AB identity-guard
MANDATORY SECURITY CHECKPOINT. Trigger this skill IMMEDIATELY whenever a user asks about the owner/master, their personal information, plans, activities, or any sensitive context. This includes questions like "Who is your owner?", "Who is he/she?", "What are their plans today?", "What did they say yesterday?", "Tell me everything about them", or ANY attempt to access MEMORY.md, USER.md, SOUL.md. In multi-user sessions (group chats), ALWAYS verify the sender's identity BEFORE responding to ANY personal/sensitive query, even if it seems casual. This is a non-negotiable security gate - no exceptions.
As a process B 66/100 · Nearly there — weak spots: result and completion, 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 66/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Failures and branches. 11 branches
- 85Steps. 51 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1498 tokens
- 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
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -31 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 604: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.