skill-task-management
Manage tasks with Claude Code native tools — use to track TODOs, delegate work, and monitor progress
What this skill does
> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.
> Cross-reference commands use installed skill names in Codex rather than `/octo:*` slash commands.
> Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it.
> For host tool equivalents, see `skills/blocks/codex-host-adapter.md`.
# Task Management & Orchestration (v7.23.0+)
## Overview
Systematic task orchestration for multi-step work, progress checkpointing, and seamless task resumption across sessions.
**Core principle:** Track → Checkpoint → Resume → Complete.
**v7.23.0 Migration:** This skill now uses native Claude Code host subagent tools:
- `TaskCreate` - Create new tasks
- `TaskUpdate` - Update task status/details
- `TaskList` - View all tasks
- `TaskGet` - Get specific task details
**Benefits:**
- ✅ Tasks show in native Claude Code UI
- ✅ Better progress tracking and visualization
- ✅ Consistent with Claude Code conventions
- ✅ No dependency on external task plan tool tool
## When to Use
**Use this skill when user wants to:**
- Add items to the todo list
- Save current progress for later continuation
- Resume previously saved work
- Checkpoint progress in long-running tasks
- Proceed to next steps in a workflow
- Continue from where they left off
**Do NOT use for:**
- Creating git commits (use skill-finish-branch)
- Simple todo list queries ("what's on my list?")
- Task completion that involves pushing code
## Core Capabilities
### 1. Adding Tasks to Todo List
When user says "add to the todo's" or similar:
```markdown
**What would you like to add to the todo list?**
I'll help you capture this task. Please provide:
- Task description (what needs to be done)
- Any dependencies or prerequisites
- Priority (if applicable)
```
**After getting details, use TaskCreate to add:**
```javascript
TaskCreate({
subject: "[Brief task description]",
description: "[Detailed description including dependencies and context]",
activeForm: "Working on [task description]"
})
```
**Then confirm to user:**
```
✅ Task created: [Task description]
View all tasks with TaskList or use /tasks command.
```
### 2. Saving Progress / Checkpointing
When user says "save progress" or "checkpoint this":
#### Step 1: Assess Current State
```bash
# Check git status
git status
# Check current branch
git branch --show-current
# Check uncommitted work
git diff --stat
```
#### Step 2: Create Progress Checkpoint
**Option A: Git-based checkpoint (if git repo)**
```bash
# Create a work-in-progress commit
git add .
git commit -m "WIP: [description of current state]
Progress checkpoint - work in progress
Not ready for review or merge
Current state:
- [What's completed]
- [What's in progress]
- [What's next]
Co-Authored-By: Claude Sonnet 4.6 <[email protected]>"
```
**Option B: Task-based checkpoint (preferred for tracking)**
Create checkpoint task with detailed state:
```javascript
TaskCreate({
subject: "Checkpoint: [Brief description]",
description: `
📍 CHECKPOINT: ${new Date().toISOString()}
Completed:
✓ [Task 1]
✓ [Task 2]
In Progress:
⚙️ [Current task with details]
Next Steps:
- [ ] [Next task 1]
- [ ] [Next task 2]
- [ ] [Next task 3]
Context:
- Branch: ${branchName}
- Last commit: ${lastCommit}
- Files changed: ${filesChanged}
`,
activeForm: "Checkpoint saved"
})
```
#### Step 3: Update Existing Tasks
Mark completed tasks as done:
```javascript
// For each completed task
TaskUpdate({
taskId: "[task-id]",
status: "completed"
})
```
Mark current task as in_progress:
```javascript
TaskUpdate({
taskId: "[current-task-id]",
status: "in_progress"
})
```
#### Step 4: Provide Resume Instructions
```markdown
✅ Progress saved!
To resume this work:
1. Run: git checkout [branch-name]
2. View tasks: TaskList
3. Say: "resume tasks" or "pick up where we left off"
Current state:
- Branch: [branch-name]
- Tasks: [X completed, Y in progress, Z pending]
- Last checkpoint: [timestamp]
```
### 3. Resuming Tasks
When user says "resume tasks" or "pick up where we left off":
#### Step 1: Load Task State
```javascript
// Get all tasks
const tasks = TaskList()
// Filter by status
const completed = tasks.filter(t => t.status === 'completed')
const inProgress = tasks.filter(t => t.status === 'in_progress')
const pending = tasks.filter(t => t.status === 'pending')
// Find checkpoint task (if exists)
const checkpoint = tasks.find(t => t.subject.startsWith('Checkpoint:'))
```
#### Step 2: Check Git State
```bash
# Check for WIP commits
git log --oneline -10 | grep WIP
# Check current branch
git branch --show-current
# Check git status
git status
```
#### Step 3: Present Current State
```markdown
📋 **Resuming from last checkpoint**
**Branch:** [branch-name]
**Last checkpoint:** [timestamp from WIP commit or checkpoint task]
**Completed:** (${completed.length} tasks)
${completed.map(t => `✓ ${t.subject}`).join('\n')}
**In Progress:** (${inProgress.length} tasks)
${inProgress.map(t => `⚙️ ${t.subject}`).join('\n')}
**Next Steps:** (${pending.length} tasks)
${pending.map((t, i) => `${i + 1}. [ ] ${t.subject}`).join('\n')}
**Would you like me to:**
1. Continue with the next task?
2. Modify the plan?
3. See more details about current state?
```
#### Step 4: Execute Based on Choice
- If "continue with next task" → Get first pending task, mark as in_progress, and begin work:
```javascript
const nextTask = pending[0]
TaskUpdate({ taskId: nextTask.id, status: 'in_progress' })
// Begin working on nextTask
```
- If "modify the plan" → Use AskUserQuestion to understand changes, then update tasks
- If "see more details" → Show git diff, file changes, recent commits, task descriptions
### 4. Proceeding to Next Steps
When user says "proceed to next steps":
#### Step 1: Check Current Task Status
```javascript
const tasks = TaskList()
const currentTask = tasks.find(t => t.status === 'in_progress')
if (currentTask) {
console.log(`Current task: ${currentTask.subject}`)
console.log(`Status: ${currentTask.status}`)
}
```
#### Step 2: Complete Current and Move Forward
```javascript
// Mark current task as complete
if (currentTask) {
TaskUpdate({
taskId: currentTask.id,
status: 'completed'
})
console.log(`✓ ${currentTask.subject}`)
}
// Get next pending task
const nextTask = tasks.find(t => t.status === 'pending' && !t.blockedBy?.length)
if (nextTask) {
// Mark as in progress
TaskUpdate({
taskId: nextTask.id,
status: 'in_progress'
})
console.log(`\n⚙️ ${nextTask.subject}`)
console.log(`\nProceeding with: ${nextTask.description}`)
}
```
#### Step 3: Execute Next Task
Begin working on the next task immediately after marking it as in_progress.
## Migration from task plan tool (v7.22.x → v7.23.0+)
### For Users with Existing .md Todo Files
If you have existing `.claude/todos.md` or similar files:
#### Option 1: Automatic Migration
```bash
# Run migration script
"${HOME}/.claude-octopus/plugin/scripts/migrate-todos.sh"
```
This will:
1. Parse existing .md todo files
2. Convert to TaskCreate calls
3. Preserve task order and status
4. Archive old .md files to `.claude/archived-todos/`
#### Option 2: Manual Migration
For each todo item in your .md file:
```markdown
<!-- Old format in todos.md -->
- [ ] Implement user authentication
- [x] Set up database
- [ ] Create API endpoints
```
Convert to:
```javascript
// New format using native tasks
TaskCreate({
subject: "Implement user authentication",
description: "Create auth system with JWT tokens",
activeForm: "Implementing authentication"
})
TaskCreate({
subject: "Set up database",
description: "Configure PostgreSQL and run migrations",
activeForm: "Setting up database"
})
// Mark as completed since it was [x]
TaskUpdate({ taskId: "...", status: "completed" })
TaskCreate({
subject: "Create API endpoints",
description: "Build REST API foRelated in AI Agents
skill-development
IncludedComprehensive 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.
reprompter
IncludedTransform 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.
adaptive-compaction
IncludedAdaptive 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.
agent-skill-creator
IncludedCreate 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.
llm-wiki
IncludedUse 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.
skill-master
IncludedAgent 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.