BC ai-daily-news
Fetch global AI news data, synchronize platform capabilities, and invoke remote AI-news analysis. Use this skill when users ask about AI or machine learning news, such as "today's AI news", "latest AI news", "current AI news", "recent AI updates", or "what's new in AI". Also use it when users want to personalize AI news preferences, set up daily or weekly AI news automation guidance, generate AI news briefings, or turn AI news into workflow artifacts such as AI Coding tech radar, content materials, knowledge-base notes, product opportunity scans, or investment/strategy briefs. For explicit date queries about AI news, use get_news_dataset. Do not use this skill for non-AI news such as sports, politics, finance, or general breaking news.
As a process C 62/100 · Has gaps — weak spots: inputs and preconditions, consistency, execution cost
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Dangerous commands
cmd-persistencescripts/lib/automation_guidance.py:270Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)Create `~/Library/LaunchAgents/com.ai-daily-news.plist`:
code literal -
medium Dangerous commands
cmd-persistencescripts/lib/automation_guidance.py:291Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)Then run: `launchctl load ~/Library/LaunchAgents/com.ai-daily-news.plist`
code literal -
low Dangerous commands
cmd-cron-mentionscripts/lib/automation_guidance.py:243Mentions editing / listing crontab (string literal in code, not executed)crontab -e
code literal -
low Dangerous commands
cmd-cron-mentionscripts/lib/automation_guidance.py:371Mentions editing / listing crontab (string literal in code, not executed; code comment)# Install with: crontab -e
code literalcomment
Files scanned: 30. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 745 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
body-longSKILL.md body ≈ 9873 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "source"
Process rating: all ten parameters 62/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Consistency. Frontmatter name (ai-daily-news) differs from the folder (grounddata-ai-daily-news)
- 40Execution cost. Instruction body is 9873 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 217 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 22 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
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
- -214 emoji in the instructions: noise for the model
- -31 of 6 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 745: enough signal without eating the budget
- +4Structure: 51 headings
- +3Step-by-step instructions: 217 items
- +3Output format is stated explicitly
- +4Has examples (21 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.