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

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-swarm-pr/SKILL.md

Quality

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an extremely weak description that provides virtually no useful information for skill selection. It only states the skill's name and invocation command without describing any capabilities, use cases, or trigger conditions. It is essentially a label rather than a description.

Suggestions

Add concrete actions describing what swarm-pr does (e.g., 'Coordinates multiple agents to review pull requests, split large PRs into smaller ones, or manage PR workflows').

Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks about pull request review, PR splitting, multi-agent code review, or collaborative PR management').

Replace the invocation instruction ('invoke with $agent-swarm-pr') with functional description content—invocation details belong in the skill body, not the description field used for skill selection.

Dimension	Reasoning	Score
Specificity	The description provides no concrete actions whatsoever. 'Agent skill for swarm-pr' is entirely vague—it doesn't describe what the skill does, only names itself. There are no verbs describing capabilities.	1 / 3
Completeness	The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides an invocation command ('$agent-swarm-pr') with no explanation of purpose or trigger conditions.	1 / 3
Trigger Term Quality	The only potentially relevant term is 'swarm-pr', which is a tool/project name rather than a natural keyword a user would say. There are no natural language trigger terms like 'pull request', 'review', 'merge', etc.	1 / 3
Distinctiveness Conflict Risk	While 'swarm-pr' is a unique name, the description is so vague that Claude cannot determine when to select it versus any other skill. Without knowing what it does, there's no basis for distinguishing it from other agent skills.	1 / 3
	Total	4 / 12 Passed

Implementation

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

This skill is extremely verbose and largely aspirational, documenting a hypothetical CLI tool ('npx ruv-swarm') with unverified commands rather than providing actionable guidance for Claude. The MCP tool calls use incorrect syntax, code examples are not executable, and there is no coherent workflow with validation steps. The content reads more like product marketing documentation than an actionable skill file.

Suggestions

Replace aspirational CLI commands with actual working instructions using the declared MCP tools (mcp__github__*, mcp__claude-flow__*) with correct invocation syntax

Reduce content by 70%+ - pick one clear workflow (e.g., 'review a PR with a swarm') and document it end-to-end with validation checkpoints, rather than listing dozens of disconnected features

Add explicit validation steps and error recovery for destructive operations like auto-merge (e.g., 'verify all checks pass before proceeding')

Move reference material (label mappings, webhook handlers, GitHub Actions configs) to separate files and keep SKILL.md as a concise overview with clear navigation

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~300+ lines with massive redundancy. Multiple sections repeat the same concepts (PR initialization shown 5+ times in different forms). Includes explanations of basic concepts, hypothetical webhook handlers, and speculative features. Much of this content appears to be for a product that may not exist, padding the skill with aspirational CLI commands rather than actionable guidance.	1 / 3
Actionability	Despite containing many code blocks, the commands reference a tool ('npx ruv-swarm') whose existence and API are unverified. The MCP tool invocations use incorrect syntax (JSON-like objects instead of actual tool call format). The webhook handler is incomplete (missing body parsing). Most examples are aspirational rather than executable, describing a hypothetical CLI interface rather than providing working instructions.	1 / 3
Workflow Clarity	No clear sequential workflow with validation checkpoints. The skill jumps between disconnected features (PR creation, comments, webhooks, metrics, merge automation) without a coherent process flow. The 'Integration with Claude Code' section lists 5 vague steps without any concrete validation or error recovery. For destructive operations like auto-merge, there are no proper safeguards or feedback loops.	1 / 3
Progressive Disclosure	The skill does reference external files at the bottom (swarm-issue.md, sync-coordinator.md, workflow-automation.md) and has section headers providing some structure. However, the main file is a monolithic wall of content that should be split into separate reference files. Inline content is far too long for a SKILL.md overview.	2 / 3
	Total	5 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Commit: 398f7c2

Reviewed: 3 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.