Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add coracoo/zspace_skill --skill file-organizergit clone --depth 1 https://github.com/coracoo/zspace_skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/coracoo/zspace_skill/file-organizer)<a href="https://agentmods.dev/skills/coracoo/zspace_skill/file-organizer"><img src="https://agentmods.dev/badge/skills/coracoo/zspace_skill/file-organizer.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00111 | $0.02278 |
| Opus 5 | $0.00056 | $0.01139 |
| Sonnet 5 | $0.00022 | $0.00456 |
| Haiku 4.5 | $0.00011 | $0.00228 |
Grade A, and why
file-organizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File Organizer — NAS 文件只读诊断
概述
通过组合 NAS MCP tool + file_organizer.py 脚本,只读诊断文件库的"重复"和"孤儿"问题。
所有写操作都不在 skill 里 — 报告生成后,用户手动决定怎么处理。
为什么只读
- 删除/移动会丢失数据,需用户确认
- 没法精确反查"哪些文件已打标签"(NAS 端点不暴露 label↔file 关联表)
- 诊断先看问题,修复单独做
3 个诊断命令
| 命令 | 用途 | 走哪个端点 |
|---|---|---|
audit-duplicates |
扫全盘找重复文件(按 size+ext 弱指纹) | /v2/file/list + /zspool/info |
audit-orphans |
找无标签 + 非影视目录的孤儿文件 | /v2/file/list + /zvideo/classification/dirs |
audit-all |
一键全跑(重复 + 孤儿) | 上面两个一起 |
工作流
场景 1:用户说"我 NAS 上有没有重复文件"
步骤:
- exec
python skills/file-organizer/file_organizer.py audit-duplicates --output /tmp/dups.json - 读 stdout 摘要 + JSON 详细清单
- 报告:总扫描 N 个文件,发现 X 组重复,共 Y 个冗余文件,占用 Z GB
- 列出前 20 组最大的重复(用户优先处理收益大的)
- ⚠️ 重要: 由于使用弱指纹(size+ext),误报率较高,需人工核对后再决定删除
场景 2:用户说"哪些文件没归类"
步骤:
- exec
python skills/file-organizer/file_organizer.py audit-orphans --output /tmp/orphans.json - 报告:总扫描 N 个文件,X 个孤儿(无标签 + 非影视)
- 建议处理:
- 大文件孤儿 → 考虑删除或归档
- 文档/图片孤儿 → 建议打标签(save_file_label)
- 临时/缓存文件 → 候选清理
场景 3:用户说"出综合诊断报告"
步骤:
- exec
python skills/file-organizer/file_organizer.py audit-all --output /tmp/full-report.json - 读 stdout(给人看) + JSON(详细数据)
- 两个 section:重复文件诊断 + 孤儿文件诊断
关键约束(必读)
- 只读诊断,不动 NAS — 这个 skill 是"找出问题",不是"修复"
- 修复走 MCP tool — 删/移/打标 用现有 MCP
remove/move/save_file_label,LLM 弹 UI 让用户批 remove不进回收站,不可逆 — 处理重复文件时优先move到_to_review/,人工确认后再删- 指纹策略(经 Task 7 验证):
- NAS
/v2/file/list返回的file_hash对真实文件也返回空字符串 - 无法精确去重 → 用
(size, ext)弱指纹分组 - 误报率高(同 size 同 ext 但内容不同),需人工核对
- NAS
- 扫描范围 — 默认所有池的
/<pool>/my/data/下(注意是/my/data/,不是/my/) - 性能约束 — 单线程顺序扫描,每页 200 条,每次请求后 sleep 0.1s(~10 req/s)
命令行选项
通用选项(所有命令都支持)
| 选项 | 默认值 | 说明 |
|---|---|---|
--pool <NAME> |
(所有池) | 限定扫描某个池 |
--output <PATH> |
(不写文件) | 将 JSON 详细结果写入文件 |
--sample <N> |
0(不限) | 限制扫描文件数(测试用) |
--min-size <MB> |
1 | 忽略小于 N MB 的文件 |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 193 lines · 111 tokens per session scan A 7d1b96d87dd9
file-organizer is a skill published in the GitHub repository coracoo/zspace_skill (21 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 2,278 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.