CtrlK
BlogDocsLog inGet started
Tessl Logo

decomposition

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.

100

Quality

100%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Task Decomposition

Dependency Resolution

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)

Delegation Spec

FieldContent
TrackerTAS-XX — Title
Complexity[score]/13 → [tier]
AgentAgent Name
Objective1-3 sentences: what to build/change and why
ContextKey files, related patterns, prior phase output, relevant lessons
ConstraintsFile partition, explicit exclusions, phase dependencies
Acceptance Criteria[ ] checklist
Expected OutputFiles 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.

Prompt Quality

QualityExample
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."

Delegation Mechanism

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)

Mixed Delegation

PhaseModeWork
1sub-agentResearch — context, patterns, file map
2backgroundFoundation — DB migration + scaffolding (parallel)
3sub-agentIntegration — wire components to data
4backgroundValidation — security audit + tests + docs (parallel)
5sub-agentQA gate — verify phases, run builds
6sub-agentPanel review — load panel-majority-vote skill

Foundation-First Pattern

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:

  • Foundation owns: src/styles/, src/components/Layout.*, src/components/ui/
  • Page tasks own: their page file + page-specific components only
  • No page task may list a foundation-owned path in its 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.

Repository
monkilabs/opencastle
Last updated
Created

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.