skills/defrag/SKILL.md
Weekly vault defragmentation. Runs a 5-phase structural audit: inbox hygiene, area completeness, project archival, MOC refresh, tag consistency, structure evolution, and generates a report. Triggers: EN: "defragment the vault", "reorganize the vault", "structural maintenance", "vault defrag", "weekly defrag". IT: "deframmenta il vault", "riorganizza il vault", "manutenzione strutturale", "defrag settimanale". FR: "defragmenter le vault", "reorganiser le vault". ES: "desfragmentar el vault", "reorganizar el vault". DE: "Vault defragmentieren", "Vault reorganisieren". PT: "desfragmentar o vault", "reorganizar o vault".
npx skillsauth add gnekt/My-Brain-Is-Full-Crew defragInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Read Meta/vault-map.md (always this literal path) to resolve folder paths. Parse the YAML frontmatter: each key is a role, each value is the actual folder path. Substitute only the vault-role tokens listed in the table below — do NOT substitute other {{...}} patterns (like {{date}}, {{Name}}, {{YYYY}}, {{ISO timestamp}}, {{today}}, {{Area Name}}, etc.), which are template placeholders.
If vault-map.md is absent: warn the user once — "No vault-map.md found, using default paths" — then use these defaults:
| Token | Default |
|-------|---------|
| {{inbox}} | 00-Inbox |
| {{projects}} | 01-Projects |
| {{areas}} | 02-Areas |
| {{resources}} | 03-Resources |
| {{archive}} | 04-Archive |
| {{templates}} | Templates |
| {{moc}} | MOC |
| {{meta}} | Meta |
If vault-map.md is present but a role is missing: warn the user — "vault-map.md does not define [role]. What folder should I use?" — and wait for their answer before proceeding.
You are executing the Architect's weekly vault defragmentation workflow. This is a structural operation — not a quality audit (that is the Librarian's job). You scan the vault's organizational skeleton, fix structural gaps, evolve the layout, and produce a comprehensive report.
Always respond to the user in their language. Match the language the user writes in. This skill file is written in English for universality, but your output adapts to the user.
Read {{meta}}/states/architect.md (if it exists). If it contains an active defrag flow, resume from the recorded phase — do NOT restart from Phase 1.
Write (or overwrite) {{meta}}/states/architect.md with:
---
agent: architect
last-run: "{{ISO timestamp}}"
---
## Post-it
### Last operation: defrag
### Summary: {{brief summary of what was done}}
### Issues detected: {{any issues that need follow-up, with suggested agents}}
Max 30 lines in the Post-it body. If you need more, summarize.
When the user triggers a defrag, execute all 5 phases in order.
Scan all files in {{inbox}}/ — anything older than 48 hours that is still in Inbox is a failure. Signal the Sorter via ### Suggested next agent to triage it, or file it yourself if the destination is obvious.
Scan {{areas}}/ — for each area:
_index.md? If not, create it.{{moc}}/? If not, create it.Scan {{projects}}/ — are there completed projects that should be archived to {{archive}}/?
Scan {{resources}}/ — are there resources that now belong to a specific area? Move them.
Scan {{moc}}/ — is the Master Index up to date? Are all area MOCs linked? Are there MOCs with no corresponding area (orphan MOCs)?
Scan {{templates}}/ — are there templates that are never used? Are there note types that lack a template?
{{meta}}/tag-taxonomy.md — either add them to the taxonomy or fix them.#ml and #machine-learning) — consolidate.#area/ prefix).{{moc}}/Index.md) links to every area MOC.{{meta}}/user-profile.md — has the user's situation changed? New jobs, new interests, new goals mentioned in recent notes?{{meta}}/vault-structure.md with all changes.Create a defragmentation report at {{meta}}/health-reports/YYYY-MM-DD — Defrag Report.md:
---
type: report
date: "{{today}}"
tags: [report, defrag, maintenance]
---
# Vault Defragmentation Report — {{date}}
## Summary
- Files moved: {{count}}
- Structures created: {{list}}
- Tags fixed: {{count}}
- MOCs updated: {{list}}
- Inbox items triaged: {{count}}
- Projects archived: {{list}}
## Structural Changes
{{Detailed list of what was created, moved, renamed, or archived}}
## Recommendations
{{Suggestions for the user — new areas to consider, templates to create, etc.}}
## Next Defrag
{{Anything to watch for next week}}
Log the defrag in {{meta}}/agent-log.md.
When Phase 4 detects a new area or sub-area is needed, follow these 7 steps:
{{areas}}/ with appropriate sub-folders._index.md with purpose, active projects, sub-areas, key resources, and a link to its MOC.{{moc}}/{{Area Name}}.md with overview, structure, key notes, active projects, and a link back to the Master Index.{{moc}}/Index.md.{{templates}}/.{{meta}}/vault-structure.md — document the new area, its sub-folders, and its purpose.{{meta}}/tag-taxonomy.md — add area-specific tags (e.g., #area/finance, #budget).For the full detailed procedure with templates and examples, see the Architect agent (agents/architect.md, Section 4).
After completing the defrag, analyze your findings and suggest follow-up agents when appropriate. Include a ### Suggested next agent section at the end of your output for each applicable case:
{{resources}}/ should be moved to a newly created area.### Suggested next agent
- **Agent**: sorter
- **Reason**: {{why this agent should run next}}
- **Context**: {{specific details about what needs attention}}
If during defrag you detect a recurring need that no existing agent covers, include:
### Suggested new agent
- **Need**: {{what capability is missing}}
- **Reason**: {{why no existing agent can handle this}}
- **Suggested role**: {{brief description of what the new agent would do}}
Always structure your response as follows:
{{meta}}/health-reports/{{meta}}/states/architect.md{{meta}}/agent-log.mddata-ai
Generate a day-by-day overview of the week combining calendar events, email deadlines, and vault tasks into a single structured agenda. Triggers: EN: "weekly agenda", "what's this week", "week overview", "plan my week". IT: "agenda settimanale", "cosa c'è questa settimana", "panoramica della settimana". FR: "agenda de la semaine", "programme de la semaine". ES: "agenda semanal", "qué hay esta semana". DE: "Wochenagenda", "Wochenübersicht". PT: "agenda semanal", "o que tem esta semana".
testing
Full 7-phase vault audit: structural scan, duplicate detection, link integrity, frontmatter audit, MOC review, cross-agent integration check, and health report. Triggers: EN: "weekly review", "check the vault", "vault audit", "full audit", "vault health". IT: "revisione settimanale", "controlla il vault", "audit del vault", "salute del vault". FR: "audit du vault", "vérifier le vault". ES: "auditoría del vault", "revisar el vault". DE: "Vault-Audit", "Vault überprüfen". PT: "auditoria do vault", "verificar o vault".
development
Process audio recordings, meeting transcripts, podcasts, or lectures. Runs an intake interview (date, mode, speakers, language) then processes into structured notes with action items, decisions, and glossary. Triggers: EN: "transcribe", "I have a recording", "process this audio", "meeting notes from recording", "summarize the call", "lecture notes", "podcast summary". IT: "trascrivi", "ho una registrazione", "processa questo audio", "note della riunione", "riassumi la call". FR: "transcrire", "j'ai un enregistrement", "résumer l'appel". ES: "transcribir", "tengo una grabación", "resumir la llamada". DE: "transkribieren", "Aufnahme verarbeiten". PT: "transcrever", "tenho uma gravação".
testing
Analyze all vault tags: find unused, orphan, near-duplicate, over-used, and under-used tags. Suggest merges and cleanup actions. Triggers: EN: "tag garden", "clean up tags", "tag cleanup", "tag audit". IT: "tag garden", "pulizia tag", "revisione tag". FR: "jardinage des tags", "nettoyer les tags". ES: "jardín de tags", "limpiar tags". DE: "Tag-Garten", "Tags aufräumen". PT: "jardim de tags", "limpar tags".