Smart File Organizer Pro

name: file-organizer-pro-en slug: file-organizer-pro-en displayName: Smart File Organizer Pro version: "1.0.0" description: "Smart file organizing; Pro: Rule engine + dedup + auto-classify" author: name: "smart" version: "1.0.0" category: "productivity" tags: - "文件" - "整理" - "效率"

What you get: a structured workflow that turns a stuck task into a repeatable one, delivering ready-to-use outputs and templates.

Overview

[TRACE 5.0 positioning] This skill is a hands-on tool. It delivers reusable artifacts and templates, not vague advice. The original GitHub skill (ComposioHQ/File Organizer) sorts loose files by type. The Pro version upgrades a one-off cleanup into a maintainable ordering system: a rule engine (matching on extension, naming pattern, date, source, and content keywords), duplicate detection (grouping by size and content fingerprint, separating true duplicates from version variants), and auto-classification with naming conventions that can be scripted and handed to a team. Everything follows a dry-run-first principle: a plan is produced before anything on disk changes.

What I can do

• Scan and profile: report type distribution, size share, time span, and naming entropy so you can see exactly where the mess is.
• Design the directory structure: project-based, timeline-based, type-based, or hybrid trees, with the maintenance cost of each spelled out.
• Write classification rules: a readable rule table (match condition, target folder, naming template, conflict handling) supporting compound conditions and priorities.
• Detect duplicates and redundancy: group by size, filename similarity, and content fingerprint; distinguish exact duplicates, version copies, and temporary caches, with keep/act recommendations.
• Generate executable scripts: cross-platform skeletons (PowerShell, Bash, Python) that default to dry-run mode and write an operation log.
• Set up long-term maintenance: an intake gate, periodic cleanup, and archival policy so the folder does not collapse again in three months.

What I cannot do

• No deleting anything without your confirmation; deletions are always proposed as a list first.
• No inspecting or transmitting sensitive content inside your files, and no content moderation.
• No replacement for a backup tool, and no responsibility for recovering lost data.
• No handling of protected system directories requiring elevated permissions.

Input specification

Provide: 1. Target directory path and its purpose (downloads folder, project drive, photo library); 2. A file listing or directory tree (exported via dir or ls; names, sizes, and modified times preferred); 3. Optional: existing naming habits, folders that must stay untouched, operating system and available scripting environment, whether cross-volume moves are allowed, and retention preferences.

Output specification

Delivered in Markdown: - Current-state diagnosis — type distribution | size share | main problems - Target directory tree (code block) - Classification rule table — priority | match condition | target folder | naming template | conflict handling - Duplicate file list — group | keep | act on | reason - Script skeleton (dry-run by default) - Rollback plan — log format and undo approach - Long-term maintenance SOP

Usage examples

Example 1

Input: A downloads folder with 3,000 mixed files and random names. Output: Diagnosis shows installers and temp files dominate disk usage; the proposed tree splits into inbox, documents, installers, media, and archive; rules file installers by extension and year; the duplicate list identifies 42 groups of same-name different-version files with keep-the-newest guidance; the script prints the planned moves before touching anything.

Example 2

Input: A team shared drive where multiple people uploaded several versions of the same documents. Output: A three-level project / phase / deliverable structure; a unified project_doctype_date_version naming template; duplicate detection separating identical copies (merge) from version progression (move to a history folder); plus team rollout notes and an intake convention for new files.

Example 3

Input: A ten-year photo library exported straight from cameras, to be organized by date and event. Output: A year / month / event structure; rules that cross-check modified time against date strings in filenames and prefer the earlier value on conflict; files with no date information listed separately for manual review; the script preserves original timestamps.

Error handling

• Special characters or overlong paths: output a high-risk file list and propose safe renames before any move.
• Missing or untrustworthy timestamps: cross-check filename dates, modified time, and folder context; flag conflicts for manual confirmation.
• Near-duplicates: never auto-delete; place them in a "similar files" group for comparison.

  更多技能请访问小葱技能站7w4.net。

• Cross-volume moves or low free space: estimate volume first and propose a batched execution order.
• Conflicting rules: match by descending priority and list overridden rules so they can be tuned.

Limitations and disclaimer

Bulk file operations are hard to reverse. Back up before executing and always run the dry-run pass to review the plan. The scripts provided are skeletons that you must review in your own environment before running; no responsibility is accepted for data loss caused by missing backups, unreviewed plans, or environment differences. For company material, follow your organization's data management policies.

Pro upgrade roadmap (Pay Skill reserved)

Billing will be enabled once the individual-creator payment channel launches. Free tier: single-directory diagnosis, structure proposal, base rule table, duplicate list, dry-run script skeleton. Pro tier: shared rule library across directories and devices, incremental organizing (new files only), content-fingerprint dedup with similarity reports, scheduled job and auto-archive templates, a team convention pack with training notes and checklists, operation logs with one-click rollback scripts, and priority support. Upgrade path: one-click switch to Pro as soon as billing opens.

Standard 5-step workflow

1. Prepare input: collect requirement keywords and business context.
2. Configure parameters: set required fields (input, output format, constraints).
3. Run: trigger the skill and follow the documented order.
4. Verify results: check against expected results and boundary conditions.
5. Reuse: save successful templates as shortcuts for next time.

Scenarios and triggers

Use this skill whenever you need, want, or are stuck on: High-frequency scenarios: - A downloads folder with thousands of files and no starting point - A desktop buried in temporary files where search is the only way to find anything - Multiple versions of one document with no clear latest copy - Low disk space and a need to locate the biggest consumers - Sorting and filtering material before migrating to a new machine - A shared drive lacking a naming convention - Reorganizing a photo library by date and event - Archiving deliverables after a project closes - Thousands of unnamed screenshots and screen recordings - Archiving finance or admin records by fiscal year - Collecting scattered assets that live outside the code repository - Establishing an intake gate to prevent future pileups - Wanting regular cleanup without risking accidental deletion - Handing colleagues an executable organizing standard - Deduplicating before a backup to reduce volume - Inconsistent folder structures across devices - Building a durable personal knowledge file structure Typical users: knowledge workers, designers and creators, engineers, admin and finance staff, and team leads maintaining shared drives.

这个 Skill 文档质量良好，功能描述清晰全面，场景覆盖广，示例丰富。但它本质上只是一份详细的使用指南，缺少实际可运行的脚本或工具，无法直接完成文件整理工作。适合需要学习文件整理方法论的用户，但不适合希望开箱即用的用户。