decomposition

Resolves task dependencies, generates machine-actionable delegation specs, 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.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

90%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable skill body that uses tables, templates, and decision trees to convey executable guidance without padding. Workflow sequencing is clear with QA checkpoints; the main gap is un-enumerated external references and a missing explicit retry loop in the spec template.

Suggestions

Enumerate the '5 Foundation References' (or link a file listing them) so the reference is not buried.

Add an explicit validate→fix→retry feedback loop to the Delegation Spec template's Expected Output section to strengthen workflow_clarity.

Clarify which referenced artifacts (LESSONS-LEARNED.md, project-consistency, panel-majority-vote) are external project/skill loads vs. bundle files, since none exist in this bundle.

Dimension	Reasoning	Score
Conciseness	The body is dense and lean — ASCII diagrams, decision trees, and tables carry the content with no padding or explanation of concepts Claude already knows; nearly every token earns its place.	5 / 5
Actionability	Provides a copy-paste-ready Delegation Spec template, a concrete filled prompt example ('TAS-42 — Fix token refresh ...'), a delegation-mechanism decision tree, and exact partition paths — fully executable guidance covering common cases.	5 / 5
Workflow Clarity	The phased sequence is clear (topological sort → phases → delegation mechanism → mixed-delegation table) with checkpoints via acceptance-criteria checkboxes and a QA-gate phase, but the spec template lacks an explicit validate→fix→retry feedback loop.	4 / 5
Progressive Disclosure	Well-organized into clear sections with one-level-deep signals ('> Load project-consistency skill', 'Read LESSONS-LEARNED.md'), but no bundle files exist and the '5 Foundation References' are mentioned without being enumerated.	4 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states both capabilities and trigger conditions in third person. Trigger terms are natural, though minor synonym/extension coverage keeps it just below maximal on that one dimension.

Dimension	Reasoning	Score
Specificity	Lists three concrete actions ('Resolves task dependencies, generates machine-actionable delegation specs, structures phased subtask plans') with comprehensive coverage of the skill's purpose, matching the multiple-specific-actions anchor.	5 / 5
Completeness	Explicitly answers both what (first sentence: resolves dependencies, generates specs, structures plans) and when ('Use when writing delegation specs, resolving task dependencies, ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'writing delegation specs', 'assigning work to sub-agents', and 'partitioning a feature into parallelizable phases' give good coverage, though it lacks common synonyms/file extensions and slightly mirrors the what-clause.	4 / 5
Distinctiveness Conflict Risk	The multi-agent delegation/decomposition framing is a clear niche with distinct triggers and minimal overlap with general planning skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: monkilabs/opencastle
Path: src/orchestrator/skills/decomposition/SKILL.md
Commit: fa0c341

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.