task-calendar

Included with Lifetime

$97 forever

Use when the user wants to "schedule a task", "block time for a task", "add task to calendar", "check if I'm free", "find a slot for this", "when can I work on", "create a calendar event for a task", "reschedule this task", or any request that bridges a Taskwarrior task with Google Calendar. Uses gogcli (gog) when available, falls back to Google Calendar MCP tools.

AI Agents

What this skill does


# Task Calendar

Bridge Taskwarrior tasks and Google Calendar. Taskwarrior is source of truth for **what** and
**when (deadline)**. Google Calendar is source of truth for **time blocks** (when you actually
sit down to work).

Follow [[task-workflow]] for all task lifecycle rules. This skill adds calendar operations only.

## Core Principle

- `due:` on a task = deadline, not a work block
- Calendar event = committed work time for a task
- Never auto-sync; always confirm with user before writing to Calendar

## Tool Selection

At the start of any calendar operation, detect which tool is available:

```bash
command -v gog && echo "gogcli available"
```

**Prefer `gog`** (gogcli) when present — runs via Bash, outputs JSON/TSV to stdout, no MCP overhead.
Fall back to `mcp__claude_ai_Google_Calendar__*` MCP tools when `gog` is absent.

gogcli docs: https://gogcli.sh/quickstart.html

## Operations

### 1. Check availability before setting a due date

When user says "add task due Friday" or asks about scheduling:

```bash
# gogcli — list events for target date
gog calendar events --today          # for today
# for a specific date, inspect output and filter by date

# MCP fallback
# mcp__claude_ai_Google_Calendar__list_events (timeMin: date start, timeMax: date end)
```

→ Report conflicts found  
→ Proceed with `task add ... due:<date>` only after user confirms

### 2. Block time for a task (write to Calendar)

When user says "schedule this", "block time", "add to calendar":

```
1. task <id> info                              — get description, due, project
2. gog calendar events --today                 — inspect free windows
3. Show proposed slot to user, get confirmation
4. Create event:

     gogcli:
       gog calendar create \
         --summary "<task description>" \
         --from "YYYY-MM-DDTHH:MM:SS+TZ" \
         --to   "YYYY-MM-DDTHH:MM:SS+TZ"

     MCP fallback:
       mcp__claude_ai_Google_Calendar__create_event

5. task <id> annotate "gcal:<summary> <date> <HH:MM>"
```

Event format:
- **`--summary`**: task description verbatim
- **Description** (if MCP): `taskwarrior id: <id>  project: <project>`
- **Duration**: 25–90 min depending on complexity; ask user if unclear
- **Timezone**: use local timezone offset (e.g. `+02:00` for CEST)

### 3. Reschedule a task

When user says "move this to next week", "reschedule task 42":

```
1. task <id> info                              — get existing gcal annotation
2. gog calendar events --today                 — find new free slot
3. Show proposed change, get confirmation
4. Recreate event with new times (gogcli has no edit command — delete + create):
     gog calendar create --summary "..." --from "..." --to "..."
5. task <id> modify due:<new-date>             — only if deadline also changed
6. task <id> annotate "Rescheduled: <old-date> → <new-date>"
```

### 4. Daily planning view with calendar context

When user says "plan my day", "what should I work on today":

```bash
# Step 1 — tasks
task +TODAY list
task +OVERDUE list

# Step 2 — calendar
gog calendar events --today
# MCP fallback: mcp__claude_ai_Google_Calendar__list_events
```

→ Report: meetings that consume time, free windows, tasks without blocks  
→ Offer to block time for unscheduled tasks

## Rules

- **Never** create a calendar event without user confirmation
- **Never** modify a task's `due:` date based on calendar data alone — only on explicit user instruction
- **Never** delete calendar events without confirmation
- If `gcal:` annotation already exists on a task, check that event before creating a new one
- Keep annotation format consistent: `gcal:<summary> YYYY-MM-DD HH:MM`

## Calendar Tool Reference

| Intent | gogcli (`gog`) | MCP fallback |
|--------|----------------|--------------|
| List today's events | `gog calendar events --today` | `mcp__claude_ai_Google_Calendar__list_events` |
| Create event | `gog calendar create --summary "..." --from "..." --to "..."` | `mcp__claude_ai_Google_Calendar__create_event` |
| Find free slot | inspect `events --today` output | `mcp__claude_ai_Google_Calendar__suggest_time` |
| Update event | delete + recreate (no edit command) | `mcp__claude_ai_Google_Calendar__update_event` |

MCP tools require loading via ToolSearch before calling:
`ToolSearch: select:mcp__claude_ai_Google_Calendar__<tool_name>`

Files: 1

Size: 4.7 KB

Complexity: 10/100

Category: AI Agents

Source: https://github.com/kjgarza/marketplace-claude/tree/main/plugins/taskwarrior/skills/task-calendar

Related in AI Agents

skill-development

Included

Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.

AI Agentsscripts

reprompter

Included

Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.

AI Agentsscripts

adaptive-compaction

Included

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

AI Agentsscripts

agent-skill-creator

Included

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

AI Agentsscripts

llm-wiki

Included

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

AI Agentsscripts

skill-master

Included

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.

AI Agentsscripts