claude/plugins/local/todoist-flow/skills/organize/SKILL.md
Audit and restructure Todoist projects, labels, sections, and filters. Proposes changes with approval before executing. Use when the user says 'organize todoist', 'restructure projects', 'clean up projects', 'fix my todoist structure', 'audit labels', 'create filters', or when /todoist dashboard shows structural issues (too many projects, empty projects, missing filters).
npx skillsauth add paulnsorensen/dotfiles organizeInstall 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.
Audit the structural health of the user's Todoist workspace and propose targeted improvements. Every change requires explicit user approval.
Spawn todoist-fetch to gather all audit data in a fresh context window:
Agent(subagent_type: "todoist-fetch", prompt: "Fetch full workspace audit data: 1) find-projects with task counts, 2) find-labels with usage counts, 3) find-sections across all projects, 4) find-filters (all existing), 5) analyze-project-health for health metrics. Return structured inventory with IDs and counts for each category.")
Check for these structural problems (from best practices in ${CLAUDE_PLUGIN_ROOT}/references/best-practices.md):
Projects:
Labels:
@client-name with many tasks)@waiting, @deep-work, @quick-win not present)Sections:
Filters:
## Todoist Structure Audit
### Projects (X active)
- [issue] "Misc" has 45 tasks and no sections → Split or add sections
- [issue] "Old ideas" is empty → Archive
- [good] 12 active projects (under 15 limit)
### Labels (X total)
- [issue] @client-acme has 30 tasks → Convert to a project
- [issue] No @waiting label → Create it
- [good] @deep-work in use (8 tasks)
### Sections
- [issue] "Work" has 38 tasks, no sections → Add phase sections
### Filters (X total)
- [issue] No "Today" filter → Create: (today | overdue) & !#Someday
- [issue] No "Waiting" filter → Create: @waiting
- [good] "This Week" filter exists
Group changes into categories and present as a plan:
## Proposed Changes
### Quick wins (safe, low-risk):
1. Archive empty project "Old ideas"
2. Create @waiting label
3. Create "Today" filter: (today | overdue) & !#Someday
### Structural (review each):
4. Add sections to "Work" project: Backlog / In Progress / Done
5. Convert @client-acme label to a project (move 30 tasks)
Approve all quick wins? (y/n)
Then I'll walk through structural changes one at a time.
Use AskUserQuestion for approval. For quick wins, batch approval is fine. For structural changes, get approval per change.
Run approved changes through the write pipeline (distill → scribe → QA):
1. Validate reasoning — spawn todoist-distill:
Agent(subagent_type: "todoist-distill", prompt: "Validate these structural changes against user approval: [approved changes with context]")
2. Format commands — spawn todoist-scribe with validated plan:
Agent(subagent_type: "todoist-scribe", prompt: "Format these validated structural operations as MCP commands: [distill's validated plan]")
3. Verify and execute — spawn todoist-qa:
Agent(subagent_type: "todoist-qa", prompt: "Verify and execute: [scribe's formatted commands]. Original intent: [distill's validated plan]")
For large batches (10+ operations), split into logical groups (filters, sections, project changes) and run each group through the pipeline separately.
After execution, re-fetch overview and show before/after:
## Results
- Projects: 18 → 14 (archived 4 empty)
- Labels: +2 created (@waiting, @quick-win), -1 converted (→ project)
- Filters: +3 cockpit filters created
- Sections: +3 added to "Work" project
If the user wants advice on how to structure a specific domain (e.g., "how should I organize my home renovation project?"), invoke the research skill:
Skill(skill="todoist-flow:research", args="Best practices for organizing [domain] tasks in a task management system. Suggest project structure, sections, and labels.")
tools
Reconstruct what a past coding-agent session was doing so you can resume it — goal, files touched, last verified state, and the next step — by querying the session logs. Use when the user says "what was I working on", "recover that session", "reconstruct where I left off", "resume my last session", "what did that session change", "rebuild context from logs", or invokes /work-recovery. Report-only — it never scores or judges. Do NOT use for usage scoring (that is /skill-improver, /tool-efficiency, /prompt-analytics) or one-off interactive log queries (that is /session-analytics).
development
Curate this repo's hallouminate wiki (.hallouminate/wiki/, the repo:dotfiles:wiki corpus) — add or update architecture pages, per-harness docs, and gotchas. Use when the user says "update the wiki", "document this in the wiki", "refresh the harness docs", "add a wiki page", "curate the wiki", "the wiki is stale", or invokes /wiki-curator. Also use at session end to write back a non-obvious decision or gotcha worth preserving. Grounds the existing wiki first, follows one-topic-per-file conventions, verifies every external doc URL before writing, and reindexes. Do NOT use for general code search (that is cheez-search) or for editing AGENTS.md command reference.
tools
Audit how a tool, command, or MCP server is actually used across coding-agent sessions and produce calibrated recommendations — tool-vs-task fit, error forensics, fix recommendations, permission friction, MCP health, and token economics. Use when the user says "tool efficiency", "am I using X efficiently", "audit tool usage", "why does X keep failing", "how do I fix this error", "what should I change", "permission friction", "is this MCP worth it", "tool error rate", "fix recommendations", or invokes /tool-efficiency. Do NOT use for auditing a skill or agent definition (that is /skill-improver) or for one-off interactive log queries (that is /session-analytics).
tools
Analyze how prompts and skill routing behave across coding-agent sessions and produce calibrated recommendations — prompt-pattern analysis, routing accuracy, and knowledge gaps. Use when the user says "analyze my prompts", "prompt patterns", "is routing working", "which skill should have fired", "knowledge gaps", "what do I keep asking", or invokes /prompt-analytics. Do NOT use for auditing a single skill/agent definition (that is /skill-improver), tool/MCP efficiency (that is /tool-efficiency), or one-off interactive log queries (that is /session-analytics).