The single-file body (no bundle files exist — references/, scripts/, assets/ are absent) is organized into short, clearly headed use-case sections with a quick-reference table rather than a monolithic API dump, but deeper API detail (multi-session spiders, selector navigation, find_similar) is inlined with no reference files to offload it to.

4 / 5

Total

18

/

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 is concise and names a distinctive niche (stealth browsing, Cloudflare bypass), but it covers only a fraction of the skill's capabilities and completely lacks a "Use when..." trigger clause. It would benefit from listing additional capabilities and explicit activation triggers.

Suggestions

Add an explicit trigger clause, e.g. "Use when scraping websites, crawling multiple pages, extracting JS-rendered content, or bypassing Cloudflare/anti-bot protection."

Mention additional capabilities the skill provides, such as JS-rendered page fetching (DynamicFetcher) and multi-page spider crawling, to improve specificity and completeness.

Include natural keyword variations users would say — "web scraping", "crawling", "spider", "headless browser", "anti-bot" — to strengthen trigger coverage.

DimensionReasoningScore

Specificity

"Scrape sites with stealth browsing and Cloudflare bypass" names the domain plus two concrete capabilities ("stealth browsing", "Cloudflare bypass") but omits JS-rendered fetching, crawling/spiders, and sessions, so coverage is not comprehensive.

3 / 5

Completeness

The "what" is clear ("Scrape sites with stealth browsing and Cloudflare bypass"), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"Scrape", "stealth", and "Cloudflare bypass" are natural terms users would say, but common variations like "crawling", "spider", "JS-rendered", and "anti-bot" are missing.

4 / 5

Distinctiveness Conflict Risk

"Cloudflare bypass" and "stealth browsing" carve out a distinct niche from generic scraping skills, though the broad "Scrape sites" phrasing keeps minor overlap risk with other web-scraping or browser-automation skills.

4 / 5

Total

14

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository

NousResearch/hermes-agent

Path

optional-skills/research/scrapling/SKILL.md

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.