Name: agent-swarm-pr
Rating: 68.2 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-swarm-pr

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

2.62x

Quality

52%

Does it follow best practices?

Impact

97%

2.62x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-swarm-pr/SKILL.md

The canonical home for this skill is agent-swarm-pr in ruvnet/claude-flow

Quality

Content

38%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 skill body is a long, code-heavy reference with strong concrete command coverage, but it is verbose, contains pervasive '$' escaping corruption that breaks many examples, lacks validation checkpoints around destructive PR operations, and references missing bundle files.

Suggestions

Fix the '$' escaping corruption throughout (e.g. '.github$workflows' -> '.github/workflows', '$swarm init' -> '$swarm init' as a literal trigger, 'actions$checkout' -> 'actions/checkout') so commands are executable.

Add explicit validation/verification steps before destructive or batch operations such as auto-merge and pr-fix --commit-fixes (e.g. verify swarm status and review count before merging).

Split the inlined reference material into actual referenced files (swarm-issue.md, sync-coordinator.md, workflow-automation.md) and create those files, or remove the dangling references.

Dimension	Reasoning	Score
Conciseness	The body is ~390 lines with many overlapping command sections and padded scenarios, noticeably verbose beyond what Claude needs; not a 1 because most sections are task-oriented rather than concept explanation.	2 / 5
Actionability	Concrete gh/npx commands and code are present, but pervasive '$' corruption in paths and MCP tool calls misformatted as bash make many examples non-executable as written.	3 / 5
Workflow Clarity	Sections are topical but lack an end-to-end sequenced workflow, and destructive/batch operations (auto-merge, pr-fix --commit-fixes, multi-PR coordination) have no validation checkpoints, which caps this at 3 per the rubric.	3 / 5
Progressive Disclosure	It is a monolithic single file with content that belongs in separate references, and the three referenced sibling .md files (swarm-issue, sync-coordinator, workflow-automation) do not exist and are only mentioned at the very end.	2 / 5
	Total	10 / 20 Passed

Description

66%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 clearly states what the skill does with several concrete capabilities, but omits any 'Use when...' trigger guidance, which caps completeness. It is reasonably specific and distinct.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases, e.g. 'Use when managing multi-agent code review on pull requests, automating PR validation, or coordinating swarm-based PR workflows.'

Include natural synonyms users might say (e.g. 'PRs', 'merge requests', 'code review swarms') to broaden trigger coverage.

Tighten 'automated PR lifecycle management' into one or two more concrete actions (e.g. 'auto-spawn review agents and merge approved PRs').

Dimension	Reasoning	Score
Specificity	Names the PR-swarm domain and several concrete actions ('coordinates multi-agent code review, validation, and integration workflows', 'automated PR lifecycle management'), with only minor abstraction gaps.	4 / 5
Completeness	The 'what' is clear, but there is no 'Use when...' or equivalent trigger clause, which the rubric explicitly caps at 3.	3 / 5
Trigger Term Quality	Natural terms users would say appear ('pull request', 'code review', 'validation', 'integration workflows', 'PR lifecycle'); a few synonyms or phrasings are missing, keeping it just below 5.	4 / 5
Distinctiveness Conflict Risk	The PR-swarm niche is mostly distinct from generic review skills, with only minor overlap risk against closely related PR tools.	4 / 5
	Total	15 / 20 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/ruflo
Path: .agents/skills/agent-swarm-pr/SKILL.md
Commit: fa13ee4

Reviewed: about 8 hours 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.