AC layered-memory-manager
Multi-tier (L1/L2) memory management skill for OpenClaw agents. Use when: (1) reading, writing, organizing, or searching memories, (2) deciding what to remember or forget, (3) performing memory hygiene (L1↔L2 sync, promotion, demotion), (4) answering questions about prior sessions, decisions, or preferences. Supports explicit forget (by tag or keyword), manual pin/promote via [[tag]] triggers, and memory_health status. This is the agent's own layered memory system — the authoritative guide for where memories live and how to keep them accurate.
As a process C 57/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5805 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 57/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 21 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 10 branches
- 70Execution cost. Instruction body is 5805 tokens
- 85Steps. 124 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (45 tags): a typed call is more reliable
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)
- -213 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 549: enough signal without eating the budget
- +4Structure: 52 headings
- +3Step-by-step instructions: 124 items
- +3Output format is stated explicitly
- +4Has examples (14 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.