AC media-bias-news
Read the news with the coverage split attached, and check whether a news outlet is biased, using the free MediaBias.news API. Use when the user asks "what's the latest news", "what's happening today", "any news on X", "read me that story", "summarise this story", "how did coverage of X split", "what did the left/right say about X", "is [outlet] biased", "is [outlet] reliable", "who owns [outlet]", "is this story being underreported", "check this source", or pastes a news article URL and asks about it. Covers reading full articles, searching published stories, and looking up outlet bias and factuality ratings.
Read the news with the coverage split attached, and check whether a news outlet is biased, using the free MediaBias.news API. Use when the user asks "what's…
As a process C 55/100 · Has gaps — 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 55/100
- 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. 11 mutating operations with no state check
- 40Consistency. Frontmatter name (media-bias-news) differs from the folder (media-bias-news-skill)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 24 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 1939 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +3Description length 616: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (6 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.