Full-power feature implementation with parallel subagents. Use when implementing, building, or creating features.
Implements complex features using parallel subagents with architecture detection, worktree isolation, and mandatory testing.
/plugin marketplace add yonatangross/orchestkit/plugin install orkl@orchestkitThis skill is limited to using the following tools:
assets/micro-plan-template.mdassets/reflection-template.mdchecklists/implementation-review.mdreferences/agent-phases.mdreferences/agent-teams-full-stack.mdreferences/agent-teams-phases.mdreferences/agent-teams-security-audit.mdreferences/cc-enhancements.mdreferences/e2e-verification.mdreferences/feedback-loop.mdreferences/interview-mode.mdreferences/micro-planning-guide.mdreferences/orchestration-modes.mdreferences/scope-creep-detection.mdreferences/team-worktree-setup.mdreferences/worktree-isolation-mode.mdreferences/worktree-workflow.mdscripts/worktree-setup.shtest-cases.jsonParallel subagent execution for feature implementation with scope control and reflection.
/ork:implement user authentication
/ork:implement real-time notifications
/ork:implement dashboard analytics
BEFORE any work, detect the project tier. This becomes the complexity ceiling for all patterns.
Scan codebase for signals: README keywords (take-home, interview), .github/workflows/, Dockerfile, terraform/, k8s/, CONTRIBUTING.md.
| Signal | Tier | Architecture Ceiling |
|---|---|---|
| README says "take-home", time limit | 1. Interview (details) | Flat files, 8-15 files |
| < 10 files, no CI | 2. Hackathon | Single file if possible |
.github/workflows/, managed DB | 3. MVP | MVC monolith |
| Module boundaries, Redis, queues | 4. Growth | Modular monolith, DI |
| K8s/Terraform, monorepo | 5. Enterprise | Hexagonal/DDD |
| CONTRIBUTING.md, LICENSE | 6. Open Source | Minimal API, exhaustive tests |
If confidence is low, use AskUserQuestion to ask the user. Pass detected tier to ALL downstream agents — see scope-appropriate-architecture.
| Tier | Phases | Max Agents |
|---|---|---|
| 1. Interview | 1, 5 only | 2 |
| 2. Hackathon | 5 only | 1 |
| 3. MVP | 1-6, 9 | 3-4 |
| 4-5. Growth/Enterprise | All 10 | 5-8 |
| 6. Open Source | 1-7, 9-10 | 3-4 |
Use AskUserQuestion to verify scope (full-stack / backend-only / frontend-only / prototype) and constraints.
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 and complexity >= 2.5ORCHESTKIT_FORCE_TASK_TOOL=1 to overrideFor features touching 5+ files, offer worktree isolation to prevent conflicts with the main working tree:
AskUserQuestion(questions=[{
"question": "Isolate this feature in a git worktree?",
"header": "Isolation",
"options": [
{"label": "Yes — worktree (Recommended)", "description": "Creates isolated branch via EnterWorktree, merges back on completion"},
{"label": "No — work in-place", "description": "Edit files directly in current branch"}
],
"multiSelect": false
}])
If worktree selected:
EnterWorktree(name: "feat-{slug}") to create isolated branchgit checkout {original-branch} && git merge feat-{slug}AskUserQuestionSee Worktree Isolation Mode for detailed workflow.
Create tasks with TaskCreate BEFORE doing any work. Each phase gets a subtask. Update status with TaskUpdate as you progress.
| Phase | Activities | Agents |
|---|---|---|
| 1. Discovery | Research best practices, Context7 docs, break into tasks | — |
| 2. Micro-Planning | Detailed plan per task (guide) | — |
| 3. Worktree | Isolate in git worktree for 5+ file features (workflow) | — |
| 4. Architecture | 5 parallel background agents | workflow-architect, backend-system-architect, frontend-ui-developer, llm-integrator, ux-researcher |
| 5. Implementation + Tests | Parallel agents, single-pass artifacts with mandatory tests | backend-system-architect, frontend-ui-developer, llm-integrator, test-generator, rapid-ui-designer |
| 6. Integration Verification | Code review + real-service integration tests | backend, frontend, code-quality-reviewer, security-auditor |
| 7. Scope Creep | Compare planned vs actual (detection) | workflow-architect |
| 8. E2E Verification | Browser + API E2E testing (guide) | — |
| 9. Documentation | Save decisions to memory graph | — |
| 10. Reflection | Lessons learned, estimation accuracy | workflow-architect |
See Agent Phases for detailed agent prompts and spawn templates.
For Agent Teams mode, see Agent Teams Phases.
If working on a GitHub issue, run the Start Work ceremony from issue-progress-tracking and post progress comments after major phases.
Maintain checkpoints after each task. See Feedback Loop for triggers and actions.
Phase 5 test-generator MUST produce tests matching the change type:
| Change Type | Required Tests | testing-patterns Rules |
|---|---|---|
| API endpoint | Unit + Integration + Contract | integration-api, verification-contract, mocking-msw |
| DB schema/migration | Migration + Integration | integration-database, data-seeding-cleanup |
| UI component | Unit + Snapshot + A11y | unit-aaa-pattern, integration-component, a11y-testing, e2e-playwright |
| Business logic | Unit + Property-based | unit-aaa-pattern, pytest-execution, verification-techniques |
| LLM/AI feature | Unit + Eval | llm-evaluation, llm-mocking |
| Full-stack feature | All of the above | All matching rules |
Before running integration tests, detect infrastructure:
# Auto-detect real service testing capability (PARALLEL)
Glob(pattern="**/docker-compose*.yml")
Glob(pattern="**/testcontainers*")
Grep(pattern="testcontainers|docker-compose", glob="requirements*.txt")
Grep(pattern="testcontainers|docker-compose", glob="package.json")
If detected: run integration tests against real services, not just mocks. Reference testing-patterns rules: integration-database, integration-api, data-seeding-cleanup.
Do NOT proceed to Phase 9 (Documentation) if test-generator produced 0 tests. Return to Phase 5 and generate tests for the implemented code.
run_in_background: true, launch all agents in ONE messageTeamDelete() after completion; press Ctrl+F twice as manual fallbackork:explore: Explore codebase before implementingork:verify: Verify implementations work correctlyork:issue-progress-tracking: Auto-updates GitHub issues with commit progressActivates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.