src/orchestrator/skills/decomposition/SKILL.md
Resolves task dependencies, generates machine-actionable delegation specs, and structures phased subtask plans for multi-agent work. Use when writing delegation specs, resolving task dependencies, building phased subtask plans for multi-agent work, assigning work to sub-agents, or partitioning a feature into parallelizable phases.
npx skillsauth add etylsarin/opencastle decompositionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
TaskB → TaskA = B depends on A (must finish first).
Topological sort: No-dep tasks → Phase 1. Tasks depending only on Phase N → Phase N+1. Same-phase tasks with no mutual deps run in parallel.
Cycle detection: If A → B → C → A, split one task into an independent part + a dependent part.
Graph: Plan:
E → C → A Phase 1: A, B (parallel)
D → B Phase 2: C, D (parallel)
F → C, D Phase 3: E, F (parallel)
| Field | Content |
|-------|---------|
| Tracker | TAS-XX — Title |
| Complexity | [score]/13 → [tier] |
| Agent | Agent Name |
| Objective | 1-3 sentences: what to build/change and why |
| Context | Key files, related patterns, prior phase output, relevant lessons |
| Constraints | File partition, explicit exclusions, phase dependencies |
| Acceptance Criteria | [ ] checklist |
| Expected Output | Files changed · Verification · AC status · Discovered issues |
For score 1-3, objective + files + criteria is sufficient. See REFERENCE.md for the full delegation spec template.
Read .opencastle/LESSONS-LEARNED.md before starting. Add a lesson if you retry any approach.
| Quality | Example |
|---------|---------|
| Strong (score 2) | "TAS-42 — Fix token refresh. Users get 'Invalid token' after 30 min. JWT 1h expiry in libs/auth/src/server.ts. Fix refresh logic. Only libs/auth/. Run auth tests." |
| Strong (score 8) | Use Delegation Spec Template above (all sections). |
| Weak | "Fix the authentication bug." |
Need result immediately?
YES → Is dependency for next step?
YES → Sub-Agent (inline)
NO → Sub-Agent or Background (if large)
NO → Expected > 5 min?
YES → Background Agent
NO → Sub-Agent (sequential)
| Phase | Mode | Work | |-------|------|------| | 1 | sub-agent | Research — context, patterns, file map | | 2 | background | Foundation — DB migration + scaffolding (parallel) | | 3 | sub-agent | Integration — wire components to data | | 4 | background | Validation — security audit + tests + docs (parallel) | | 5 | sub-agent | QA gate — verify phases, run builds | | 6 | sub-agent | Panel review — load panel-majority-vote skill |
Apply when: 2+ pages/views/UI sections · multiple agents produce visual output · no existing design system.
Phase 1: foundation-setup
├── Creates: design tokens, layout, UI component library, style guide brief
└── All visual tasks → depends_on: [foundation-setup]
Phase 2+: page tasks (parallel)
├── Each prompt includes 5 Foundation References
└── Consume tokens — never create new values
Partition rules:
src/styles/, src/components/Layout.*, src/components/ui/files[]Common mistake: Decomposing pages as independent Phase 1 tasks → each agent invents its own design.
Distinctive note (AI delegation): This skill focuses on decomposition that produces machine-actionable delegation prompts: file partitions, explicit acceptance criteria, and machine-friendly constraints (exact paths, line ranges, forbidden files). The output should be ready to paste into a sub-agent prompt without additional human translation.
Load the project-consistency skill for the full Foundation Phase pattern, prompt templates, and anti-patterns.
development
Defines 10 sequential validation gates: secret scanning, lint/test/build checks, blast radius analysis, dependency auditing, browser testing, cache management, regression checks, and smoke tests. Use when running pre-deploy validation or CI checks, CI/CD pipelines, deployment pipeline validation, pre-merge checks, continuous integration, or pull request validation.
development
Generates test plans, writes unit/integration/E2E test files, identifies coverage gaps, and flags common testing anti-patterns. Use when writing tests, creating test suites, planning test strategies, mocking dependencies, measuring code coverage, or test planning.
development
Provides model routing rules, validates delegation prerequisites, supplies cost tracking templates, and defines dead-letter queue formats for Team Lead orchestration. Load when assigning tasks to agents, choosing model tiers, starting a delegation session, running a multi-agent workflow, delegating work, choosing which model to use, or assigning tasks.
testing
Saves and restores session state including task progress, file changes, and delegation history. Use when saving progress, resuming interrupted work, picking up where you left off, or checkpointing current work.