agent-github-modes

Agent skill for github-modes - invoke with $agent-github-modes

1.07x

Quality

Does it follow best practices?

Impact

86%

1.07x

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-github-modes/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 is an extremely weak description that fails on all dimensions. It provides no information about what the skill does, when it should be used, or what specific capabilities it offers. It reads more like an internal label than a functional description for skill selection.

Suggestions

Describe the specific actions this skill performs (e.g., 'Switches between GitHub workflow modes such as PR review, issue triage, and branch management').

Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user wants to change GitHub workflow mode, review PRs, manage issues, or switch between GitHub operational contexts').

Remove the invocation command ('invoke with $agent-github-modes') from the description and replace it with concrete capability details that help Claude distinguish this skill from other GitHub-related skills.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for github-modes' 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 provides an invocation command, with no explanation of functionality or usage triggers.	1 / 3
Trigger Term Quality	The only keyword is 'github-modes' which is a technical/internal term, not something a user would naturally say. There are no natural trigger terms like 'pull request', 'branch', 'merge', etc.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it could overlap with any GitHub-related skill. 'github-modes' is undefined and provides no clear niche or distinct triggers.	1 / 3
	Total	4 / 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 a catalog of GitHub mode names and abstract descriptions with no actionable implementation. It lists 10 modes with repetitive metadata-style bullet points but never defines what Claude should actually do when any mode is invoked. The content is verbose, lacks executable code, has no workflow steps or validation, and would be far more effective as a concise overview pointing to detailed per-mode files.

Suggestions

For each mode, define concrete step-by-step workflows with actual gh CLI commands and validation checkpoints (e.g., 'verify PR was created with gh pr view <number>') instead of abstract property lists.

Reduce the main file to a brief overview table of modes with one-line descriptions, then link to separate files (e.g., PR-MANAGER.md, RELEASE-MANAGER.md) for detailed instructions.

Remove descriptive metadata like 'Conflict Resolution: Intelligent' and 'Review Mode: Automated' that provide no actionable guidance, replacing them with executable examples showing exact commands and expected outputs.

Replace pseudocode examples (the BatchTool and swarm integration blocks) with real, executable bash or tool invocation sequences that Claude can actually run.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with repetitive structure across 10+ modes that all follow the same template pattern. Most content is descriptive metadata (bullet points like 'Review Mode: Automated', 'Conflict Resolution: Intelligent') that provides no actionable value. Claude already knows what these GitHub concepts are.	1 / 3
Actionability	Despite listing many modes and tools, there is no concrete, executable guidance for any of them. The usage examples show invocation syntax ($github pr-manager ...) but never show what Claude should actually do when a mode is invoked. The 'batch operations' and 'swarm integration' examples are pseudocode/pseudo-JSON, not executable code.	1 / 3
Workflow Clarity	No multi-step workflows are defined for any mode. Each mode is described with abstract properties but lacks any sequenced steps, validation checkpoints, or error handling. For operations involving git and GitHub (which can be destructive), this is a significant gap.	1 / 3
Progressive Disclosure	Monolithic wall of text with 10+ modes all inlined at the same level of detail. No references to external files for detailed mode instructions. The content would benefit enormously from a brief overview with links to per-mode documentation.	1 / 3
	Total	4 / 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: 0d9f9b1

Reviewed: 2 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.