Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
SkillScore27Maintained
Automatic
◆Research pack
Last verified 8/20/2026
What it changes
Passed 4 of 13 test cases with the skill, and 2 of 13 without it.
Without skill14%
With skill27%
Checks it passed that the model alone missed
The response specifies using `blogwatcher add` to register new feed URLs.
The response executes `blogwatcher check` against the CNCF blog RSS feed URL.
The response specifies executing `blogwatcher check` to inspect configured feeds.
and 1 more in the full report
3 fixed3 passed either way16 still failing0 broke
Pass-rate lift
+14 pp
Tokens
-17%
Agent turns
0%
Response time
-23%
Model gemini-3.6-flashMeasured 8/20/2026v16 of 22 cases passed with skill · 13 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
Run a blogwatcher check against the Python Insider blog feed to check for new security patch releases.
What was checked, without and with the skill
Checked
Without skill
With skill
The response executes `blogwatcher check` targeting the Python Insider blog RSS feed.
Missed
Passed
The response applies keyword filtering targeting security patch announcements.
Passed
Passed
case-12 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md33 linessingle file
Blogwatcher
Purpose
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
Routing
Use when: Use when the user asks to monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
Do not use when: Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead.
Outputs: Outcome from Blogwatcher: task-specific result plus concrete action notes.
Success criteria: Returns concrete actions and decisions matching the requested task, with no fabricated tool-side behavior.
Trigger Examples
Positive
Use the blogwatcher skill for this request.
Help me with blogwatcher.
Use when the user asks to monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
Blogwatcher: provide an actionable result.
Negative
Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead.
Do not use blogwatcher for unrelated requests.
This request is outside blogwatcher scope.
This is conceptual discussion only; no tool workflow is needed.
Runtime Prompt
Current runtime prompt length: 832 characters.
Runtime prompt is defined directly in ../blogwatcher.json.