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.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/agent-teams/skills/parallel-feature-development/SKILL.md

Quality

Content

72%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.

The body is well-structured and highly actionable, with a clean overview-plus-references split and concrete examples for every strategy. Its main weakness is workflow_clarity: integration and merge workflows involve destructive/batch operations but lack explicit validate-then-proceed checkpoints, which caps that dimension.

Suggestions

Add an explicit integration verification checkpoint to the Branch Management section (e.g., 'After merging all sub-branches, run the build/type/test checks from references/merge-strategies.md before declaring the feature complete') to lift workflow_clarity above the destructive/batch cap.

In the Interface Contracts section, include a one-line validation step such as 'run tsc --noEmit to confirm both implementers still satisfy the contract' so the coordination loop has a concrete feedback checkpoint.

Replace abstract guidance like 'communicate the change via broadcast' with a concrete trigger (e.g., naming the channel or message template) to push actionability from 4 to 5.

Dimension	Reasoning	Score
Conciseness	The body is largely lean — sectioned strategies, short 'Best for' tags, and compact code blocks with no lecturing on concepts Claude already knows; minor verbosity comes from the troubleshooting section restating ideas already covered in Conflict Avoidance, but it earns its place for actionability.	4 / 5
Actionability	Concrete, copy-pasteable artifacts throughout: ownership tables, branch-tree diagrams, a complete TypeScript interface-contract example, and named remediation steps in troubleshooting; it stops short of 5 because several guidance blocks (e.g., 'broadcast before modification') describe intent without a concrete command or template.	4 / 5
Workflow Clarity	Sequences are present (the numbered 'When Files Must Be Shared' flow, the hybrid/vertical/horizontal decision framing) but there are no explicit validation checkpoints for integration — the rubric's destructive/batch cap applies since merges and shared-file edits are risky batch operations, capping this at 3 despite clear sequencing.	3 / 5
Progressive Disclosure	SKILL.md is a well-organized overview that defers depth to two real one-level-deep references (file-ownership.md, merge-strategies.md) and signals cross-skill links clearly; the bundle structure matches the body's references, so navigation is easy and appropriately split.	5 / 5
	Total	16 / 20 Passed

Description

83%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.

The description is strong: it states concrete capabilities and provides an explicit, multi-scenario 'Use this skill when...' trigger clause that clearly answers both what and when. It is slightly long but the added detail serves trigger clarity rather than padding.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'decomposing a large feature', 'establishing file ownership', 'designing interface contracts', 'deciding vertical slices versus horizontal layers' — with only minor coverage gaps (e.g., integration/merge work is named in the body but not the description).	4 / 5
Completeness	Explicitly answers both what ('Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns') and when via a detailed 'Use this skill when...' clause enumerating five concrete trigger scenarios.	5 / 5
Trigger Term Quality	Strong natural triggers ('merge conflicts', 'interface contracts', 'parallel implementers', 'vertical slices versus horizontal layers') that a user would plausibly say; a few common synonyms (e.g., 'concurrent development', 'splitting work') are absent, keeping it just below 5.	4 / 5
Distinctiveness Conflict Risk	The multi-agent parallel-development niche is fairly distinct and unlikely to collide with unrelated skills, though it overlaps somewhat with general team-composition/communication skills referenced at the bottom; minor overlap risk keeps it at 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: wshobson/agents
Path: plugins/agent-teams/skills/parallel-feature-development/SKILL.md
Commit: 367cb6a

Reviewed: 2 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.