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 user requests should trigger it. It reads more like an internal label than a functional description.

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 asks about GitHub workflows, PR modes, review settings, or branch strategies').

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

Dimension	Reasoning	Score
Specificity	The description provides 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 how to invoke it, providing no functional or contextual information.	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 conflict 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 essentially a catalog of mode names with superficial metadata but no actionable content. It lists 10 GitHub integration modes with vague descriptions and non-executable pseudo-examples, but never defines what Claude should actually do when any mode is invoked. The content is simultaneously too long (verbose repetitive structure) and too shallow (no real workflows, commands, or validation steps).

Suggestions

Replace the shallow mode catalog with actual step-by-step workflows for each mode, including specific gh CLI commands, validation checkpoints, and error recovery steps (e.g., 'If PR has conflicts: run git merge --no-commit, resolve, then gh pr push')

Reduce the number of inline modes to 2-3 core ones with full executable examples, and split remaining modes into separate referenced files (e.g., [PR_MANAGER.md](PR_MANAGER.md))

Remove all vague metadata fields like 'Review Quality: Deep' and 'Conflict Resolution: Intelligent' that provide no actionable guidance, replacing them with concrete configuration or behavioral instructions

Convert the pseudo-JavaScript batch operations and swarm integration examples into actual executable code or real CLI commands that Claude can run

Dimension	Reasoning	Score
Conciseness	Extremely verbose with repetitive structure across 10+ modes, each listing vague metadata fields like 'Coordination Mode: Hierarchical' and 'Review Quality: Deep' that add no actionable value. Much of this is padding that Claude doesn't need—descriptions like 'Pull request management and review coordination' are self-evident from the mode name.	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 like '$github pr-manager "..."' but never explain what actually happens or what steps Claude should take. The batch operations and swarm integration examples use pseudocode/pseudo-JavaScript that isn't executable. No real commands, no real workflows, no copy-paste-ready solutions.	1 / 3
Workflow Clarity	No multi-step workflows are defined for any of the 10 modes. There are no sequenced steps, no validation checkpoints, no error handling, and no feedback loops. Each mode is just a bullet-point description with no actual process. For operations involving PR merges, releases, and security scans, the complete absence of workflow steps is a critical gap.	1 / 3
Progressive Disclosure	The content is a monolithic wall of text with 10 modes all described at the same shallow level inline, with no references to supporting files. There are no bundle files, no linked documentation, and no hierarchy. The content would benefit enormously from splitting each mode into its own file with detailed workflows, while keeping SKILL.md as a concise overview.	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: e6dc21f

Reviewed: 4 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.