agent-swarm-issue
Agent skill for swarm-issue - invoke with $agent-swarm-issue
34
0%
Does it follow best practices?
Impact
97%
2.93xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-swarm-issue/SKILL.mdQuality
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 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 domain it operates in. It reads more like a stub or placeholder than a functional skill description.
Suggestions
Describe what 'swarm-issue' actually does with concrete actions (e.g., 'Creates, triages, and assigns issues across multiple repositories' or whatever the actual functionality is).
Add an explicit 'Use when...' clause with natural trigger terms that describe the scenarios and user language that should activate this skill.
Include domain-specific keywords and file types or concepts the skill handles to make it distinguishable from other agent skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for swarm-issue' 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 states it's an 'agent skill' and how to invoke it, providing no functional or contextual information. | 1 / 3 |
Trigger Term Quality | The only keyword is 'swarm-issue' which is technical jargon, not a natural term a user would say. There are no natural language trigger terms that would help Claude match user requests to this skill. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so generic ('agent skill') that it provides no distinguishing characteristics. Without knowing what it does, it could conflict with any other agent-based skill. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an extremely verbose, largely non-actionable document that references fictional CLI tools (npx ruv-swarm) throughout, making almost none of the code examples executable. It reads more like a product marketing document or wishlist than an actual skill instruction set. The content is massively over-scoped, covering everything from GitHub Actions workflows to cross-repo coordination to metrics analytics, without providing concrete, working guidance for any single task.
Suggestions
Remove all references to the fictional 'npx ruv-swarm' CLI and replace with actual executable commands using real tools (gh CLI, MCP tools listed in frontmatter, or bash scripts)
Reduce content by 80%+ to focus on the core workflow: reading an issue, decomposing it into tasks, spawning agents, and tracking progress—with real, executable examples for each step
Add explicit validation checkpoints (e.g., verify issue exists before processing, confirm agent spawn succeeded, validate subtask creation) and error handling for destructive operations like auto-closing issues
Move detailed sections like GitHub Actions configs, issue templates, automation examples, and metrics into separate referenced files to improve progressive disclosure
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 400+ lines with massive redundancy. Many sections repeat similar CLI patterns (issue-init, issue-decompose, etc.) with slight variations. Includes extensive hypothetical tooling (npx ruv-swarm) commands that are not real executable tools, and explains concepts like issue templates, label strategies, and best practices that Claude already understands. The 'Best Practices' and 'Security & Permissions' sections are generic advice that adds no actionable value. | 1 / 3 |
Actionability | Nearly all code examples reference a non-existent CLI tool (npx ruv-swarm) with fabricated subcommands, making them entirely non-executable. The bash scripts mix real gh CLI commands with fictional tools, creating confusion about what actually works. The MCP tool invocations at the end use incorrect syntax (not valid JSON calls). None of the examples are copy-paste ready for real use. | 1 / 3 |
Workflow Clarity | Despite showing many multi-step processes, there are no validation checkpoints or error recovery steps. The 'Task Decomposition' and 'Progress Tracking' sections show sequences but never verify success of intermediate steps. Destructive operations like auto-closing stale issues and closing duplicates lack confirmation or rollback mechanisms. The overall flow between sections is unclear—it's a collection of disconnected command snippets rather than a coherent workflow. | 1 / 3 |
Progressive Disclosure | Monolithic wall of content with 15+ sections all inline, many of which could be separate files (automation examples, integration patterns, metrics, GitHub Actions config). References to swarm-pr.md, sync-coordinator.md, and workflow-automation.md at the bottom, but no bundle files are provided. The sheer volume of inline content defeats any organizational benefit from the section headers. | 1 / 3 |
Total | 4 / 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 | |
- Repository
- ruvnet/ruflo
- Commit
619b263
- 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.