git-pr

Generate PR description and automatically create pull request on GitHub

Quality

41%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/git-pr/SKILL.md

Quality

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 is concise and identifies the core task (generating PR descriptions and creating pull requests on GitHub), but it lacks a 'Use when...' clause, which is critical for skill selection. It would benefit from more specific capability details and explicit trigger terms to help Claude distinguish it from other GitHub or git-related skills.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to open a PR, create a pull request, generate a PR description, or submit changes to GitHub.'

Include common user-facing trigger term variations such as 'PR', 'open a PR', 'merge request', 'submit changes', 'code review description'.

Expand the capability description with more specific actions, e.g., 'Analyzes git diffs to generate PR descriptions, supports templates, and automatically creates pull requests on GitHub via the API.'

Dimension	Reasoning	Score
Specificity	Names the domain (GitHub PRs) and two actions (generate PR description, create pull request), but doesn't elaborate on specific capabilities like template usage, diff analysis, or formatting details.	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. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also fairly thin, warranting a 1.	1 / 3
Trigger Term Quality	Includes good natural terms like 'PR description', 'pull request', and 'GitHub', but misses common variations users might say such as 'PR', 'merge request', 'open a PR', 'submit PR', or 'code review'.	2 / 3
Distinctiveness Conflict Risk	Fairly specific to GitHub pull requests which helps distinguish it, but could overlap with general GitHub skills, git workflow skills, or code review skills without clearer boundary definitions.	2 / 3
	Total	7 / 12 Passed

Implementation

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill provides a reasonable overview of PR automation with clear option variants and tool priorities, but falls short on actionability—lacking concrete examples of generated PR descriptions, template formats, or MCP tool call patterns. Workflow steps lack validation checkpoints and error recovery, and some sections (Mermaid guidelines, Context7 integration) provide generic advice rather than specific, actionable instructions.

Suggestions

Add a concrete example of a generated PR description showing the expected output format, including the Mermaid diagram and Japanese content

Include validation/error handling steps in workflows (e.g., check if branch exists on remote before push, verify PR template exists, handle gh CLI failures)

Replace the generic Mermaid Diagram Guidelines section with a specific example diagram showing a typical code change visualization

Make the Context7 Integration section actionable by showing the exact MCP tool call pattern with example queries rather than listing technology names

Dimension	Reasoning	Score
Conciseness	Mostly efficient but includes some unnecessary sections like the Mermaid Diagram Guidelines which are fairly generic advice Claude already knows (appropriate diagram types, consistent styling). The Context7 Integration section is also somewhat vague padding.	2 / 3
Actionability	Provides specific tool names and CLI commands (gh pr create --draft, gh pr edit --body), but lacks executable examples of actual PR description output, template format, or concrete Serena MCP tool invocation patterns. The Mermaid and Context7 sections are vague rather than concrete.	2 / 3
Workflow Clarity	Three workflow variants are clearly sequenced with numbered steps, but there are no validation checkpoints or error handling. What happens if gh pr create fails? What if there's no PR template? What if the branch doesn't exist on remote? No feedback loops for these failure modes.	2 / 3
Progressive Disclosure	Content is reasonably structured with clear sections and a useful options table, but everything is inline in one file. The PR template format, example PR descriptions, and Mermaid diagram examples could be split into referenced files. No external references are provided.	2 / 3
	Total	8 / 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: sc30gsw/claude-code-customes
Commit: 7aff694

Reviewed: 7 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.