AB Digest
Curates news, feeds, and industry sources into personalized recurring digests: sourcing, filtering, ranking, and delivery. Use to set up a daily briefing or morning/evening news roundup, track competitors, an industry, people, or markets, or run a scheduled or weekly update. Also when a digest feels too long or repetitive, keeps missing stories, or a rumor needs checking before it ships. Covers source vetting, deduplication, single-source holds, corrections, urgent alerts, slow news days, and channel formats (email, Slack, Telegram, audio); learns format, timing, and depth preferences from reactions. Not for summarizing documents the user provides or internal business reporting.
As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 7 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 100Tools and files. No external tools needed
- 100Steps. 39 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2725 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 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
- +5Description has no quoted example phrases that should trigger the skill
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 687: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 39 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.