agent-pr-manager
Agent skill for pr-manager - invoke with $agent-pr-manager
39
13%
Does it follow best practices?
Impact
75%
3.94xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-pr-manager/SKILL.mdQuality
Discovery
0%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 triggers should activate it. It reads as a placeholder rather than a functional description.
Suggestions
Add concrete actions the skill performs, e.g., 'Creates, reviews, and manages pull requests, updates PR descriptions, adds reviewers, and handles merge operations.'
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 PR descriptions.'
Remove the invocation instruction ('invoke with $agent-pr-manager') from the description, as it is operational detail that doesn't help Claude decide when to select this skill.
| 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. | 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 trigger information. | 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. Missing terms like 'pull request', 'PR review', 'merge', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so generic that it provides no distinguishing characteristics. 'Agent skill for pr-manager' could overlap with any PR-related skill and gives no clear niche. | 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 instructive, spending significant tokens on aspirational capability descriptions ('Automatic retry logic', 'No single point of failure') without concrete implementation. The code examples are pseudocode with hardcoded values rather than generalizable templates, and the lack of validation checkpoints in merge/review workflows is a notable gap. The content would benefit from aggressive trimming, executable examples, and splitting into overview + reference files.
Suggestions
Cut the 'Capabilities', 'Best Practices', 'Integration with Other Modes', and 'Error Handling' sections drastically - most describe features rather than instruct Claude. Replace with concrete error handling code and actual validation steps.
Make code examples generalizable by using placeholder variables (`:owner`, `:repo`, `:pr_number`) consistently instead of hardcoded values like 'ruvnet/ruv-FANN' and PR #54.
Add explicit validation checkpoints to workflows: check PR status before merging, verify test results before approving, handle merge conflict scenarios with concrete steps.
Split detailed examples and batch operations into a separate EXAMPLES.md file, keeping SKILL.md as a concise overview with the core workflow and links to detailed references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with significant padding. The 'Capabilities' bullet list, 'Best Practices' section, 'Integration with Other Modes', and 'Error Handling' sections are largely aspirational descriptions rather than actionable content. Much of this describes what the system supposedly does rather than instructing Claude on what to do. The content could be cut by 60%+ without losing actionable information. | 1 / 3 |
Actionability | Contains code examples with specific tool calls and bash commands, which is good. However, the JavaScript-style examples are pseudocode (not actually executable - e.g., `mcp__claude-flow__swarm_init { topology: "mesh", maxAgents: 4 }` isn't valid syntax for any runtime). The examples are hardcoded to specific repos ('ruvnet/ruv-FANN', PR #54) making them non-generalizable templates. The error handling section describes capabilities without concrete implementation. | 2 / 3 |
Workflow Clarity | The numbered usage patterns (Create PR, Review, Merge) provide a reasonable sequence, and the batch operations example shows a lifecycle. However, there are no explicit validation checkpoints or feedback loops - no 'if merge fails, do X' or 'verify PR status before merging' steps. For destructive operations like merging PRs, the absence of validation gates is a significant gap. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files for detailed content. Everything is inline - the batch operations, best practices, error handling, and integration sections all bloat the main file. The 'Integration with Other Modes' section references other modes but doesn't link to documentation. The content would benefit greatly from splitting detailed examples and reference material into separate files. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
100%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/ruflo
- Commit
398f7c2
- Reviewed
Table of Contents
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.