CC awublack-personal-memory-system
一个智能化、高可靠性的个人知识操作系统。它不仅自动同步你的 MEMORY.md 到 SQLite 数据库并提供自然语言查询，更通过 Git 版本控制、守护进程和日志监控，确保你的记忆**永不丢失、可追溯、可恢复**。 **使用场景**： (1) 用户需要查询“我过去对 AI 模型的看法？” (2) 用户希望系统自动记录重要决策，避免“心理笔记” (3) 需要一个可版本控制、可检索、可恢复的个人知识库 **核心功能**： - 自动将 MEMORY.md 中的 ### 标题块同步到 memory.db 数据库 - **智能查询**：接收自然语言问题，自动转换为 SQL 查询，从 memory.db 中精准检索并生成自然语言回答 - 与 Obsidian 和 Git 同步，实现个人知识库的完整闭环 **系统依赖**： - 必须存在 /home/awu/.openclaw/workspace-work/MEMORY.md - 必须存在 /home/awu/.openclaw/workspace-work/auto_sync_memory.py - 必须存在 /home/awu/.openclaw/workspace-work/memory.db - 必须存在 /home/awu/.openclaw/workspace-work/skills/awublack-personal-memory-system/query_memory.py - **必须存在** /home/awu/.openclaw/workspace-work/obsidian-vault/ （Obsidian 知识库） - **必须存在** /home/awu/.openclaw/workspace-work/git_sync_on_save.sh （Git 自动同步守护进程） - **必须存在** /home/awu/.openclaw/workspace-work/git_sync.log （同步日志） - **必须运行** git_sync_on_save.sh （每10秒检查并推送 Obsidian 变更） **重要**：此技能不提供任何外部 API 调用，所有数据均存储在本地，安全可靠。你的记忆存在于三个独立位置： 1. 本地工作区：MEMORY.md, memory.db, git_sync_on_save.sh 2. Obsidian 知识库：/home/awu/.openclaw/workspace-work/obsidian-vault/ 3. 远程 Git 仓库：https://github.com/awublack/obsidian-vault 任何一处损坏，其他两处均可恢复。
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- 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
-
low Dangerous commands
cmd-background-processREADME.md:22Starts a background / autostarted processnohup ./git_sync_on_save.sh > git_sync.log 2>&1 &
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1150 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
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. 2 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 35 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 549 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 1149: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +4Structure: 7 headings
- +3Step-by-step instructions: 35 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 36.