git-pr
Generate PR description and automatically create pull request on GitHub
Install with Tessl CLI
npx tessl i github:sc30gsw/claude-code-customes --skill git-pr65
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear domain (GitHub PRs) and basic actions but suffers from missing explicit trigger guidance, which is critical for skill selection. It's moderately specific but would benefit from more concrete action details and a 'Use when...' clause to help Claude distinguish it from related git/GitHub skills.
Suggestions
Add a 'Use when...' clause with trigger terms like 'create PR', 'open pull request', 'submit for review', 'push changes to GitHub'
Expand specific capabilities such as 'analyzes git diff to generate descriptions', 'supports PR templates', or 'adds reviewers and labels'
Include common user phrasings like 'merge request', 'ready for review', or 'submit my changes'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (GitHub PRs) and two actions (generate description, create pull request), but lacks detail on what kind of descriptions or additional capabilities like templates, formatting, or diff analysis. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'PR', 'pull request', and 'GitHub' which are natural terms, but misses common variations like 'merge request', 'open PR', 'submit changes', or 'push to review'. | 2 / 3 |
Distinctiveness Conflict Risk | GitHub and PR are fairly specific, but could overlap with general git skills, code review skills, or other GitHub automation skills without clearer boundaries. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is well-structured and concise, effectively communicating the PR automation workflow with good organization. However, it lacks concrete executable examples for the MCP tool calls and gh commands, and missing validation/error handling steps reduce confidence in complex multi-step operations.
Suggestions
Add concrete executable examples showing actual Serena MCP tool calls with expected inputs/outputs (e.g., `mcp__serena__search_for_pattern` with specific parameters)
Include complete gh command examples with all flags: `gh pr create --draft --title "..." --body "..."`
Add validation checkpoints: what to check after pushing, how to verify PR was created successfully, error recovery if gh command fails
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables and bullet points effectively. No unnecessary explanations of concepts Claude already knows - it jumps straight to actionable content. | 3 / 3 |
Actionability | Provides clear tool names and workflow steps, but lacks executable code examples. The gh commands are mentioned but not shown with full syntax, and Serena MCP tool usage lacks concrete examples of actual calls. | 2 / 3 |
Workflow Clarity | Steps are listed for each option variant, but validation checkpoints are missing. No error handling or feedback loops for when gh commands fail or when Serena tools return unexpected results. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections, appropriate use of tables for options, and logical grouping. Content is appropriately sized for a single SKILL.md file without needing external references. | 3 / 3 |
Total | 10 / 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.
- 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.