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 fails on every dimension. It provides no information about what the skill does, when it should be used, or what user requests should trigger it. It reads as a placeholder rather than a functional description, containing only an invocation command and an opaque internal name.

Suggestions

Describe the concrete actions this skill performs (e.g., 'Creates and manages pull requests across multiple repositories' or 'Coordinates parallel PR reviews using swarm agents').

Add an explicit 'Use when...' clause with natural trigger terms users would say, such as 'pull request', 'PR', 'code review', 'merge request', or whatever the actual use case is.

Remove or supplement the invocation command with a meaningful explanation of the skill's purpose and capabilities so Claude can determine when to select it.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for swarm-pr' is entirely vague and does not describe what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only provides an invocation command ('$agent-swarm-pr') without explaining the skill's purpose or trigger conditions.	1 / 3
Trigger Term Quality	The only keyword is 'swarm-pr' which is a technical/internal name, not a natural term a user would say. There are no natural language trigger terms like 'pull request', 'PR review', 'code review', etc.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it provides no distinguishing characteristics. Without knowing what 'swarm-pr' does, it's impossible to differentiate it from any other skill.	1 / 3
	Total	4 / 12 Passed

Implementation

14%

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

This skill is excessively verbose, repeating similar concepts across multiple sections without clear workflow sequencing or validation checkpoints. While it provides numerous code examples, many reference unverifiable tools or use non-executable pseudo-syntax. The monolithic structure with no supporting bundle files despite referencing three external files makes it poorly organized for practical use.

Suggestions

Reduce content by 60-70%: eliminate redundant sections (e.g., merge automation appears 3 times), remove explanations of basic concepts (webhooks, GitHub Actions), and consolidate the PR init examples into one canonical workflow

Add explicit validation checkpoints and error recovery: after each major step (swarm init, agent spawn, review posting, merge), include verification steps and what to do when operations fail

Split into referenced files: move GitHub Actions config, webhook setup, label mappings, and metrics/reporting into separate bundle files, keeping SKILL.md as a concise overview with clear navigation links

Make MCP tool invocations use proper syntax and provide a single end-to-end executable workflow rather than scattered disconnected examples

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~300+ lines with massive redundancy. Multiple sections show the same concepts (PR init, status checks, merge automation) repeated in different forms. The webhook handler, label mapping JSON, GitHub Actions YAML, and extensive bash examples are largely duplicative. Much of this explains concepts Claude already knows (how webhooks work, how to parse JSON with jq, basic GitHub Actions syntax). The 'Advanced Swarm PR Coordination' section at the end repeats earlier content using MCP tool syntax.	1 / 3
Actionability	Contains many concrete bash commands and code examples, but they reference a tool ('npx ruv-swarm') whose existence and API are unverifiable. The MCP tool invocations at the end use a pseudo-syntax (not valid JSON or function calls) making them non-executable. The JavaScript lifecycle hooks reference undefined functions (analyzePRComplexity, getOptimalAgents). Much is aspirational rather than copy-paste ready.	2 / 3
Workflow Clarity	Despite being a complex multi-step workflow involving destructive operations (merging PRs, auto-committing fixes), there are no explicit validation checkpoints or error recovery steps. The sequences are loosely described across many disconnected sections without a clear end-to-end workflow. No feedback loops for when swarm operations fail, reviews are rejected, or merge conflicts occur.	1 / 3
Progressive Disclosure	Monolithic wall of text with no content split into referenced files despite the massive length. References to swarm-issue.md, sync-coordinator.md, and workflow-automation.md at the bottom, but no bundle files exist to support them. The content that could be in separate reference files (webhook setup, GitHub Actions config, label mappings, metrics/reporting) is all inline, making the skill overwhelming.	1 / 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/claude-flow
Commit: 9d4a9ea

Reviewed: 6 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.