AD jina-reader
Fetch the markdown content of any webpage using Jina AI's Reader API (r.jina.ai), or search the web using Jina AI's Search API (s.jina.ai). Use this skill whenever you need to read a URL and get clean LLM-friendly markdown output, extract article/documentation content from a page, or search the web and retrieve rich results with content. Triggers on: read this URL, fetch this page, get the content of, what does this page say, summarize this link, search the web for, look up, or any request requiring clean markdown from a URL.
As a process D 46/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, consistency
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 46/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (jina-reader) differs from the folder (jina-ai-skill)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 75Steps. 3 steps
- 100Execution cost. Instruction body is 459 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 531: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 3 items
- +4Has examples (5 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.