AC Agents
Design, build, and deploy AI agents with architecture patterns, framework selection, memory systems, and production safety.
Design, build, and deploy AI agents with architecture patterns, framework selection, memory systems, and production safety.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
For the model run — optional
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Instruction override
en-ignore-previoussecurity.md:11Instruction-override phrase ("ignore previous instructions") (documentation table row; documentation of a security skill)| **Persona hijacking** | "Ignore previous instructions..." | Agent abandons safety constraints |
tablesecurity skill -
low Risky intent
intent-offensive-securitysecurity.md:16Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| **Chained exploitation** | Combining read+write+exec | Privilege escalation |
-
low Risky intent
intent-offensive-securitysecurity.md:26Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| **Credential harvesting** | Extracting secrets from environment |
Files scanned: 7. 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)
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 526 tokens
- 100Progress reporting. Reports progress
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 123: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.