parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system simultaneously, when establishing file ownership to prevent merge conflicts in a shared codebase, when designing interface contracts so parallel implementers can build against each other's APIs before they are ready, or when deciding whether to use vertical slices versus horizontal layers for a full-stack feature.
63
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/agent-teams/skills/parallel-feature-development/SKILL.mdQuality
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 an excellent skill description that clearly defines a specific niche (multi-agent parallel development coordination), lists concrete actions and strategies, and provides comprehensive trigger conditions via an explicit 'Use this skill when...' clause with five distinct scenarios. The description uses proper third-person voice and includes domain-specific trigger terms that users would naturally use when needing this capability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: coordinate parallel feature development, file ownership strategies, conflict avoidance rules, integration patterns, decomposing features into work streams, establishing file ownership, designing interface contracts, and choosing vertical slices vs horizontal layers. | 3 / 3 |
Completeness | Clearly answers both 'what' (coordinate parallel feature development with file ownership, conflict avoidance, integration patterns) and 'when' with an explicit 'Use this skill when...' clause listing five specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'parallel feature development', 'file ownership', 'merge conflicts', 'multi-agent', 'interface contracts', 'vertical slices', 'horizontal layers', 'full-stack feature', 'shared codebase', 'work streams'. These cover a wide range of natural phrasings for this domain. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a very clear niche around multi-agent parallel development coordination, file ownership, and conflict avoidance. The specificity of terms like 'multi-agent implementation', 'file ownership strategies', and 'interface contracts' make it highly unlikely to conflict with general coding or project management skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-organized strategic guide for parallel feature development that covers the key concepts (file ownership, conflict avoidance, integration patterns, branch management) with reasonable structure. Its main weaknesses are the lack of a concrete sequenced workflow for actually performing decomposition, and the content being more descriptive/conceptual than actionable — it reads more like a reference document than an executable skill. The troubleshooting section is a genuine strength, providing practical solutions to common problems.
Suggestions
Add a concrete step-by-step workflow at the top (e.g., '1. List all files the feature touches → 2. Group into ownership sets → 3. Verify no file has two owners → 4. Create interface contracts for boundaries → 5. Assign branches') with explicit validation checkpoints.
Make the actionability more concrete by providing a template or checklist that Claude can fill out when decomposing a feature, such as a markdown table mapping files to owners with a conflict-check step.
Consider extracting the detailed integration patterns (vertical/horizontal/hybrid) and troubleshooting into separate referenced files to improve progressive disclosure and keep the main SKILL.md focused on the core workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably well-structured but includes some unnecessary elaboration. The 'When to Use This Skill' section repeats the description, and some patterns (vertical slice, horizontal layer) are explained at a level Claude already understands. The pros/cons lists and 'Best for' annotations add modest value but could be tighter. | 2 / 3 |
Actionability | The skill provides concrete structural examples (directory assignments, TypeScript interface contracts, branch naming conventions) which are helpful. However, it's primarily a conceptual/strategic guide rather than executable — there are no actual commands to run, no scripts to invoke, and the code blocks are illustrative rather than copy-paste ready for a real workflow. | 2 / 3 |
Workflow Clarity | The skill describes strategies and patterns but lacks a clear sequenced workflow for actually performing parallel feature decomposition. There's no step-by-step process like '1. Analyze the feature, 2. Identify boundaries, 3. Create contract files, 4. Assign ownership, 5. Validate no overlaps.' The troubleshooting section partially compensates but there are no explicit validation checkpoints or feedback loops for the decomposition process itself. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and the related skills links at the bottom are appropriate one-level-deep references. However, the document is fairly long (~150 lines of substantive content) and some sections like the detailed integration patterns or troubleshooting could be split into separate files. Without bundle files, the skill is monolithic but not egregiously so. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
34632bc
- 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.