agent-pr-manager

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

3.94x

Quality

13%

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 essentially a stub that only provides invocation syntax ('$agent-pr-manager') without describing any capabilities, use cases, or trigger conditions. It fails on every dimension because it gives Claude no information to determine when this skill should be selected over others. This would be indistinguishable from many other skills in a multi-skill environment.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Creates pull requests, updates PR descriptions, manages review assignments, and handles PR merges.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to create a pull request, update a PR description, request reviewers, merge a PR, or manage GitHub/GitLab pull requests.'

Remove the invocation instruction ('invoke with $agent-pr-manager') from the description field, as it is operational detail rather than selection criteria, and replace it with capability and trigger information.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for pr-manager' is entirely vague and does not describe what the skill actually does—no mention of creating PRs, reviewing code, managing branches, or any other specific capability.	1 / 3
Completeness	The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no 'Use when...' clause and no explanation of capabilities. It only states how to invoke the agent.	1 / 3
Trigger Term Quality	The only potentially relevant term is 'pr-manager', which is a tool name rather than a natural keyword a user would say. There are no natural trigger terms like 'pull request', 'PR review', 'merge', 'code review', etc.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it provides no clear niche. 'pr-manager' could overlap with any skill related to pull requests, project management, or even public relations. There are no distinct triggers to differentiate it.	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 padded with generic descriptions, marketing-style capability lists, and aspirational error handling claims that lack implementation details. While it provides some concrete code examples for PR management workflows, they use pseudo-syntax and are hardcoded to a specific repository, reducing their general utility. The skill would benefit significantly from trimming unnecessary content, adding validation checkpoints, and splitting detailed examples into referenced files.

Suggestions

Remove the 'Capabilities', 'Best Practices', and 'Error Handling' sections—they are generic advice and aspirational claims that waste tokens without providing actionable guidance.

Add explicit validation checkpoints before destructive operations like merging (e.g., 'Verify all checks pass: `gh pr checks 54` before proceeding to merge').

Replace hardcoded repo/PR values with placeholder patterns and ensure MCP tool call syntax matches actual invocation format rather than JavaScript-like pseudocode.

Extract the batch operations and detailed examples into a separate reference file (e.g., EXAMPLES.md) and keep SKILL.md as a concise overview with clear links.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with significant padding. Lists vague 'capabilities' Claude already understands, includes unnecessary best practices sections that are generic advice, explains concepts like 'no single point of failure' and 'automatic agent failover' that are aspirational rather than instructional. The 'Error Handling' section describes behaviors without any actionable implementation. Much of the content is marketing-style description rather than instruction.	1 / 3
Actionability	Provides concrete code examples with specific MCP tool calls and gh CLI commands, which is good. However, the code is not truly executable—it uses JavaScript-like pseudocode syntax for MCP calls (e.g., `mcp__claude-flow__swarm_init { topology: "mesh" }`) that isn't valid in any language. Examples are hardcoded to specific repos ('ruvnet/ruv-FANN') and PR numbers (54), making them templates rather than generalizable guidance. The error handling section describes behaviors without showing how to implement them.	2 / 3
Workflow Clarity	The PR lifecycle steps are presented in a logical sequence (create → review → test → merge), but there are no explicit validation checkpoints or feedback loops. For destructive operations like merging, there's no 'verify before proceeding' step. The error handling section claims automatic retry and conflict resolution but provides no concrete steps for how to handle failures. Missing validation caps this at 2.	2 / 3
Progressive Disclosure	Monolithic wall of content with no references to external files despite the complexity warranting them. The 'Integration with Other Modes' section references other skills but provides no links or file paths. No bundle files exist to support the content. All content—from basic usage to batch operations to best practices—is crammed into a single file with no clear navigation hierarchy.	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: d29d87f

Reviewed: 5 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.