create-pr
Use when creating a pull request — defaults to draft PRs, uses repo PR template if available, supports "ready for review" override
86
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
57%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 establishes a clear niche for PR creation and includes a 'Use when' clause, which is good. However, it focuses more on default behaviors and configuration options rather than concrete capabilities, and the trigger term coverage could be broader to catch common user phrasings like 'open a PR' or 'submit my changes'.
Suggestions
Add concrete actions the skill performs, e.g., 'Creates pull requests with generated titles and descriptions based on commit history'
Expand trigger terms to include common variations: 'PR', 'open a PR', 'submit changes', 'merge request'
Broaden the 'Use when' clause to cover related scenarios: 'Use when creating PRs, opening pull requests, submitting code for review, or when user mentions PR, pull request, or merge request'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (pull requests) and mentions some specific behaviors (defaults to draft, uses repo PR template, supports override), but doesn't list concrete actions like 'generates PR title', 'writes description', or 'analyzes diff'. | 2 / 3 |
Completeness | Has a 'Use when' clause which is good, but the 'what' is weak - it describes behaviors/defaults rather than capabilities. The 'when' is also narrow ('creating a pull request') without covering related scenarios like 'submitting code' or 'opening a PR'. | 2 / 3 |
Trigger Term Quality | Includes 'pull request' and 'draft PRs' which are natural terms, but misses common variations like 'PR', 'merge request', 'open a PR', or 'submit changes'. The phrase 'ready for review' is good but limited coverage overall. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on PR creation with distinct triggers. The mention of draft PRs, PR templates, and 'ready for review' makes it unlikely to conflict with other git-related skills like commit message generation. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that demonstrates best practices: it's concise yet complete, provides executable commands at every step, includes clear workflow with prerequisites and validation, and documents common pitfalls. The draft-by-default principle is well-explained with clear override conditions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, providing only necessary commands and guidance without explaining what PRs are or how git works. Every section serves a clear purpose. | 3 / 3 |
Actionability | Provides fully executable bash commands throughout, with specific gh CLI syntax, template detection paths, and copy-paste ready examples for both draft and non-draft scenarios. | 3 / 3 |
Workflow Clarity | Clear 3-step sequence with explicit prerequisites check, conditional logic for unpushed branches, template detection with fallback behavior, and validation steps before PR creation. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections (Overview, Process steps, Common Mistakes, Integration). Content is appropriately sized for a single file with references to related commands at the end. | 3 / 3 |
Total | 12 / 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.