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
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly articulates specific capabilities, provides explicit trigger guidance via a 'Use when...' clause, and uses domain-specific terminology that carves out a distinct niche. The description is concise yet comprehensive, covering both what the skill does and when it should be selected. It uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'resolves task dependencies', 'generates machine-actionable delegation specs', and 'structures phased subtask plans'. These are distinct, concrete capabilities rather than vague abstractions. | 3 / 3 |
Completeness | Clearly answers both 'what' (resolves dependencies, generates delegation specs, structures phased plans) and 'when' with an explicit 'Use when...' clause listing five distinct trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'delegation specs', 'task dependencies', 'subtask plans', 'multi-agent work', 'sub-agents', 'parallelizable phases', 'assigning work', 'partitioning a feature'. Good coverage of terms a user orchestrating multi-agent workflows would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around multi-agent task orchestration, delegation specs, and dependency resolution. The domain-specific terminology ('machine-actionable delegation specs', 'parallelizable phases', 'sub-agents') makes it highly unlikely to conflict with general project management or coding skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that is concise, highly actionable, and well-structured. It uses efficient notation (dependency arrows, decision trees, tables) to convey complex multi-agent decomposition workflows without wasted tokens. The progressive disclosure is well-handled with clear pointers to reference materials, and the Foundation-First pattern includes important anti-patterns and partition rules that prevent common mistakes.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. It uses tables, decision trees, and compact notation (e.g., `TaskB → TaskA`) instead of verbose prose. No unnecessary explanations of concepts Claude already knows. Every section earns its place. | 3 / 3 |
Actionability | Provides concrete, actionable artifacts: a complete delegation spec template with specific fields, a decision tree for delegation mechanism, partition rules with exact paths, and strong/weak prompt examples. The guidance is specific enough to produce machine-actionable output directly. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced: dependency resolution has an explicit algorithm (topological sort), phased delegation has numbered phases with modes, and the Foundation-First pattern has clear sequencing with dependency declarations. The decision tree for delegation mechanism provides clear branching logic. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references: 'See REFERENCE.md for the full delegation spec template' and 'Load the project-consistency skill for the full Foundation Phase pattern.' Content is appropriately split between overview and detailed materials. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- monkilabs/opencastle
- Commit
f5c8508
- Reviewed
Table of Contents
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.