agent-swarm-issue
Agent skill for swarm-issue - invoke with $agent-swarm-issue
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-swarm-issue45
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 97%
↑ 2.93xAgent success when using this skill
Validation for skill structure
Discovery
0%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 provides only a name and invocation command without explaining what the skill does, what actions it performs, or when it should be used. Claude would have no basis for selecting this skill appropriately from a pool of available skills.
Suggestions
Add concrete actions describing what the skill does (e.g., 'Creates, triages, and manages swarm-related issues' or 'Coordinates multi-agent task distribution').
Include a 'Use when...' clause with natural trigger terms users might say (e.g., 'Use when coordinating multiple agents, distributing tasks, or managing swarm workflows').
Explain the domain and context so Claude can distinguish this from other agent-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for swarm-issue' is completely abstract with no indication of what the skill actually does. | 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 with no explanation of purpose or use cases. | 1 / 3 |
Trigger Term Quality | The only terms present are 'agent', 'swarm-issue', and the invocation command. These are technical/internal terms, not natural keywords a user would say when needing this functionality. | 1 / 3 |
Distinctiveness Conflict Risk | While 'swarm-issue' is a unique term, the description is so vague that Claude cannot determine when to select this skill. The lack of any functional description makes proper skill selection impossible. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill attempts to be comprehensive but sacrifices usability for exhaustiveness. It covers too many scenarios (bug reports, features, technical debt, epics, cross-repo, metrics) in a single file, making it difficult to find relevant guidance. The reliance on an unverified 'ruv-swarm' CLI tool and inconsistent MCP tool syntax reduces practical actionability.
Suggestions
Reduce to a focused quick-start section (under 50 lines) with the most common issue-to-swarm workflow, moving specialized scenarios (bug handling, epic management, metrics) to separate reference files
Remove explanatory content about GitHub Actions, issue templates, and gh CLI basics that Claude already knows - focus only on the swarm-specific integration patterns
Add explicit validation checkpoints for destructive operations like auto-closing issues (e.g., 'Review the list of issues to be closed before proceeding')
Clarify which tools are real MCP tools vs hypothetical CLI commands, and ensure consistent syntax for MCP tool invocations
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with massive code blocks covering every possible scenario. Much of this content (GitHub Actions syntax, issue templates, basic gh CLI usage) is knowledge Claude already possesses. The skill is over 400 lines when it could be under 100. | 1 / 3 |
Actionability | Provides concrete bash commands and code examples, but many rely on a hypothetical 'npx ruv-swarm' tool that may not exist or work as shown. The mcp__claude-flow calls at the end use inconsistent syntax (underscores vs hyphens) and mix pseudocode with real commands. | 2 / 3 |
Workflow Clarity | Steps are listed for various operations but lack explicit validation checkpoints. For destructive operations like auto-closing stale issues, there's no verification step before execution. The workflow jumps between many different use cases without clear sequencing. | 2 / 3 |
Progressive Disclosure | References other files at the end (swarm-pr.md, sync-coordinator.md) which is good, but the main content is a monolithic wall of examples covering every possible scenario. Content that should be in separate reference files (issue templates, GitHub Actions workflows, all the different swarm types) is inline. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 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 |
Total | 10 / 11 Passed | |
- Reviewed
Table of Contents
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.