agent-swarm-pr

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

2.62x

Quality

28%

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

Quality

Content

50%

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

The body offers extensive, mostly concrete command-based guidance for PR swarm management, but it is overly long, contains broken path escaping that makes several examples non-executable, and lacks validation checkpoints around destructive operations. Its only cross-file references are broken and point to non-existent files.

Suggestions

Fix the '$'-instead-of-'/' escaping throughout (paths like '.github/workflows/swarm-pr.yml', './swarm-issue.md', 'swarm/tasks-complete') so examples are executable.

Add explicit validation/feedback loops before destructive or batch steps such as 'pr-fix --commit-fixes' and 'gh pr merge --auto'.

Trim redundant command-variant sections and either create the referenced companion files or remove the broken 'See also' links.

Dimension	Reasoning	Score
Conciseness	The body is concrete (commands, not conceptual fluff Claude already knows), but at ~430 lines it is heavily bloated with redundant similar command examples and feature-listing sections that could be consolidated.	2 / 3
Actionability	Many 'gh' and 'npx ruv-swarm' commands are concrete, but pervasive '$'-instead-of-'/' path escaping (e.g. '.github$workflows$swarm-pr.yml', '$swarm*'), pseudocode MCP call blocks, and an incomplete webhook JS example make a meaningful portion non-executable as written.	2 / 3
Workflow Clarity	Some workflows are sequenced and the merge automation includes status/review checkpoints, but destructive and batch operations (auto-fix --commit-fixes, auto-merge) lack validation/feedback loops, capping this dimension at 2.	2 / 3
Progressive Disclosure	Section headers provide organization, but the only file references ('See also' swarm-issue.md, sync-coordinator.md, workflow-automation.md) use broken '.$' paths and the files do not exist in the bundle, while large reference-style content stays inline.	2 / 3
	Total	8 / 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 essentially an invocation hint rather than a capability statement: it names the skill but says nothing about what it does or when to use it. It lacks concrete actions, natural trigger terms, and any explicit usage guidance.

Suggestions

Rewrite the description to list concrete actions, e.g. 'Coordinates multi-agent code review, validation, and merge workflows on GitHub pull requests'.

Add an explicit trigger clause such as 'Use when managing PR-driven code review, automated PR validation, or multi-agent merge coordination'.

Replace the invocation-token phrasing with natural user keywords ('pull requests', 'PR code review', 'swarm coordination').

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for swarm-pr - invoke with $agent-swarm-pr' names a domain but states no concrete actions, matching the vague 'Helps with documents' anchor rather than the multi-action score-3 anchor.	1 / 3
Completeness	It neither explains what the skill concretely does nor provides any 'Use when...' trigger guidance, so both the 'what' and 'when' are missing or very weak.	1 / 3
Trigger Term Quality	'swarm-pr' and '$agent-swarm-pr' are invocation tokens, not natural phrases a user would say; there is no coverage of common terms like 'pull request', 'code review', or 'PR'.	1 / 3
Distinctiveness Conflict Risk	The explicit '$agent-swarm-pr' invoke token makes accidental triggering unlikely, but the surrounding prose is generic and could overlap with other agent/swarm skills, so it is not a clear score-3 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
Path: .agents/skills/agent-swarm-pr/SKILL.md
Commit: 26c35b5

Reviewed: about 5 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.