agent-github-pr-manager

Agent skill for github-pr-manager - invoke with $agent-github-pr-manager

1.08x

Quality

13%

Does it follow best practices?

Impact

94%

1.08x

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-pr-manager/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 functions as little more than a label. It provides no information about what the skill does, when it should be used, or what user requests should trigger it. Claude would have almost no basis for selecting this skill appropriately from a list of available skills.

Suggestions

Add concrete actions the skill performs, e.g., 'Creates, reviews, merges, and manages GitHub pull requests. Lists open PRs, adds reviewers, checks CI status, and resolves merge conflicts.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about pull requests, PRs, code reviews, merging branches, or GitHub repository management.'

Remove the invocation syntax ('invoke with $agent-github-pr-manager') from the description and replace it with capability and trigger information that helps Claude decide when to select this skill.

Dimension	Reasoning	Score
Specificity	The description provides no concrete actions whatsoever. It only names a tool ('github-pr-manager') without describing what it does. 'Agent skill for' is completely vague.	1 / 3
Completeness	The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance.	1 / 3
Trigger Term Quality	While 'github' and 'pr' appear in the tool name, there are no natural keywords a user would say like 'pull request', 'review', 'merge', 'code review', or 'GitHub'. The invocation syntax '$agent-github-pr-manager' is technical jargon, not a user trigger term.	1 / 3
Distinctiveness Conflict Risk	While the name 'github-pr-manager' hints at a niche, the description itself is so vague ('Agent skill for...') that it provides no distinguishing information. It could conflict with any GitHub-related skill since no specific capabilities are outlined.	1 / 3
	Total	4 / 12 Passed

Implementation

27%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is overly verbose and descriptive rather than instructional, spending significant tokens explaining concepts Claude already understands (merge strategies, CI/CD, review processes). While it includes some useful executable gh CLI commands, most content is abstract workflow descriptions and organizational concepts without concrete, actionable steps or validation checkpoints. The monolithic structure with no supporting bundle files compounds the token inefficiency.

Suggestions

Cut the content by 60-70%: remove explanations of what PRs, merge strategies, and CI/CD are; focus only on specific commands, flags, and decision logic Claude wouldn't already know.

Make workflow patterns executable: replace prose steps like 'Assign reviewers based on CODEOWNERS' with actual gh CLI commands (e.g., `gh pr edit --add-reviewer @team`), and add explicit validation checkpoints (e.g., 'Run `gh pr checks` and only proceed when all pass').

Split into bundle files: move the PR description template to a TEMPLATES.md file, error handling to TROUBLESHOOTING.md, and multi-agent coordination to COORDINATION.md, keeping SKILL.md as a concise overview with references.

Remove or make concrete the 'Multi-Agent Coordination' section—currently it describes abstract 'swarm' concepts with no executable implementation, consuming tokens without adding actionable value.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with many sections that describe concepts Claude already knows (what merge strategies are, what CI/CD integration means, what a PR description template looks like). The 'Multi-Agent Coordination' section references vague 'swarm' concepts without actionable detail. Much of this reads like documentation about PR workflows rather than targeted instructions Claude needs.	1 / 3
Actionability	The 'GitHub CLI Integration' section provides real executable commands, and the PR description template is concrete. However, most workflow patterns are listed as numbered prose steps without executable commands, and the 'Usage Examples' section shows natural language prompts rather than actionable instructions. The review swarm and multi-agent coordination sections are entirely abstract with no concrete implementation.	2 / 3
Workflow Clarity	Multiple workflow patterns are listed (Standard Feature PR, Hotfix PR, Large Feature PR) with numbered steps, but they lack validation checkpoints and feedback loops. There's no explicit 'verify before proceeding' step in any workflow. Error handling is mentioned but only as a descriptive list without concrete recovery commands or validation steps.	2 / 3
Progressive Disclosure	The content is a monolithic wall of text with no references to external files and no bundle files to support it. Everything is inlined—PR templates, workflow patterns, error handling, best practices—resulting in a very long document that would benefit significantly from splitting into separate reference files.	1 / 3
	Total	6 / 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: 9d4a9ea

Reviewed: 6 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.