agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-github-modes35
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 — 86%
↑ 1.07xAgent 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 technical invocation command without explaining what the skill does, when to use it, or what capabilities it offers. This would be nearly impossible for Claude to correctly select from a pool of skills.
Suggestions
Add concrete actions describing what 'github-modes' actually does (e.g., 'Switches between GitHub workflow modes, manages branch strategies, configures PR templates').
Include a 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks about GitHub workflows, branch management, or PR processes').
Remove the invocation syntax from the description and replace with functional content that explains the skill's purpose and capabilities.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for github-modes' is completely abstract and does not describe 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, not functional information. | 1 / 3 |
Trigger Term Quality | The only potential trigger term is 'github-modes' which is technical jargon, not a natural phrase users would say. No common variations or natural keywords are included. | 1 / 3 |
Distinctiveness Conflict Risk | While 'github-modes' is a specific term, the description is so vague that it's unclear what distinguishes this from any other GitHub-related skill. The lack of specificity creates ambiguity. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a catalog of mode names and capabilities without any actionable implementation guidance. It describes what modes exist and what tools they use, but never explains how Claude should actually perform any GitHub workflow. The content is verbose, repetitive, and lacks the concrete steps, validation checkpoints, and executable examples needed to be useful.
Suggestions
Replace mode catalogs with actual workflow implementations - show step-by-step what Claude should do when 'pr-manager' is invoked, including validation and error handling
Remove redundant capability listings and tool enumerations that Claude already knows; focus on project-specific conventions and constraints
Add concrete, executable examples with expected inputs/outputs instead of pseudocode patterns
Define explicit validation checkpoints for multi-step GitHub operations (e.g., 'verify PR created successfully before proceeding to review assignment')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with repetitive mode descriptions that follow identical patterns. Lists obvious tool names and capabilities Claude already knows (e.g., 'gh pr create', 'gh pr view'). The metadata-style bullet points ('Coordination Mode: Hierarchical', 'Max Parallel Operations: 10') add no actionable value. | 1 / 3 |
Actionability | Despite listing many 'modes', there's no concrete guidance on how to actually implement any of them. The usage examples show invocation syntax but not what Claude should actually do when invoked. The code examples are illustrative pseudocode, not executable workflows. | 1 / 3 |
Workflow Clarity | No actual workflows are defined - just lists of capabilities and tool names. There are no step-by-step processes, no validation checkpoints, and no error handling guidance. The 'Batch Operations Example' shows parallel commands but no sequencing or verification. | 1 / 3 |
Progressive Disclosure | Content is organized into sections with headers, but it's a monolithic document that could benefit from splitting detailed mode specifications into separate files. The structure exists but everything is inline with no references to external documentation. | 2 / 3 |
Total | 5 / 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.