Skip to main content
ClaudeWave
Skill283 repo starsupdated 25d ago

cowork-calendar-defrag

Audit your calendar with Cowork's calendar tools -- measure meeting load and fragmentation, identify which recurring meetings earn their slot, propose consolidations and focus blocks, and draft the diplomatic messages that reclaim your week.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/OneWave-AI/claude-skills /tmp/cowork-calendar-defrag && cp -r /tmp/cowork-calendar-defrag/cowork-calendar-defrag ~/.claude/skills/cowork-calendar-defrag
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Cowork Calendar Defrag

Treat the calendar like a disk that needs defragmenting: measure what is actually there, identify waste, consolidate, and carve out contiguous space for real work. Uses the connected calendar tools (Microsoft 365 / Google Calendar) to read events; every change is proposed, and the human approves before anything is created, moved, or declined.

## Workflow

1. **Measure.** Pull the last 4 weeks and the next 2. Compute: hours in meetings per week, longest uninterrupted block per day, fragmentation score (count of gaps under 45 minutes -- too short to do real work, long enough to lose), meetings by type (recurring vs. ad hoc, internal vs. external), and after-hours creep.
2. **Score the recurring load.** For each recurring meeting: duration x frequency x attendee count = weekly cost. Flag candidates against the classic tells -- no agenda in the invite, attendance optional-in-practice, could-be-async status updates, double-booked slots the user routinely skips. External and client meetings are measured but never flagged for cuts without explicit instruction.
3. **Propose the defrag.** A specific plan, not principles: which recurrings to shorten (60 -> 25), consolidate (three 1:1s into office hours), make async, or leave alone; where the 2-3 weekly focus blocks go (matched to when the calendar shows the user actually has energy-adjacent free space, e.g. mornings); and which small gaps to close by nudging meetings adjacent.
4. **Draft the messages.** For each proposed change involving other people: a short, warm, blame-free draft ("I'm consolidating my recurring syncs -- can we fold this into..."). The awkward message is the real barrier to a better calendar; remove it.
5. **Execute on approval.** Create the focus blocks (marked busy, named for the work), send nothing -- updated invites and messages remain drafts for the human to send. Output `calendar-defrag-report.md` with before/after metrics: meeting hours reclaimed, longest block gained.

## Rules

- Read freely, write only what was approved, send nothing. Calendars are shared surfaces; a wrong move is publicly visible.
- Never propose cutting external, client, or 1:1-with-manager meetings unless the user asked for a full-scope review.
- Fragmentation is the enemy, not meetings. Six hours of meetings in two blocks beats four hours scattered across nine slots.
- Focus blocks get names ("Proposal writing") -- anonymous "Busy" blocks get scheduled over within two weeks.
- Respect the user's stated no-touch zones (school pickup, gym, standing personal events) as hard constraints.
- Re-run comparisons honestly: if the defrag did not hold (blocks got booked over), report it and diagnose which changes stuck.

## Scheduled Mode

As a monthly Cowork scheduled task: re-measure, compare against the last report, flag regression (creeping recurrings, eroded focus blocks), and propose the next round of cuts.

## Quick Commands

- "Audit my calendar" -- steps 1-2, the measurement and scorecard
- "Defrag my week" -- full workflow
- "Where can I fit 3 hours of deep work?" -- focus-block placement only
- "Draft the decline for [meeting]" -- one diplomatic message
accessibility-auditorSkill

Audit websites for accessibility issues and WCAG compliance. Use when checking accessibility, fixing a11y issues, or ensuring WCAG compliance.

agent-armySkill

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.

agent-swarm-deployerSkill

Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.

agent-team-builderSkill

Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.

agent-to-agentSkill

Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.

ai-readiness-assessmentSkill

Assesses how ready a business is for AI adoption across six dimensions. Evaluates data maturity, tech stack, team skills, process documentation, budget, and culture. Generates a comprehensive ai-readiness-report.md with scores, gap analysis, and recommended starting points. Aligned with OneWave AI's audit methodology.

animateSkill

Generate animated videos and motion graphics from natural language descriptions. Creates a standalone Vite + React project with Framer Motion scenes that auto-play in the browser. Use when the user wants to create animations, motion graphics, video intros, animated presentations, or product demos.

api-documentation-writerSkill

Generate comprehensive API documentation including endpoint descriptions, request/response examples, authentication guides, error codes, and SDKs. Creates OpenAPI/Swagger specs, REST API docs, and developer-friendly reference materials. Use when users need to document APIs, create technical references, or write developer documentation.