AC proxy-web-fetch
Proxy Web Page Fetch Tool - Fetches and parses web page content into structured Markdown or text via the OpenClaw Manager proxy. Use when: - Need to fetch and read the content of a web page by URL - Need to convert web pages to Markdown or plain text format - Need to extract page content with or without images - Need to get page metadata (title, description, keywords) - Need to control caching, image retention, or summary options for fetched content - User asks to "read a URL", "fetch a page", "grab the content of a web page", "scrape" or "crawl" a URL This skill routes all fetch requests through the Manager Web Fetch Proxy (configured via `WEB_FETCH_PROXY_URL` env var, required), which handles API key management automatically — no manual configuration needed. Do NOT confuse with web search — this skill fetches a specific URL's content, it does not perform keyword searches.
As a process C 56/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, progress reporting
How to improve
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 56/100
- 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
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 75Steps. 3 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 948 tokens
- 100Running it twice. No mutating operations
- low The response is described with custom markup (5 tags): a typed call is more reliable
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 889: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 10 headings
- +3Step-by-step instructions: 3 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.