agent-pr-creator
Analyzes git diffs and commit history to intelligently fill PR templates and create pull requests via gh CLI. Use when user wants to create a PR, needs PR description help, or says 'create a pull request', 'fill PR template', 'make a PR', 'open a pull request', or mentions PR creation.
92
Quality
88%
Does it follow best practices?
Impact
100%
1.04xAverage score across 3 eval scenarios
Quality
Discovery
100%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 excellent skill description that hits all the key criteria. It provides specific capabilities (git diff analysis, template filling, gh CLI usage), comprehensive trigger terms covering natural user phrasings, and a clear 'Use when...' clause. The description is concise yet complete, making it easy for Claude to select this skill appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Analyzes git diffs and commit history', 'intelligently fill PR templates', and 'create pull requests via gh CLI'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (analyzes diffs, fills templates, creates PRs via gh CLI) AND when with explicit 'Use when...' clause containing multiple trigger scenarios and exact phrases users might say. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'create a PR', 'PR description help', 'create a pull request', 'fill PR template', 'make a PR', 'open a pull request', 'PR creation'. Covers common variations and phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on PR creation workflow with distinct triggers like 'PR template', 'gh CLI', and pull request-specific terminology. Unlikely to conflict with general git or code review skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with excellent actionability and workflow clarity. The step-by-step process is clear with proper validation checkpoints, and the commands are executable. Minor improvements could be made by trimming the trigger examples and condensing the troubleshooting section, as Claude can infer much of this behavior.
Suggestions
Remove or significantly condense the 'Positive Trigger' and 'Non-Trigger' examples section - Claude can infer appropriate triggering from the description
Consider condensing the troubleshooting section into a brief inline note or moving to a separate TROUBLESHOOTING.md file
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some redundancy, such as the positive/negative trigger examples which explain obvious behavior Claude can infer. The troubleshooting section, while useful, adds bulk that could be condensed. | 2 / 3 |
Actionability | Provides fully executable bash commands, specific gh CLI syntax, clear title formatting rules, and concrete examples of how to fill each template section. Copy-paste ready commands throughout. | 3 / 3 |
Workflow Clarity | Clear 5-step sequence with explicit validation checkpoints: checking for existing PRs, uncommitted changes, and remote tracking before proceeding. The 'Important' section adds critical guardrails for destructive operations. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections, but everything is inline in one file. The troubleshooting section and examples could potentially be split out, though for a skill of this complexity, keeping it together is reasonable. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
- 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.