create-pr
Push the current branch and create a pull request against docker/docs. Use after changes are committed and reviewed. "create a PR", "submit the fix", "open a pull request for this".
90
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%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-crafted skill description that concisely covers what the skill does, when to use it, and includes natural trigger phrases. It uses third person voice, names a specific repository target, and provides clear temporal guidance ('after changes are committed and reviewed'). The description is both concise and comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Push the current branch' and 'create a pull request against docker/docs'. The target repository is explicitly named, adding specificity. | 3 / 3 |
Completeness | Clearly answers both what ('Push the current branch and create a pull request against docker/docs') and when ('Use after changes are committed and reviewed'), plus provides explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would actually say: 'create a PR', 'submit the fix', 'open a pull request for this'. These are realistic user utterances covering common variations. | 3 / 3 |
Distinctiveness Conflict Risk | Targets a very specific niche: pushing and creating PRs against the docker/docs repository. The combination of git push + PR creation against a named repo makes it clearly distinguishable from general git or code review skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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, highly actionable skill with excellent workflow clarity and concrete executable commands throughout. The duplicate PR detection step and reviewer verification fallback demonstrate thoughtful error handling. Minor weaknesses include some verbosity in the optional Learnings section and the lack of progressive disclosure to external references, though the latter is less critical for a skill of this size.
Suggestions
Trim the optional Learnings section — the explanation about the 'weekly PR learnings scanner' and the detailed guidance on what to include/exclude adds tokens without much value for Claude.
Consider moving the fallback reviewer assignment commands and the duplicate PR check into a referenced troubleshooting file to keep the main flow leaner.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with concrete commands, but includes some unnecessary explanation (e.g., the optional Learnings section is quite verbose, and the explanation about the weekly PR learnings scanner is context Claude doesn't need). The duplicate PR check section is thorough but slightly wordy. | 2 / 3 |
Actionability | Every step includes fully executable, copy-paste-ready bash commands. The gh CLI commands are specific with proper flags, the FORK_OWNER derivation is a real working sed command, and even edge cases like label application via the Issues API are covered with concrete commands. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (verify → push → create PR → label/review → report) with explicit validation checkpoints: checking for unstaged changes, verifying remote URL, checking for duplicate PRs before creating one, and verifying reviewer assignment with a fallback. The duplicate PR check is an excellent guard against destructive/wasteful operations. | 3 / 3 |
Progressive Disclosure | The content is well-structured with numbered sections and clear headings, but it's a moderately long single file with no references to external files. The optional Learnings section and the fallback reviewer assignment patterns could potentially be split out, though for a standalone skill this is acceptable. | 2 / 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.
- Repository
- docker/docs
- Commit
c0aa985
- 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.