BC soul-archive
Soul Archive — A digital personality persistence system + agentic memory. Builds your digital soul clone through everyday AI conversations, with proactive context injection, cross-session recall, failure-pattern warning, and pattern distillation. All data stored locally as plaintext JSON. Six modes: Soul Extract, Soul Chat, Soul Report, Soul Context Inject, Agent Memory Recall, AI Self-Improvement. | 灵魂存档 ---- 通过日常 AI 对话构建数字人格克隆体 + 主动智能体记忆。支持自动 hook、对话开始时主动注入人格摘要、跨会话召回、失败模式预警、行为模式蒸馏。数据全部本地明文 JSON。六大模式：灵魂沉淀、灵魂对话、灵魂报告、上下文注入、智能体记忆召回、AI 自我改进。Trigger words: soul extract, soul archive, soul update, soul chat, soul report, soul context, soul recall, soul warn, self-reflect, self-improve, learn from mistakes, 灵魂沉淀, 灵魂提取, 灵魂存档, 灵魂报告, 灵魂对话, 自我反思, 自我批评, 自我学习.
As a process C 55/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Write Edit Bash Grep Glob
Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "requirements"
Process rating: all ten parameters 55/100
- 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
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 39 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2188 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
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
- -249 emoji in the instructions: noise for the model
- -42 reference files, but SKILL.md never points to them: the model will not open them
- -37 of 9 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 758: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.