AF openclaw-memory-canonical
Lightweight file-based memory system for single-user AI agents. Uses markdown files only: HOT/WARM/COLD/BUFFER plus SCRATCH learnings, with tiered loading, WAL-lite writes, compaction recovery, weekly review, TTL archival, health checks, and a built-in self-improvement loop. Use when setting up or improving agent memory, preventing memory bloat or repeated mistakes, promoting recurring lessons into durable files, validating memory health, or when users mention memory systems, working buffers, episodic/semantic/procedural memory, learnings, weekly review, self-improvement, or how an AI agent should remember and improve between sessions.
As a process F 53/100 · Will not run — References files that are not bundled: references/package-tree.sha256
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7290 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/package-tree.sha256
Process rating: all ten parameters 53/100
- 0Tools and files. 1 referenced file(s) missing: references/package-tree.sha256
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 7290 tokens
- 100Steps. 132 steps
- 100Failures and branches. 30 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 643: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 132 items
- +4Has examples (13 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.