SKILLEMALL.ai
GitHub ↗ RU Sign in

BF scrapfly-agent-rules

Cross-tool golden rules for an autonomous Scrapfly web agent connected to the Scrapfly MCP server (web_scrape, screenshot, extract, classify_block, the Cloud Browser lifecycle, snapshot/click/fill/type/press/scroll/select/drag, and WebMCP). Use when an LLM agent has access to the Scrapfly MCP toolset and needs to choose between stateless scraping and a stateful Cloud Browser session, decide when to call browser_unblock, or coordinate multi-tool flows.

ClawHub Agent Skills author: Scrapfly v1.0.0 MIT-0 2 files body ≈ 1 482 tokens Open the sourceclawhub.ai↗ analyzed 25 h ago

Cross-tool golden rules for an autonomous Scrapfly web agent connected to the Scrapfly MCP server (webscrape, screenshot, extract, classifyblock, the Cloud…

As a process F 43/100 · Will not run — References files that are not bundled: ../scrapfly-alerting/, ../scrapfly-cli/, ../scrapfly-scraper/

ReferenceAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
100
Quality 40%
72
Run on models
none yet
Process rating
F
43/100
Will not run
References files that are not bundled: ../scrapfly-alerting/, ../scrapfly-cli/, ../scrapfly-scraper/
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: ../scrapfly-alerting/
  • warning missing-ref reference to a missing file: ../scrapfly-cli/
  • warning missing-ref reference to a missing file: ../scrapfly-scraper/
  • warning missing-ref reference to a missing file: ../scrapfly-screenshot/
  • warning missing-ref reference to a missing file: ../scrapfly-extraction/
  • warning missing-ref reference to a missing file: ../scrapfly-crawler/
  • warning missing-ref reference to a missing file: ../scrapfly-browser/

Process rating: all ten parameters 43/100

Will not run. References files that are not bundled: ../scrapfly-alerting/, ../scrapfly-cli/, ../scrapfly-scraper/
  • 0Tools and files. 7 referenced file(s) missing: ../scrapfly-alerting/, ../scrapfly-cli/, ../scrapfly-scraper/
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 3 mutating operations with no state check
  • 100Steps. 14 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1482 tokens

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 455: enough signal without eating the budget
  • +4Structure: 5 headings
  • +3Step-by-step instructions: 14 items
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.

External checks

ClawHub: suspicious
The skill is a disclosed browser-automation helper, but it can act through logged-in sessions and handle an API key without a clear approval boundary for actions that may change accounts or websites.
LLM: suspicious (medium) · VirusTotal: · 9 Jul 2026