BF agent-design-review
Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools, memory/context, failure handling, cost, and safety — with prioritised findings and fixes.
Review an LLM agent design and find where it will be unreliable, expensive, or unsafe.
As a process F 56/100 · Will not run — References files that are not bundled: ../agent-spec/SKILL.md, ../llm-cost-latency-budget/SKILL.md, ../llm-guardrails-spec/SKILL.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../agent-spec/SKILL.md - warning
missing-refreference to a missing file: ../llm-cost-latency-budget/SKILL.md - warning
missing-refreference to a missing file: ../llm-guardrails-spec/SKILL.md - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 56/100
- 0Tools and files. 3 referenced file(s) missing: ../agent-spec/SKILL.md, ../llm-cost-latency-budget/SKILL.md, ../llm-guardrails-spec/SKILL.md
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 998 tokens
- 100Running it twice. Mutating operations check current state
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)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 404: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 16 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.