agent-pr-manager

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

3.94x

Quality

25%

Does it follow best practices?

Impact

75%

3.94x

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-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 description is critically deficient across all dimensions. It functions more as a label than a description, providing only an invocation command without explaining capabilities, use cases, or trigger conditions. Claude would have no meaningful basis to select this skill appropriately.

Suggestions

Add specific actions the skill performs (e.g., 'Creates pull requests, reviews PR diffs, manages PR comments, merges branches')

Include a 'Use when...' clause with natural trigger terms like 'pull request', 'PR', 'code review', 'merge request', 'GitHub PR'

Remove the invocation instruction from the description and replace with functional content that distinguishes this from other git/code skills

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for pr-manager' is completely abstract and does not describe what the skill actually does with PRs.	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 potentially relevant term is 'pr-manager' which is a technical/internal name, not natural language users would say. Missing terms like 'pull request', 'PR review', 'merge', 'GitHub', etc.	1 / 3
Distinctiveness Conflict Risk	While 'pr-manager' hints at pull requests, the description is so vague it could conflict with any code review, git, or repository management skill. No clear niche is established.	1 / 3
	Total	4 / 12 Passed

Implementation

50%

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

This skill provides a reasonable overview of PR management with swarm coordination but suffers from unclear syntax in examples (neither valid JavaScript nor proper MCP tool invocation format), missing validation checkpoints for merge operations, and some verbosity in capability descriptions. The structure is decent but the actionability is compromised by ambiguous code examples.

Suggestions

Convert code examples to proper MCP tool invocation syntax or clearly executable bash commands - the current JavaScript-like syntax is not copy-paste ready

Add explicit validation checkpoints before merge operations (e.g., 'Verify all checks pass: gh pr checks --watch' before proceeding to merge)

Trim the 'Capabilities' bullet list and 'Error Handling' sections which describe rather than instruct - Claude already understands these concepts

Include a concrete example of error recovery when a merge conflict occurs, showing the actual commands to resolve and retry

Dimension	Reasoning	Score
Conciseness	The content is moderately efficient but includes some unnecessary verbosity like marketing-style bullet points ('Comprehensive testing integration and validation') and explanatory sections that could be trimmed. The examples are useful but could be more compact.	2 / 3
Actionability	Provides code examples but they use JavaScript-like syntax that isn't clearly executable (e.g., `mcp__claude-flow__swarm_init { topology: "mesh" }` isn't valid syntax). Mixes pseudo-API calls with actual bash commands, creating ambiguity about what's copy-paste ready.	2 / 3
Workflow Clarity	Steps are listed in logical sequence but lack explicit validation checkpoints. The 'Batch Operations Example' shows a workflow but doesn't include verification steps between operations or error recovery loops for destructive merge operations.	2 / 3
Progressive Disclosure	Content is organized with clear sections and references other modes at the end, but the main content is somewhat monolithic. The 'Integration with Other Modes' section provides good cross-references, but the core content could benefit from splitting detailed examples into separate files.	2 / 3
	Total	8 / 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: b2618f9

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.