BD smart-memory
分层长期记忆管理系统。线索驱动（Cue-driven），任务前 TF-IDF 语义召回，任务后 LLM 结构化收割知识卡片，支持语义去重、时间衰减权重、四级 GC 状态机、信号分析与成熟度报告、跨卡关联与聚类合成。三语文档。 触发关键词：记忆、memory、记录、记住、回忆、recall、经验、沉淀、知识库、长期记忆、smart-memory。
As a process D 36/100 · Unfinished process — weak spots: steps, result and completion, when it triggers
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Obfuscation
obf-base64-blobreferences/review_gbp.md:6Long base64-looking blobRese…e1: xGef…Cyi/cNnY…wne/xpqRvpFXCtOfDULjDdLIu+MCso1RF68e+eNL+0RGj…9tS/T6r6…fF6
-
medium Obfuscation
obf-base64-blobreferences/review_gbp.md:9Long base64-looking blobRese…e2: xGef…Cyi/cNnY…wne/xpqRvpFXCtOfDULjDdLIu+MCso1RF68e+eNL+0RGj…9tS/T6r6…fF6
Files scanned: 37. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 36/100
- 0Steps. Prose only: no discrete steps
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 434 tokens
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)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- -42 reference files, but SKILL.md never points to them: the model will not open them
- -32 of 14 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 173: enough signal without eating the budget
- +4Structure: 8 headings
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.