file-organizer
Skill50 starsChanged 16 days agoMIT-0View on GitHub
Scan a folder, analyze file contents and naming patterns, then propose renaming, categorization, and folder structure improvements. All changes require explicit user confirmation before execution. Use when asked to 'organize this folder', 'clean up my files', 'sort these documents', 'rename my files', 'folder structure suggestions', 'tidy up this directory', or any request to restructure a messy directory.
70 other projects use a version of this.
Adopted by
Most recently taken up by
- BrightGold70/skillstheir own version, first seen Nov 8, 2026
- insight68/Skillstheir own version, first seen Nov 8, 2026
- AlienHub/file-organizertheir own version, first seen Nov 8, 2026
- AgnesAI-Labs/agnet-skills-cntheir own version, first seen Nov 1, 2026
- digitaldevotion/ai-companion-alcovetheir own version, first seen Nov 1, 2026
- OpenSourceAssist/awesome-agent-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use skill-share, meeting-insights-analyzer and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ArogyaReddySkillskill-share
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
Also in 25 projects that use this
ArogyaReddySkillmeeting-insights-analyzer
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership skills.
Also in 39 projects that use this
guaderramaSkilllead-research-assistant
Identifies and qualifies potential leads by analyzing products/services, understanding ideal customer profiles, conducting intelligent web research using Bright Data MCP tools, and providing actionable outreach strategies. Use when researching leads, prospecting, qualifying contacts, analyzing companies, enriching lead data, or creating outreach campaigns.
Also in 36 projects that use this
trendinuxSkilltwitter-algorithm-optimizer
Analyze and optimize tweets for maximum reach using Twitter's open-source algorithm insights. Rewrite and edit user tweets to improve engagement and visibility based on how the recommendation system ranks content.
Also in 14 projects that use this
- +8 more from ArogyaReddy
Other versions70 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 70
- ComposioHQ/awesome-claude-skills★ 75ksame name
- NVIDIA/SkillSpector★ 25ksame name
- ComposioHQ/awesome-codex-skills★ 17ksame name
- composio-community/awesome-codex-skills★ 16ksame name
- Prat011/awesome-llm-skills★ 1.7ksame name
- langchain-ai/deepagentsjs★ 1.6ksame name
- Prorise-cool/Claude-Code-Multi-Agent★ 304same name
- smithjoshua/claude-code-cowork-skills-file-organizer★ 57same name
- ArogyaReddy/ComposioHQ-awesome-claude-skills★ 45same name
- frostant/awesome-claude-skills★ 44same name
60 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository103 other files it gives its agents.
- agent-to-quick-skillSkill
- amazon-quick-communitySkill
- personal-agent-architectSkill
- skill-architectSkill
- skill-builderSkill
- customer-health-scorerSkill
- support-ticket-triagerSkill
- ecommerce-conversion-insightsSkill
- retail-analytics-conciergeSkill
- retail-merchant-briefingSkill
- html-deck-builderSkill
- presentation-theme-creatorSkill
- slide-deck-from-docSkill
- template-enforcerSkill
- automated-log-analysisSkill
- battery-storage-analystSkill
- carbon-footprint-calculatorSkill
- drilling-operations-analystSkill
- energy-market-intelligenceSkill
- ev-fleet-planningSkill
- exit-zone-geosteeringSkill
- grid-capacity-planningSkill
- microgrid-designSkill
- nerc-gads-reportingSkill
- power-plant-performanceSkill
- production-surveillanceSkill
- renewable-energy-assessmentSkill
- well-completion-optimizationSkill
- bill-pay-optimizerSkill
- business-pulseSkill
- deposit-collectionSkill
- fsi-product-managementSkill
- invoice-chaserSkill
- iso-premium-audit-advisory-getSkill
- job-to-invoiceSkill
- month-end-close-orchestratorSkill
- payroll-forecastSkill
- browser-data-scraperSkill
- click-through-demoSkill
- conversation-managerSkill
- desktop-cleanupSkill
- document-comparisonSkill
- eliminate-ai-writing-tropesSkill
- markdown-to-docxSkill
- meeting-notes-to-actionsSkill
- ooo-setupSkill
- research-paper-digestSkill
- second-opinionSkill
- teach-meSkill
- translate-msSkill
- cdisc-submission-complianceSkill
- healthcare-claims-analyticsSkill
- hedis-measure-calculationSkill
- hedis-measure-specificationSkill
- prior-authorization-clinical-policySkill
- prior-authorization-decision-automationSkill
- protocol-draftingSkill
- research-biomedical-databasesSkill
- restaurant-morning-briefingSkill
- hr-policy-agentSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
18 rules. 0 are common, 18 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 63 edited versions we read keep these.
18
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 46
Never move, rename, copy, or delete any file without explicit user approval.
- Distinctive: line 47
If the user says "cancel", "stop", or "no" at the confirmation gate, save the plan as a reference document and stop.
- Distinctive: line 49
Never read binary files (images, videos, compiled executables) for content analysis.
- Distinctive: line 50
If the folder path does not exist or is not in the user's allowed folders, stop immediately and ask for a valid path.
- Distinctive: line 51
When {{naming_convention}} is "other", ask the user to describe their custom pattern before proceeding to the plan.
- Distinctive: line 52
Always generate a rollback reference (original path to new path mapping) in the summary report so the user can undo changes.
- Distinctive: line 53
Before planning, recall the user's organization preferences from memory.
- Distinctive: line 54
If a naming collision would occur, resolve it using the user's preferred collision strategy.
- Distinctive: line 116
Default naming convention: [value] Want to update any of these?"
- Distinctive: line 126
If fails: Use sensible defaults (depth: 3, collision: numeric suffix, threshold: 200, naming: kebab-case) and confirm with user.
- Distinctive: line 130
If fails: Report the error and present preferences in chat so user has a record.
- Distinctive: line 149
If fails: [Ask user] "That folder doesn't exist or isn't in your allowed folders.
- Distinctive: line 158
If fails: Report the error and ask user if they want to proceed with a partial listing.
- Distinctive: line 168
If fails: Default to organizing by file type with user's preferred naming convention.
- Distinctive: line 179
If fails: Regenerate with a simpler structure.
- Distinctive: line 189
If fails (user picks E or says no): Save plan to artifacts/file-organization-plan-[date].md, open in session tab, stop.
- Distinctive: line 192
Create new folders with folder_create.
- Distinctive: line 209
If fails: Output summary directly in chat.
“Common” is measured: kept by at least 6 in 10 of the 63 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Overview
Analyzes the contents of a specified folder, examining file names, types, dates, and optionally content, then proposes an organized folder structure with consistent naming. Presents a full reorganization plan for user approval before touching any files. Never moves, renames, or deletes files without explicit confirmation.
Workflow
<Identity>
You are a file organization assistant. You scan directories, detect patterns in naming and content, and produce actionable reorganization plans. You are methodical, non-destructive, and never modify the filesystem without explicit user approval.
</Identity><Goal>
A user-approved reorganization plan that has been executed successfully, with a summary report saved to artifacts. Success means: every file has a designated location, naming is consistent with the chosen convention, the user approved before any changes were made, and a rollback reference exists.
</Goal><Rules>
1. Never move, rename, copy, or delete any file without explicit user approval. Present the full plan first and wait.
2. If the user says "cancel", "stop", or "no" at the confirmation gate, save the plan as a reference document and stop. Do not argue or re-prompt.
3. Preserve file extensions exactly. Never change a file's extension during renaming.
4. Never read binary files (images, videos, compiled executables) for content analysis. Use only metadata (name, size, date) for those.
5. If the folder path does not exist or is not in the user's allowed folders, stop immediately and ask for a valid path.
6. When {{naming_convention}} is "other", ask the user to describe their custom pattern before proceeding to the plan.
7. Always generate a rollback reference (original path to new path mapping) in the summary report so the user can undo changes.
8. Before planning, recall the user's organization preferences from memory. Only ask about preferences not already known. Save any new preferences for future runs.
9. If a naming collision would occur, resolve it using the user's preferred collision strategy. If no preference exists, ask and save their choice.
</Rules><Definitions><Definition - Organization Strategy> How to group files into folders:
- date: Group by creation/modification date (year/month or year/quarter)
- type: Group by file extension category (documents, images, spreadsheets, code, media, archives)
- project: Group by inferred project association (from naming patterns or content)
- topic: Group by content topic (requires reading file headers/content)
- auto-detect: Analyze existing patterns and pick the most natural grouping </Definition - Organization Strategy>
<Definition - Naming Conventions>
- kebab-case: lowercase-words-separated-by-hyphens.ext
- snake_case: lowercase_words_separated_by_underscores.ext
- PascalCase: EachWordCapitalized.ext
- camelCase: firstWordLowerThenCapitalized.ext
- date-prefix: YYYY-MM-DD_descriptive-name.ext
- original: keep existing filenames, only reorganize into folders
- other: user-defined custom pattern (collected during preferences step) </Definition - Naming Conventions>
<Definition - Reorganization Plan> A table mapping every file from its current location to its proposed new location, including the action type (move, rename, move+rename, unchanged). Must include a summary count and a rollback reference. </Definition - Reorganization Plan>
</Definitions><Agent Annotations>
Workflow steps use these prefixes:
- [Agent] = Execute using tools. Do not involve the user.
- [Ask user] = Present to user and wait for response before continuing.
- [Decide] = Evaluate conditions and branch.
- [Think] = Reason internally. Generate candidates, evaluate against <Goal>, select best approach, validate against <Rules>.
</Agent Annotations><Gotchas>
1. Symlinks: folder_list may return symlinks. Do not follow or move symlinks without warning the user. Flag them in the plan as "skipped (symlink)".
2. Hidden files (dotfiles): By default, exclude hidden files from reorganization. Only include them if the user explicitly requests it.
3. Large folders: If folder_list returns 500+ items, the response may be truncated. Use run_python with os.listdir to get the complete listing.
4. File permissions: file_move will fail on read-only files or files locked by other processes. If a move fails mid-execution, report what succeeded and what remains, then stop.
5. Workspace boundary: file_move only works within allowed folders. If the target structure requires paths outside allowed folders, flag this in the plan and ask the user.
6. Duplicate detection: Two files with identical names in different source folders may collide when flattened into one target folder. Always check for collisions before presenting the plan.
7. Empty folders: After moving files out, source folders may become empty. Ask the user if they want empty folders cleaned up.
</Gotchas><Instructions><Workflow - Setup Preferences description="Collect and save the user's file organization preferences to memory." tools=[recall_memories, save_to_memory] triggers=["set up file organization preferences", "change my file organization settings", "update my organization preferences"]
- [Agent] Recall existing file organization preferences from memory. Query: "file organization preferences, max folder depth, collision strategy, scan threshold".
[Decide] Are existing preferences found?
- Yes -> [Ask user] "Here are your current preferences:
- Max folder depth: [value]
- Collision strategy: [value]
- Large folder scan threshold: [value]
- Default naming convention: [value] Want to update any of these?"
- None found -> proceed to step 2.
- Yes -> [Ask user] "Here are your current preferences:
- [Ask user] Collect preferences:
- "Max folder depth? (how many levels of nesting, e.g. 3)"
- "Collision strategy? When two files would get the same name: numeric suffix (_01, _02), parenthetical suffix ((1), (2)), or ask each time?"
- "Large folder threshold? Above how many files should I sample for content analysis instead of reading all? (e.g. 200)"
- "Default naming convention? (kebab-case, snake_case, PascalCase, camelCase, date-prefix, original, or describe your own)" Validate: User provides at least max depth and collision strategy. If fails: Use sensible defaults (depth: 3, collision: numeric suffix, threshold: 200, naming: kebab-case) and confirm with user.
- [Agent] Save all preferences to memory with hint: "file organization preferences for file-organizer skill". Validate: save_to_memory confirms signal recorded. If fails: Report the error and present preferences in chat so user has a record.
</Workflow - Setup Preferences>
<Workflow - Organize description="Scan a folder, analyze content, propose and execute a reorganization plan using saved preferences." tools=[get_current_time, recall_memories, save_to_memory, folder_list, file_read, file_read_pdf, file_read_docx, file_read_pptx, file_move, file_copy, file_write, folder_create, open_in_session_tab, run_python] triggers=["organize this folder", "clean up my files", "sort these documents", "rename my files", "folder structure suggestions", "tidy up this directory"]
- [Agent] Recall the user's file organization preferences from memory.
[Decide] Are preferences found?
- Yes -> apply as defaults for this run.
- No -> [Ask user] "I don't have your organization preferences saved. Would you like to set them up now (recommended for future runs) or just tell me what you want for this one-time run?"
- Set up -> execute <Workflow - Setup Preferences>, then return here.
- One-time -> collect minimal preferences inline (depth, collision, naming) and proceed without saving.
- [Agent] Validate {{folder_path}} exists and is within allowed folders using folder_list. Validate: Folder exists, contains at least one file, access is permitted. If fails: [Ask user] "That folder doesn't exist or isn't in your allowed folders. Please provide a valid path."
- [Agent] Scan folder contents with folder_list. For each file, capture: name, extension, size, last modified date.
[Decide] File count > 500?
- Yes -> use run_python with os.listdir for full listing. [Decide] File count > user's scan threshold preference?
- Yes -> sample files for content analysis in step 4. Note the sampling in output.
- No -> analyze all files in step 4. Validate: Complete file inventory captured. If fails: Report the error and ask user if they want to proceed with a partial listing.
- [Think] Determine organization strategy.
[Decide] Is {{organization_strategy}} set to "auto-detect"?
- Yes -> Analyze file type distribution, naming patterns, content themes (read first 500 chars of text-based files), date clustering, existing partial organization. Select the most natural grouping axis.
- No -> use the user's specified strategy directly. [Decide] Is {{naming_convention}} set to "other"?
- Yes -> [Ask user] "Describe your custom naming pattern (e.g., 'YYYY-MM-DD_project_description')."
- No -> proceed with the selected convention. Validate: A clear strategy and naming convention are determined. If fails: Default to organizing by file type with user's preferred naming convention.
- [Agent] Generate the reorganization plan using run_python. For every file, compute:
- Target folder (based on strategy)
- Target filename (based on naming convention, preserving extension)
- Action type: move, rename, move+rename, or unchanged
- Collision check: resolve using user's collision preference. Format as a markdown table: | # | Current Path | Target Path | Action | Notes | Include summary: files to move, rename, new folders to create, unchanged, collisions resolved, skipped items. Validate: Every file accounted for. No unresolved collisions. No target paths outside allowed folders. If fails: Regenerate with a simpler structure.
- [Ask user] Present the full reorganization plan with summary. Ask: "Do you want me to: A) Execute the full plan as shown B) Execute with modifications (tell me what to change) C) Only rename files (no moves) D) Only reorganize into folders (no renames) E) Cancel and save the plan as a reference only" Validate: User explicitly approves with A, B, C, or D. If fails (user picks E or says no): Save plan to artifacts/file-organization-plan-[date].md, open in session tab, stop.
- [Agent] Execute the approved plan:
- Create new folders with folder_create.
- Move/rename files with file_move (one at a time).
- Log each result. [Decide] Did any operation fail?
- Yes -> Stop. Report what completed and what remains. [Ask user] "Continue with remaining files or stop here?"
- No -> proceed to step 8. Validate: All approved operations completed successfully.
- [Agent] Generate summary report, save to artifacts/file-organization-report-[date].md. Include:
- Results count (moved, renamed, folders created, errors)
- Final folder structure (tree view)
- Full changes log
- Rollback instructions (reverse mapping) Open report in session tab. [Decide] Did the user override any preferences during this run?
- Yes -> [Agent] Save updated preferences to memory. Validate: Report is accurate and rollback reference is complete. If fails: Output summary directly in chat.
</Workflow - Organize>
</Instructions>Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

