Use this skill when asked to create a pull request (PR). It ensures all PRs follow the repository's established templates and standards.
Install with Tessl CLI
npx tessl i github:google-gemini/gemini-cli --skill pr-creator73
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/skillAgent success when using this skill
Validation for skill structure
Discovery
40%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 correctly uses third person voice and includes a 'Use when' clause, but lacks specificity about what concrete actions the skill performs beyond vaguely 'following templates and standards'. The trigger terms are adequate but could include more variations, and the overall description is too brief to clearly distinguish this skill from other git/code workflow skills.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Generates PR titles, descriptions, and checklists based on repository templates'
Expand trigger terms to include variations like 'merge request', 'submit code', 'open PR', 'push changes for review'
Clarify what 'templates and standards' means - does it auto-fill templates, validate formatting, add labels, link issues?
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only mentions 'create a pull request' as an action and vaguely references 'templates and standards' without specifying what concrete actions are performed (e.g., generating descriptions, adding labels, linking issues, running checks). | 1 / 3 |
Completeness | Has a 'Use when' clause addressing when to use it ('asked to create a pull request'), but the 'what' is weak - it only says it 'ensures PRs follow templates and standards' without explaining what specific actions or outputs the skill produces. | 2 / 3 |
Trigger Term Quality | Includes 'pull request' and 'PR' which are natural terms users would say, but misses common variations like 'merge request', 'open a PR', 'submit changes', or 'code review'. | 2 / 3 |
Distinctiveness Conflict Risk | The PR/pull request focus provides some distinction, but 'templates and standards' is vague enough that it could overlap with other code review, git workflow, or documentation skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill with excellent actionability and workflow clarity. It provides concrete, executable commands with critical safety checkpoints for preventing pushes to main. The content is appropriately concise while being comprehensive enough to guide PR creation end-to-end.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, providing only necessary information without explaining concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides fully executable bash commands throughout, with specific examples for git operations, gh CLI usage, and the temp file workaround for multi-line markdown. Commands are copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear 8-step sequence with explicit validation checkpoints (branch verification before push, preflight checks before PR creation). Includes critical safety rails with feedback loops for error prevention. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but the skill is self-contained without references to external files. For a skill of this complexity, some content (like template location patterns or conventional commits details) could be split out, though the current structure is functional. | 2 / 3 |
Total | 11 / 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.
Table of Contents
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.