agent-pr-manager
Agent skill for pr-manager - invoke with $agent-pr-manager
35
7%
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 this is operational detail that doesn't help Claude decide when to select the 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
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is heavily padded with marketing-style descriptions and abstract claims ('Intelligent Review Strategy', 'No single point of failure') that provide no actionable guidance. The code examples use non-executable pseudocode with hardcoded values, and critical workflows like merging and batch operations lack any validation checkpoints or error recovery steps. The document would benefit greatly from being reduced to ~40 lines of concrete, executable guidance with explicit validation gates.
Suggestions
Remove all descriptive/marketing sections (Capabilities, Integration with Other Modes, abstract Best Practices) and replace with a concise quick-start workflow showing the most common PR lifecycle with real, parameterized commands.
Add explicit validation checkpoints before destructive operations: check PR status before merge, verify test results before approval, confirm no merge conflicts before proceeding.
Replace JavaScript pseudocode with actual executable bash commands using `gh` CLI or real MCP tool call syntax, using placeholder variables instead of hardcoded repo names and PR numbers.
Implement the claimed error handling with concrete code: show actual retry logic, conflict detection commands, and conditional branching based on test/check results.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with significant padding. Sections like 'Capabilities' are bullet-point marketing copy that adds no actionable value. 'Best Practices' and 'Error Handling' sections describe abstract concepts ('Automatic retry logic', 'No single point of failure') without any concrete implementation. 'Integration with Other Modes' is a list of references with no substance. Much of the content explains what the skill does rather than instructing how to do it. | 1 / 3 |
Actionability | The code examples show specific MCP tool calls and bash commands, which provides some concrete guidance. However, the JavaScript-style syntax is pseudocode (not executable), uses hardcoded repo names/PR numbers making them non-generalizable, and key operations like 'Automated conflict resolution' and 'Automatic retry logic' are mentioned but never implemented with actual code or commands. | 2 / 3 |
Workflow Clarity | While there are numbered usage patterns, there are no validation checkpoints or feedback loops for what are clearly destructive/batch operations (merging PRs, approving reviews). The 'Batch Operations Example' shows approving and merging without any conditional checks on test results or review status. The 'Error Handling' section claims automatic retry and conflict resolution but provides zero implementation details or verification steps. | 1 / 3 |
Progressive Disclosure | The skill is a monolithic wall of text with no bundle files to support it. References to other modes ('$github issue-tracker', '$sparc reviewer') are listed but not linked to actual files. All content is inline with no separation of overview from detailed reference material. The document is over 150 lines with no clear hierarchy between essential and supplementary information. | 1 / 3 |
Total | 5 / 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/claude-flow
- Commit
9d4a9ea
- 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.