AC lobster-memory
真正的长期记忆管理技能。自动维护记忆文件、定期归档、智能提醒。 包含 Working Buffer 协议、Memory Maintenance 清单、自动学习日志。 When to use: - User asks about prior work, decisions, dates, people, preferences - Context exceeds 60% and needs compaction - Setting up autonomous daily learning and memory maintenance - Creating long-term memory system for AI assistant This skill transforms AI from stateless chatbot to stateful assistant with persistent memory.
真正的长期记忆管理技能。自动维护记忆文件、定期归档、智能提醒。 包含 Working Buffer 协议、Memory Maintenance 清单、自动学习日志。 When to use: - User asks about prior work, decisions, dates, people…
As a process C 53/100 · Has gaps — 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "zhName" - note
frontmatter-keyunknown frontmatter key "authors" - note
frontmatter-keyunknown frontmatter key "created"
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 25 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 824 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)
- +3Output format is not stated: the model decides each time
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 2 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 416: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (8 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.