Best for
- Breaking down complex multi-step implementations
- Coordinating parallel work across multiple files
- Tracking progress on large features
yonatangross/orchestkit/src/skills/task-dependency-patterns/SKILL.md
Task Management patterns with TaskCreate, TaskUpdate, TaskGet, TaskList tools. Decompose complex work into trackable tasks with dependency chains. Use when managing multi-step implementations, coordinating parallel work, or tracking completion status.
Decision brief
Task Management patterns with TaskCreate, TaskUpdate, TaskGet, TaskList tools. Decompose complex work into trackable tasks with dependency chains.
Compatibility matrix
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Declared | Source record | Install path and trigger |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/yonatangross/orchestkit --skill "src/skills/task-dependency-patterns"Inspect the Agent Skill "task-dependency-patterns" from https://github.com/yonatangross/orchestkit/blob/1ff988bd66daf223028ed44767b591fecc8510c2/src/skills/task-dependency-patterns/SKILL.md at commit 1ff988bd66daf223028ed44767b591fecc8510c2. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
pending: Task created but not started
Review the “Team Workflow” section in the pinned source before continuing.
Breaking down complex multi-step implementations
Break complex work into atomic, trackable units:
Break complex work into atomic, trackable units:
Permission review
No configured static risk pattern was detected
This is not proof of safety. Runtime behavior, indirect dependencies, and hidden external systems are outside the static scan.
Evidence record
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 93/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 224 | Source | Repository attention, not individual Skill quality |
| Compatibility | 1 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Claude Code 2.1.16 introduces a native Task Management System with four tools:
CC 2.1.233 caveat: the Task tools are removed for the newest models unless
CLAUDE_CODE_ENABLE_TODO_TOOLS=1is set in user or managed settings (or the shell). ork cannot ship that flag (CC reads onlypermissionsfrom plugin settings), so treat every Task-tool call in this skill as conditional on the operator's environment.
Tasks enable structured work tracking, parallel coordination, and clear progress visibility.
Break complex work into atomic, trackable units:
Feature: Add user authentication
Tasks:
#1. [pending] Create User model
#2. [pending] Add auth endpoints (blockedBy: #1)
#3. [pending] Implement JWT tokens (blockedBy: #2)
#4. [pending] Add auth middleware (blockedBy: #3)
#5. [pending] Write integration tests (blockedBy: #4)
Use addBlockedBy to create execution order:
// Task #3 cannot start until #1 and #2 complete
{"taskId": "3", "addBlockedBy": ["1", "2"]}
pending → in_progress → completed
↓ ↓
(unblocked) (active)
pending/in_progress → deleted
Use status: "deleted" to permanently remove tasks:
// Delete a task
{"taskId": "3", "status": "deleted"}
When to delete:
When NOT to delete:
Provide present-continuous form for spinner display:
| subject (imperative) | activeForm (continuous) |
|---|---|
| Run tests | Running tests |
| Update schema | Updating schema |
| Fix authentication | Fixing authentication |
Agent Teams provides multi-agent coordination with shared task lists and peer-to-peer messaging.
CC 2.1.161 — independent parallel-tool failure: A failed tool call in a parallel batch no longer cancels siblings; each returns its own result. Teammates must check task status independently and handle failures explicitly rather than assuming a batch-wide abort.
1. (implicit team — CC 2.1.178+) → one team per session; no TeamCreate
2. TaskCreate(subject, description) → Add tasks to shared list
3. Agent(name, team_name, prompt) → Spawn teammates into the implicit team
4. TaskUpdate(owner: "teammate-name") → Assign tasks
5. SendMessage(to, message, summary) → Direct teammate communication
6. (turn / background ends) → teammates wind down; Ctrl+F x2 for bg
| Criteria | Task Tool (subagents) | Agent Teams |
|---|---|---|
| Independent tasks | Yes | Overkill |
| Cross-cutting changes | Limited | Yes |
| Agents need to talk | No (star topology) | Yes (mesh) |
| Cost sensitivity | Lower (~1x) | Higher (~2.5x) |
| Complexity < 3.0 | Yes | No |
| Complexity > 3.5 | Possible | Recommended |
# Spawn teammate into shared task list
Agent(
prompt="You are the backend architect...",
team_name="my-feature",
name="backend-architect",
subagent_type="ork:backend-system-architect"
)
# Teammate claims and works tasks
TaskList → find unblocked, unowned tasks
TaskUpdate(taskId, owner: "backend-architect", status: "in_progress")
# ... do work ...
TaskUpdate(taskId, status: "completed")
TaskList → find next task
# Direct message between teammates (params: to, message, summary)
SendMessage(to: "frontend-dev",
message: "API contract ready: GET /users/:id returns {...}",
summary: "API contract shared")
# No broadcast primitive — send to each teammate, or post to the shared
# task list (TaskCreate/TaskUpdate) so every teammate sees it
SendMessage(to: "backend-dev",
message: "Breaking change: auth header format changed",
summary: "Breaking auth change")
When using Agent Teams, if context limit is reached mid-workflow:
TaskListTaskUpdate(taskId: task_id, status: "completed", metadata: {"skipped": "context limit"})ork:implement - Implementation workflow with task tracking and progress updatesork:verify - Verification tasks and completion checklistsork:fix-issue - Issue resolution with hypothesis-based RCA trackingork:brainstorm - Design exploration with parallel agent tasksLoad on demand with Read("${CLAUDE_PLUGIN_ROOT}/skills/task-dependency-patterns/references/<file>"):
| File | Content |
|---|---|
dependency-tracking.md | Dependency tracking patterns |
status-workflow.md | Status workflow details |
multi-agent-coordination.md | Multi-agent coordination |
Frequently asked questions
Task Management patterns with TaskCreate, TaskUpdate, TaskGet, TaskList tools. Decompose complex work into trackable tasks with dependency chains.
The source record exposes this install command: npx skills add https://github.com/yonatangross/orchestkit --skill "src/skills/task-dependency-patterns". Inspect the command and pinned source before running it.
The pinned source record declares support for: claude code.
Alternatives
oaustegard/claude-skills
Generate hierarchical _FEATURES.md files that describe what a codebase DOES from a user/consumer perspective, anchored to source symbols via tree-sitting. Supports large complex codebases through feature-driven decomposition into sub-feature files. Uses a multi-pass synthesis: orientation → detail → overview rewrite. Use when someone says "what does this do", "document features", "feature inventory", "_FEATURES.md", or needs to understand a codebase's purpose before modifying it. Complements tre
vasilyu1983/AI-Agents-public
Configures Claude Code hooks and Codex hooks.json/notify callbacks. Use when adding guardrails, preflight, audit trails, worktree automation, or budget enforcement.
vasilyu1983/AI-Agents-public
Guides iOS testing with XCTest, XCUITest, Swift Testing, simctl, and xcresult. Use when choosing destinations, controlling flakes, or parsing test artifacts for native apps.
PaulRBerg/agent-skills
Create/scaffold/init a project-local agent skill under `.agents/skills` in an ordinary repository; defer to repository instructions that define a source catalog and lifecycle.