pedrojaimot-file-organizer
Skill0 starsChanged 26 days agoMITView on GitHub
Organizes Pedro Jaimot's personal files (Downloads, Documents, Desktop, Google Drive at pedrojaimot@gmail.com) into his standard personal structure, finds duplicates, and enforces his naming rules. Use when Pedro asks to clean up, sort, organize, dedupe, or archive personal files or folders. Not for Atlas Ocean Voyages / Mystic Cruises work files.
In this repository60 other files it gives its agents.
- 21st-aiSkill
- 21st-cli-useSkill
- 21st-design-syncSkill
- 21st-registrySkill
- 21st-ui-buildSkill
- 21st-ui-exploreSkill
- 21st-ui-reviewSkill
- ab-testingSkill
- ad-creativeSkill
- adsSkill
- ainoteSkill
- ai-seoSkill
- analyticsSkill
- asoSkill
- attributionSkill
- cavemanSkill
- churn-preventionSkill
- cold-emailSkill
- co-marketingSkill
- community-marketingSkill
- competitor-profilingSkill
- competitorsSkill
- content-strategySkill
- copy-editingSkill
- copywritingSkill
- croSkill
- customer-researchSkill
- directory-submissionsSkill
- emailsSkill
- eventsSkill
- free-toolsSkill
- imageSkill
- influencer-marketingSkill
- launchSkill
- lead-magnetsSkill
- marketing-councilSkill
- marketing-ideasSkill
- marketing-loopsSkill
- marketing-planSkill
- marketing-psychologySkill
- meeting-assistantSkill
- offersSkill
- onboardingSkill
- paywallsSkill
- popupsSkill
- pricingSkill
- product-marketingSkill
- programmatic-seoSkill
- prospectingSkill
- public-relationsSkill
- referralsSkill
- revopsSkill
- sales-enablementSkill
- schemaSkill
- seo-auditSkill
- signupSkill
- site-architectureSkill
- smsSkill
- socialSkill
- videoSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 72
Keep the copy with the best name or best location (newest if they tie).
- Distinctive: line 85
After a "yes": create the folders, run the moves, write the log, and print the counts.
- Distinctive: line 94
If the Google Drive connector is available, use the same structure and rules.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Pedro Jaimot — Personal File Organizer
Personal files only. Employer files (Atlas Ocean Voyages, Mystic Cruises, charter/MICE client material) are out of scope: flag them, never sort them into personal folders.
Operating rules (non-negotiable)
- Plan before action. Analyze → propose plan → wait for explicit "yes" → execute.
- No deletes without approval. Duplicates and junk go to
99_Archive/_To-Delete/first; permanent delete only on a second explicit approval. - Log every move to
_organizer-log/YYYY-MM-DD.tsv(old_path<TAB>new_path, in execution order) at the target root so any run can be undone. - Move with
mv -nonly. It preserves timestamps, works across volumes, and never overwrites. Never usecp(it leaves the source behind, and removing it is a delete). On name clash, append_v2,_v3. - Stop and ask on anything sensitive (IDs, passwords, financial or medical records) or ambiguous. Never print their contents.
- Concise output. Tables and lists only. No long explanations.
Standard structure
Personal/
├── 00_Inbox/ # landing zone; empty weekly
├── 01_Admin/ # IDs, passports, visas, licenses, insurance, legal, home, vehicles
├── 02_Finance/ # banking, taxes/<YYYY>, investments, receipts/<YYYY>, contracts
├── 03_Career/ # CV, certifications, training, personal copies of performance records, network
├── 04_Health/ # medical, fitness, wellness, stress and focus
├── 05_Projects/ # personal ventures and business ideas, one folder each
├── 06_Learning/ # courses, books, research, AI/automation notes
├── 07_Travel/ # personal trips: <YYYY>-<destination>/
├── 08_Media/ # photos/<YYYY>, videos/<YYYY>, creative work
├── 09_Reference/ # manuals, templates, saved articles
├── 99_Archive/ # inactive >12 months, mirrored by area; _To-Delete/
└── _Work-Flagged/ # Atlas / Mystic files found in personal space, untouched, for Pedro to moveRules:
- Max depth: 3 levels below an area folder. Flatten anything deeper.
- New top-level folders only with Pedro's approval.
- Personal travel →
07_Travel. Charter/MICE operations →_Work-Flagged.
Naming convention
YYYY-MM-DD_area_short-description.ext
- Lowercase, hyphens, no spaces, no
final,v2 (1),copy. - Date = document date, not download date (use the file's mtime if no date appears in the content or name).
- Examples:
2026-04-15_finance_irs-1040-return.pdf,2026-09-02_career_cv-director-charter-mice.pdf - Photos and videos: keep camera names, sort into
<YYYY>/<YYYY-MM>/instead.
Workflow
1. Scope (ask only what's unknown)
Target folder? Conservative (sort and rename only) or full (also archive and dedupe)? Anything to exclude?
2. Analyze
T="<target>"
find "$T" -type f | wc -l; du -sh "$T"
find "$T" -type f | sed -n 's/.*\.\([^./]*\)$/\1/p' | tr A-Z a-z | sort | uniq -c | sort -rn | head -15
find "$T" -type f -size +100M -exec du -h {} + | sort -rh | head -10
find "$T" -type f -mtime +365 | wc -l # archive candidates
# Work-file detection (macOS + Linux); matches are candidates only, confirm before flagging
grep -rliE 'atlas|mystic|charter|mice|manifest|rfp|contract.*(cruise|vessel)' --include='*.txt' --include='*.md' --include='*.csv' "$T" 2>/dev/null | head
find "$T" -type f | grep -iE 'atlas|mystic|charter|mice|manifest|rfp|beo' | head3. Duplicates
find "$T" -type f -size +0 -print0 | xargs -0 sha256sum | sort | awk 'seen[$1]++{print}' # exact dupes (Linux); macOS: shasum -a 256Keep the copy with the best name or best location (newest if they tie). The rest go to _To-Delete/.
4. Plan (present exactly this)
| Area | Files | Action |
| 02_Finance | 34 | move + rename |
| _Work-Flagged | 6 | isolate, untouched |
| _To-Delete | 12 dupes (1.4 GB) | needs approval |
Plus: decisions needed (list), risks (list). End with: Proceed? yes / modify / no
5. Execute
After a "yes": create the folders, run the moves, write the log, and print the counts.
6. Close-out
- Summary: files moved, renamed, archived, flagged; space recoverable.
- Undo command (replays the log newest-first so chained moves reverse cleanly; on Linux use
tacinstead oftail -r):tail -r _organizer-log/<date>.tsv | while IFS=$'\t' read -r o n; do mv -n "$n" "$o"; done - Upkeep: weekly empty
00_Inbox, monthly archive and dedupe, January rollFinance/taxesandMediayear folders.
Google Drive (pedrojaimot@gmail.com)
If the Google Drive connector is available, use the same structure and rules. Search and read with the connector, propose moves in the same plan table, and only change or trash files after a "yes". Never change sharing permissions.
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.

