agent-swarm-pr

Agent skill for swarm-pr - invoke with $agent-swarm-pr

2.62x

Quality

—

Does it follow best practices?

Impact

97%

2.62x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

42%

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

The body is highly actionable with concrete executable commands but is verbose and redundant, lacks an explicit sequenced workflow with validation checkpoints for risky merge operations, and references external files that do not exist. It reads as a feature catalog rather than a navigable, layered skill document.

Suggestions

Collapse the repeated PR-init examples (feature/bug/doc PRs) into one parameterized example and move the long command catalogs into reference files to cut token weight and reduce redundancy.

Add an explicit end-to-end workflow with validation checkpoints for destructive operations, e.g. validate review status -> confirm swarm complete -> only then auto-merge, with a fix-and-retry loop on failure.

Either create the referenced swarm-issue.md, sync-coordinator.md, and workflow-automation.md files in a references/ directory or remove the broken 'See also' links so navigation is not misleading.

Dimension	Reasoning	Score
Conciseness	At ~390 lines the body is padded with near-duplicate npx ruv-swarm command variants and repeated PR-init examples, plus concept reminders Claude already knows ('Ensure GitHub tokens have appropriate scopes'), fitting the verbose/padded anchor.	1 / 3
Actionability	It provides extensive concrete, copy-paste-ready commands with specific flags (e.g. 'gh pr view 123 --json ...', 'npx ruv-swarm github pr-init 123 --auto-agents', 'gh pr merge 123 --auto --squash'), matching the fully-executable anchor.	3 / 3
Workflow Clarity	Content is organized as feature-categorized examples rather than a sequenced workflow, and destructive/batch operations like auto-merge lack explicit validation-feedback checkpoints, capping clarity at the steps-present-but-checkpoints-implicit level.	2 / 3
Progressive Disclosure	The body is a monolithic wall of code blocks with weak sectioning, and it closes by referencing swarm-issue.md, sync-coordinator.md, and workflow-automation.md that do not exist in any bundle directory, matching the monolithic/broken-organization anchor.	1 / 3
	Total	7 / 12 Passed

Description

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 frontmatter description is a placeholder-style meta-label that fails to state concrete capabilities or when to use the skill, relying on an internal invocation token instead of natural trigger language. It is distinguishable only by its jargon name, not by any described behavior.

Suggestions

Replace 'Agent skill for swarm-pr - invoke with $agent-swarm-pr' with a third-person statement of concrete actions, e.g. 'Coordinates multi-agent code-review swarms on GitHub pull requests: spawns review/test/security agents, posts progress, and drives merge readiness.'

Add an explicit 'Use when...' trigger clause naming natural terms users would say, such as 'Use when managing multi-agent PR reviews, coordinating swarm validation, or automating PR lifecycle tasks.'

Drop the internal 'invoke with $agent-swarm-pr' instruction from the description; move invocation mechanics into the body so the description reads as a capability summary.

Dimension	Reasoning	Score
Specificity	The description only labels the skill ('Agent skill for swarm-pr') without naming any concrete capability or action, matching the vague/abstract anchor rather than a domain-plus-actions level.	1 / 3
Completeness	It offers only a meta-label of what the skill is and provides no 'Use when...' clause, leaving both the 'what does this do' and 'when should Claude use it' questions very weak.	1 / 3
Trigger Term Quality	'invoke with $agent-swarm-pr' supplies a single internal jargon token rather than natural phrases a user would say, fitting the no-natural-keywords/technical-jargon anchor.	1 / 3
Distinctiveness Conflict Risk	The 'swarm-pr' token is fairly distinct so broad conflict is unlikely, yet the description gives no functional niche, keeping it in the somewhat-specific-but-overlapping band rather than a clear niche.	2 / 3
	Total	5 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: ruvnet/claude-flow
Commit: 8ae8752

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.