Name: agent-swarm-issue
Rating: 55.400000000000006 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-swarm-issue

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

2.93x

Quality

33%

Does it follow best practices?

Impact

97%

2.93x

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-issue/SKILL.md

The canonical home for this skill is agent-swarm-issue 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 body is command-dense and broadly actionable but suffers from excessive length and redundancy, broken/non-existent tool invocations and file paths, missing validation around destructive batch operations, and a monolithic structure with dead cross-references. It functions more as a dumped command catalog than a well-organized skill overview.

Suggestions

Split the monolith: move templates, the full command catalog, and examples into references/ files and keep SKILL.md as a concise overview with one-level-deep links — and create the referenced swarm-pr.md/sync-coordinator.md/workflow-automation.md or remove the links.

Add validation checkpoints to destructive/batch workflows (e.g. dry-run before 'gh issue close', confirm count before batch label edits, verify subtask creation before editing the parent body).

Fix the broken shell and paths: replace '2>$dev$null' with '2>/dev/null' and restore '/' in paths like '.github/swarm-labels.json', 'org/repo#456', and '.github/workflows/issue-swarm.yml'.

Dimension	Reasoning	Score
Conciseness	At ~580 lines the body is noticeably verbose, with many redundant sections (Issue Types & Strategies, Examples, Automation Examples, Integration Patterns) repeating near-identical 'npx ruv-swarm github ...' command patterns that could be collapsed, matching the score-2 anchor for padded sections.	2 / 5
Actionability	It provides many concrete, mostly-executable gh/jq commands, but several are non-functional: '2>$dev$null' instead of '2>/dev/null' and corrupted paths like '.github$swarm-labels.json' and 'org$repo#456' where '/' was replaced by '$', leaving guidance incomplete.	3 / 5
Workflow Clarity	Sequences like Initialize-from-Issue and Task Decomposition are commented step-by-step, but destructive/batch operations (auto-closing stale issues, closing duplicates, batch label edits) have no validation or dry-run checkpoints, capping workflow clarity at 3 per the batch/destructive rule.	3 / 5
Progressive Disclosure	Content is a single monolithic file with no bundle files present, yet it inlines ~580 lines of templates, examples, and command reference that belong in separate files, and its only cross-references (swarm-pr.md, sync-coordinator.md, workflow-automation.md) point to non-existent files.	2 / 5
	Total	10 / 20 Passed

Description

28%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 reads as an auto-generated placeholder: it names the skill domain and its invocation token but states no concrete capabilities and provides no 'Use when' trigger guidance. It fails to tell a user or Claude what the skill actually does or when to reach for it.

Suggestions

Replace the placeholder with concrete actions, e.g. 'Decomposes GitHub issues into multi-agent swarm tasks, assigns agents by topology, and tracks progress via issue checklists and comments.'

Add an explicit trigger clause: 'Use when the user wants to break a GitHub issue into coordinated subtasks, automate issue triage, or run a multi-agent swarm against an issue.'

Drop the redundant 'invoke with $agent-swarm-issue' line — invocation is handled by the skill system, not the description.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for swarm-issue - invoke with $agent-swarm-issue' names the domain but lists zero concrete actions, mirroring the score-2 anchor 'Processes PDF files' rather than the action-rich score-4/5 anchors.	2 / 5
Completeness	It gives a vague 'what' ('Agent skill for swarm-issue') and no 'Use when...' trigger guidance at all, so per the cap for missing trigger clauses it cannot exceed 3 and sits at 2 for having only a vague what with no when.	2 / 5
Trigger Term Quality	It offers only the invocation token '$agent-swarm-issue' and the bare term 'swarm-issue', missing the natural phrases a user would actually say, matching the score-2 anchor of one or two generic keywords.	2 / 5
Distinctiveness Conflict Risk	The 'swarm-issue' niche is somewhat specific, but the generic 'Agent skill for...' framing gives no distinct behavioral triggers, leaving moderate overlap risk with other coordination/automation skills.	3 / 5
	Total	9 / 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
skill_md_line_count	SKILL.md is long (578 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: ruvnet/ruflo
Path: .agents/skills/agent-swarm-issue/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.