AB Brief
Turns raw material into decision-ready briefs: executive summaries, status updates, meeting pre-reads, and decision documents. Use when asked to brief someone, write a TL;DR or weekly update, prepare a board, investor, or incident update, hand off a project, compare options with a recommendation, or condense a long report, thread, transcript, or doc pile into what the reader needs to act. Also when updates run long, readers skim past the point, or the lede keeps getting buried. Not for plain compression with no decision to serve, or for recurring digests pulled from external sources.
As a process B 73/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
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 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 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
- 100Tools and files. No external tools needed
- 100Steps. 42 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3261 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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 590: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 42 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.