AD boss-interaction
Governs all interactions with the boss (Sếp) in Telegram and chat. MUST trigger for every message from boss. Enforces zero-question policy: always call a tool before asking anything. Covers morning brief automation, command routing, intent detection, Vietnamese communication style, and escalation rules.
As a process D 39/100 · Unfinished process — weak spots: steps, when it triggers, inputs and preconditions
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Governs all interactions with the boss (Sếp) in Telegram and chat.… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 39/100
- 0Steps. Prose only: no discrete steps
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (boss-interaction) differs from the folder (ads-claw3)
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 1192 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +3No numbered steps or checklist
- +1No license
- +2Single-language instructions
- +3Description length 304: enough signal without eating the budget
- +4Structure: 14 headings
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.