AD MemCore 记忆核心
v2.1.0 (WAL+VFM enhanced). Five-tier adaptive memory system with WAL indexing, Working Buffer search, and VFM scoring. 为 OpenClaw 打造的五层自适应记忆检索系统，四层自进化记忆模型（L1轨迹→L2模式→L3世界模型→技能结晶），反馈驱动的价值评分，自动维护与健康诊断。适用场景：(1) 带降级保障的记忆搜索，(2) 带历史故障诊断的健康检查，(3) 每日散会流程自动模式归纳，(4) 生成启动简报替代全量MEMORY.md注入节省92% token，(5) 跨领域模式关联检查防止重复犯错。 Five-tier adaptive memory retrieval, self-evolving four-layer memory model (L1 trace → L2 pattern → L3 world model → Skill crystallization), feedback-driven value scoring, auto-maintenance, and health diagnostics for OpenClaw agents. Use when: (1) Searching memory with fallback guarantees, (2) Running health checks with historical fault diagnosis, (3) Daily 散会流程 with auto pattern induction, (4) Generating startup brief to replace full MEMORY.md injection, (5) Checking cross-domain pattern associations to prevent recurring failures.
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (MemCore 记忆核心) differs from the folder (memcore-memory)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 6 steps
- 100Execution cost. Instruction body is 866 tokens
- 100Progress reporting. Reports progress
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)
- +3Description length 847: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.