organize-research-files
Skill0 starsChanged 5 months agoMITView on GitHub
Audit, classify, and safely organize Bowen Li's Desktop, Downloads, and research-document folders using a numbered filing scheme with dry runs, move manifests, and undo scripts. Use when asked to clean up files, organize Desktop or Downloads, locate misfiled research documents, review ambiguous files, or repeat inbox-zero filing.
In this repository9 other files it gives its agents.
- build-reimbursement-packetsSkill
- design-lnp-experimentsSkill
- manage-research-portfolioSkill
- run-pi-operationsSkill
- scan-nanomedicine-literatureSkill
- downloads-triageSkill
- lab-pi-opsSkill
- lit-scoutSkill
- reimburse-trackerSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 2 are distinctive, and 6 are 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.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use ${CLAUDE_SKILL_DIR}/scripts/organize_files.py for deterministic classification and reversible moves.
- Very specific: line 12
Run a dry run first: python3 ${CLAUDE_SKILL_DIR}/scripts/organize_files.py ~/Desktop ~/Downloads
- Distinctive: line 17
Verify that the category folders exist, loose files are gone, and manifests plus undo scripts were written.
- Very specific: line 22
Keep 00_Active_Now untouched unless the user explicitly asks to archive it.
- Distinctive: line 25
Never delete duplicates or installers automatically.
- Very specific: line 26
Never move 60_Personal_Legal_Finance into a synced or shared location without explicit approval.
- Very specific: line 27
Prefer 90_Archive_To_Review over a confident-looking guess.
- Very specific: line 29
Read references/filing-scheme.md when extending categories or classifier 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
Organize research files
Use ${CLAUDE_SKILL_DIR}/scripts/organize_files.py for deterministic classification and reversible moves.
Workflow
- Run a dry run first:
python3 ${CLAUDE_SKILL_DIR}/scripts/organize_files.py ~/Desktop ~/Downloads - Review counts and every proposed move. Treat personal, legal, financial, medical, unpublished, and partner-confidential files as sensitive.
- Apply only when the user asked for organization:
python3 ${CLAUDE_SKILL_DIR}/scripts/organize_files.py ~/Desktop ~/Downloads --apply - Verify that the category folders exist, loose files are gone, and manifests plus undo scripts were written.
- Report moved counts, ambiguous files left for review, and exact undo paths.
Rules
- Keep
00_Active_Nowuntouched unless the user explicitly asks to archive it. - Preserve project folders as units; do not scatter their internal contents.
- During second-pass auditing, move only high-confidence misclassifications.
- Never delete duplicates or installers automatically.
- Never move
60_Personal_Legal_Financeinto a synced or shared location without explicit approval. - Prefer
90_Archive_To_Reviewover a confident-looking guess.
Read references/filing-scheme.md when extending categories or classifier rules.
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.

