BC agent-sensei-ultimate
Reference reading, not a runtime policy: a field guide of 40 lessons from running AI agents 24/7 on real tasks — ethics, messaging security, context and memory layout, configuration safety, scheduled jobs, multi-model routing, budget, bot collaboration, epistemic hygiene, and how to improve checklists over time through human-reviewed proposals. Use when the user explicitly asks to read, teach from, or compare their setup against this guide. It installs nothing, schedules nothing and writes nothing. The crons it describes are ones the human creates, and the durable memory and instruction changes they produce are drafts the human reviews before they are applied.
Reference reading, not a runtime policy: a field guide of 40 lessons from running AI agents 24/7 on real tasks — ethics, messaging security, context and…
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 3. 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 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 11 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 744 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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 668: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 11 items
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.