AB rss-feed-generator
Generate valid RSS 2.0 or Atom 1.0 feeds from web pages that contain post lists but lack a native feed. Triggers on phrases like "generate a feed for", "create an RSS feed from", "make an Atom feed for", "this page has no RSS", or any request to produce a feed URL or feed XML from a blog/news/post-list page. The skill fetches the page, extracts post metadata, and outputs well-formed feed XML plus a self-hostable HTML wrapper with an embedded feed discovery link tag.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, consistency, progress reporting
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (rss-feed-generator) differs from the folder (rss-generator-skill)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 20 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 1878 tokens
- 100Running it twice. Mutating operations check current state
- low The response is described with custom markup (6 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)
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 470: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 20 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.