workspace-organizer
v2.0.0任务文件组织与记忆管理。创建时间戳文件夹，支持会话恢复。
⭐ 1· 172·3 current·3 all-time
byHillsye@hou0515
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (organise workspace, save checkpoints, recover sessions) match the included scripts and SKILL.md. The scripts implement creating task folders, writing daily and long-term memory, updating per-task metadata, scanning and presenting recoverable tasks — all coherent with the stated purpose.
Instruction Scope
SKILL.md instructs running bundled Python/PowerShell scripts and operating under a workspace root ('.openclaw/workspace' or output/...). The instructions reference only the included scripts and local workspace paths; they do not instruct reading unrelated system files, network endpoints, or arbitrary environment secrets. Heartbeat functionality is described but requires the user to install/configure scheduling outside the skill.
Install Mechanism
No install spec or external downloads are used. All code is bundled with the skill. There are no brew/npm/remote fetch steps or archive extraction from untrusted URLs in the package.
Credentials
The skill requests no environment variables or credentials. Scripts read common location variables (APPDATA, HOME, USERPROFILE) to locate the user workspace directory — this is expected for a local workspace tool and proportional to its function.
Persistence & Privilege
always:false and no special agent-level persistence is requested. The skill only writes files under the user's workspace (memory files, .task-meta.json) and provides optional PowerShell wrappers; it does not modify other skills or global agent settings.
Assessment
This skill appears coherent and local-only: it writes/reads files under your OpenClaw workspace and uses bundled Python/PowerShell scripts. Before installing or running: (1) review the scripts if you want to be certain where files will be written (they target ~/.openclaw/workspace or common AppData paths); (2) run the Python scripts manually the first time to confirm behaviour (they have no network calls); (3) be aware the PowerShell helpers are shipped as .txt and must be renamed to .ps1 to use — only do that if you trust the package; (4) if you rely on automated heartbeat checks, configure scheduling explicitly rather than enabling broad auto-execution. If you want extra assurance, run the package in a test workspace or sandbox first.Like a lobster shell, security has layers — review code before you run it.
latestvk97fd728aby3tpt7mhm1ht7f0x836x6g
License
MIT-0
Free to use, modify, and redistribute. No attribution required.