coderabbit-install-auth
Install and configure CodeRabbit AI code review on GitHub or GitLab repositories. Use when setting up CodeRabbit for the first time, installing the GitHub App, configuring the CLI, or connecting CodeRabbit to your repositories. Trigger with phrases like "install coderabbit", "setup coderabbit", "coderabbit auth", "configure coderabbit", "add coderabbit to repo".
67
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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 an excellent skill description that clearly identifies the specific tool (CodeRabbit), the concrete actions (install, configure, connect), the platforms (GitHub, GitLab), and provides explicit trigger guidance with natural user phrases. It follows best practices by using third person voice and including both 'Use when' and 'Trigger with' clauses.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: install, configure, set up CodeRabbit, install the GitHub App, configure the CLI, and connect CodeRabbit to repositories. | 3 / 3 |
Completeness | Clearly answers both 'what' (install and configure CodeRabbit AI code review on GitHub/GitLab) and 'when' (explicit 'Use when...' clause with specific scenarios, plus a 'Trigger with phrases like...' section). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'install coderabbit', 'setup coderabbit', 'coderabbit auth', 'configure coderabbit', 'add coderabbit to repo'. Also includes platform names (GitHub, GitLab) as natural keywords. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — CodeRabbit is a specific product, and the description narrows scope to installation/configuration only. Very unlikely to conflict with other skills due to the unique product name and specific action domain. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with clear step-by-step instructions and good error handling coverage. Its main weaknesses are moderate verbosity (explaining what CodeRabbit is, seat management details) and missing validation checkpoints after configuration and the test review step. The content would benefit from trimming explanatory context and adding explicit verification steps for the configuration and first review stages.
Suggestions
Remove or drastically shorten the Overview paragraph — Claude doesn't need to know what CodeRabbit is; focus on what to do.
Add an explicit validation checkpoint after placing .coderabbit.yaml (e.g., verify the file is on the default branch and parseable) and after Step 5 (e.g., 'If no review appears within 5 minutes, check the error handling table below').
Move the Seat Management section and GitLab Setup to separate referenced files to improve progressive disclosure and reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The overview paragraph explains what CodeRabbit is and how it works, which is unnecessary context for Claude. The seat management section and some markdown-fenced instructional steps add bulk. However, the configuration example and bash commands are reasonably tight. | 2 / 3 |
Actionability | Provides fully concrete, copy-paste-ready commands for installation verification, YAML configuration, CLI installation, and triggering a first review. The error handling table gives specific solutions for specific problems. The GitHub App installation steps are clear and specific with URLs. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced (install → verify → configure → optional CLI → trigger review), but there's no explicit validation/feedback loop after creating the configuration file or after the test PR. Step 2 verifies installation but there's no checkpoint after Step 3 (config) or guidance on what to do if the first review in Step 5 doesn't appear within the expected timeframe. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections, but it's somewhat monolithic — the error handling table, seat management, and GitLab alternative could be in separate referenced files. The Resources section links to external docs which is good, but there are no bundle files to offload detail into. The reference to 'coderabbit-hello-world' at the end is a good forward pointer. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
8a9cd04
- 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.