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 description is critically deficient across all dimensions. It functions as a bare invocation stub rather than a useful skill description—it provides no information about what the skill does, when to use it, or what user requests should trigger it. Claude would have no basis for selecting this skill from a list of available skills.

Suggestions

Add a clear description of what the skill does with concrete actions (e.g., 'Creates and manages pull requests across multiple repositories in a swarm pattern' or whatever the actual functionality is).

Add an explicit 'Use when...' clause with natural trigger terms that users would say (e.g., 'Use when the user asks about creating PRs across repos, multi-repo pull requests, or batch PR management').

Replace the invocation instruction ('invoke with $agent-swarm-pr') with capability-focused language—invocation details belong in the skill body, not the description.

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 that it exists.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states how to invoke it ('$agent-swarm-pr') without explaining its purpose or trigger conditions.	1 / 3
Trigger Term Quality	The only potential trigger term is 'swarm-pr', which is a technical/internal name that users would not naturally say. There are no natural language keywords describing the skill's purpose.	1 / 3
Distinctiveness Conflict Risk	The unique invocation command '$agent-swarm-pr' provides some distinctiveness, so it's unlikely to conflict with other skills. However, the lack of any meaningful description means Claude cannot properly distinguish when to use it.	2 / 3
	Total	5 / 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 excessively verbose, largely aspirational, and lacks actionable executable guidance. It reads more like a product roadmap or marketing document than an operational skill file, with hypothetical CLI commands for a tool that isn't clearly established, duplicated concepts across sections, and no coherent workflow with validation checkpoints. The MCP tool usage examples use incorrect syntax and the overall structure buries any useful information in hundreds of lines of speculative content.

Suggestions

Strip the content down to 50-80 lines focusing on the actual MCP tools listed in frontmatter with correct invocation syntax and a single clear workflow (e.g., PR review lifecycle)

Add a concrete sequential workflow with numbered steps and explicit validation checkpoints (e.g., 1. Get PR diff → 2. Analyze complexity → 3. Spawn agents → 4. Validate results → 5. Post review)

Remove or move to separate reference files: webhook setup, GitHub Actions YAML, label mapping config, metrics/reporting, and security considerations

Replace hypothetical 'npx ruv-swarm' commands with actual executable examples using the MCP tools declared in frontmatter (mcp__github__*, mcp__claude-flow__*)

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~300+ lines with massive redundancy. Multiple sections show the same concepts (PR init, review, merge) repeated with slight variations. The 'Advanced Swarm PR Coordination' section largely duplicates earlier content using MCP tool syntax. Explains obvious concepts like webhook handling and label mapping that Claude already understands. Many code blocks are aspirational/hypothetical rather than functional.	1 / 3
Actionability	Most commands reference a non-standard tool ('npx ruv-swarm') with no installation or setup instructions. The MCP tool invocations use incorrect syntax (JSON-like objects instead of actual function calls). Code examples are largely hypothetical/aspirational rather than executable - the webhook handler is incomplete (missing body parsing), and the bash scripts assume tools that may not exist. No clear indication of what's real vs. planned.	1 / 3
Workflow Clarity	Despite being a complex multi-step workflow skill, there are no clear sequential workflows with validation checkpoints. The content jumps between disconnected features without establishing a coherent process. No error handling, no feedback loops for failed operations, no validation steps before destructive actions like merging. The pre/post hooks in frontmatter hint at a workflow but the body never clearly sequences them.	1 / 3
Progressive Disclosure	References to related files (swarm-issue.md, sync-coordinator.md, workflow-automation.md) at the bottom provide some navigation, but no bundle files exist to support them. The content itself is a monolithic wall covering too many topics inline (webhooks, GitHub Actions, label mapping, metrics, security) that should be split into separate reference files. Some section organization exists but is poorly prioritized.	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/claude-flow
Commit: 2b9e2de

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.