agent-swarm-pr
Agent skill for swarm-pr - invoke with $agent-swarm-pr
34
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/skillValidation 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, when to use it, or any natural trigger terms. A user or Claude would have no way to know when this skill is appropriate to select.
Suggestions
Add a clear explanation of what 'swarm-pr' actually does (e.g., 'Coordinates multiple agents to review and process pull requests' or whatever the actual functionality is)
Include a 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when reviewing PRs, coordinating code reviews, or managing pull request workflows')
Replace or supplement the technical name 'swarm-pr' with descriptive language that explains the skill's purpose in plain terms
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for swarm-pr' 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 triggers. | 1 / 3 |
Trigger Term Quality | The only terms present are 'agent skill', 'swarm-pr', 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 | Without any description of what the skill does, it's impossible to distinguish it from other skills. The term 'swarm-pr' is opaque and provides no context for differentiation. | 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 is excessively verbose, containing far more example code than necessary to convey the concepts. While it provides concrete commands, the reliance on undocumented tools and inconsistent syntax reduces actionability. The content would benefit significantly from consolidation - the same patterns are repeated multiple times with minor variations.
Suggestions
Consolidate the 10+ similar PR initialization examples into a single template with parameter variations noted, reducing content by 50%+
Clarify the MCP tool invocation syntax - use consistent format (either JSON objects or function call syntax) and explain how these are actually executed
Add explicit validation checkpoints to workflows, especially before merge operations (e.g., 'Verify swarm consensus before proceeding')
Move the webhook handler, GitHub Actions workflow, and detailed code examples to separate reference files, keeping only essential quick-start content in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive repetition of similar concepts. Contains massive amounts of example code that could be consolidated, explains obvious concepts like webhook handlers, and includes redundant sections (e.g., multiple nearly identical PR initialization examples for different PR types). | 1 / 3 |
Actionability | Provides concrete bash commands and code examples that appear executable, but many rely on hypothetical tools ('npx ruv-swarm') without clear installation/setup instructions. The MCP tool invocations use inconsistent syntax (JSON-like objects vs actual function calls) making them ambiguous. | 2 / 3 |
Workflow Clarity | Contains multiple workflow examples but lacks explicit validation checkpoints. The pre/post hooks describe what happens but don't provide clear error recovery paths. Missing validation steps between critical operations like swarm initialization and task orchestration. | 2 / 3 |
Progressive Disclosure | References external files at the end (swarm-issue.md, sync-coordinator.md, workflow-automation.md) which is good, but the main content is a monolithic wall of examples without clear hierarchy. Core concepts are buried among extensive code samples that could be moved to separate reference files. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
100%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.
- 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.