AB layered-memory-architecture
Build cheap, truthful long-term memory for agents with a layered architecture instead of a memory blob. Design, explain, audit, or improve a system that separates hot canon, durable topic doctrine, project-scoped working memory, episodic logs, and generated live summaries. Use when creating token-efficient agent memory, reducing memory bloat and context cost, comparing layered memory against generic persistent-memory systems, defining memory boundaries, improving retrieval trust, or migrating from blob memory to a layered model.
As a process B 66/100 · Nearly there — weak spots: when it triggers, 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: 10. 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
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 4 branches
- 85Steps. 84 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1459 tokens
- 100Progress reporting. Reports progress
- low 11 top-level sections: this looks like several domains in one skill
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 534: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 84 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (7 of 8)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.