project-setup
Create a new GitHub project with standard configuration. Use when user asks to "create a project", "set up a new repo", "initialize a repository", or wants to start a new GitHub project.
92
88%
Does it follow best practices?
Impact
100%
1.75xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%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 a well-structured skill description with excellent trigger terms and completeness. The main weakness is the lack of specificity about what 'standard configuration' entails - listing concrete actions like creating README, .gitignore, license files, or setting up branch protection would strengthen it.
Suggestions
Expand 'standard configuration' to list specific actions (e.g., 'Creates README, .gitignore, license, and configures branch settings')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (GitHub project) and one action (create with standard configuration), but doesn't list multiple specific concrete actions like what 'standard configuration' includes (e.g., README, .gitignore, license, branch protection). | 2 / 3 |
Completeness | Clearly answers both what (create a new GitHub project with standard configuration) and when (explicit 'Use when' clause with multiple trigger phrases). The structure follows best practices. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'create a project', 'set up a new repo', 'initialize a repository', 'start a new GitHub project'. These are realistic phrases users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on GitHub project creation. The trigger terms are specific to repository initialization and unlikely to conflict with other skills like code editing or general file management. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill with executable commands and clear structure. The main weakness is the lack of validation steps between operations - if the repo creation fails or API calls return errors, there's no guidance on detection or recovery. The content is appropriately concise and well-organized for its purpose.
Suggestions
Add validation after repo creation (e.g., 'Verify with `gh repo view <repo-name>` before proceeding')
Include error handling guidance for common API failures (409 Conflict, 404, permission errors)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, providing only the necessary commands and configuration without explaining what GitHub, repos, or branch protection are. Every section serves a clear purpose. | 3 / 3 |
Actionability | Fully executable bash commands throughout with proper gh CLI syntax. All commands are copy-paste ready with clear placeholders for customization. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced, but lacks validation checkpoints. No verification that repo creation succeeded before configuring settings, no error handling guidance if API calls fail. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections: overview of what gets created, then step-by-step process, then example usage. Appropriate length for a single SKILL.md without needing external references. | 3 / 3 |
Total | 11 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- dwmkerr/claude-toolkit
- Commit
92f335c
- 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.