CtrlK
BlogDocsLog inGet started
Tessl Logo

coderabbit-hello-world

Create a minimal working CodeRabbit configuration and trigger your first AI review. Use when starting with CodeRabbit, testing your setup, or learning basic .coderabbit.yaml patterns. Trigger with phrases like "coderabbit hello world", "coderabbit example", "coderabbit quick start", "first coderabbit review".

66

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable config and command examples and clean single-level organization. It loses points for repeated config blocks and a missing validation/feedback checkpoint in the PR-creation workflow.

Suggestions

Add an explicit validation step before pushing the PR (e.g., lint the YAML or confirm the CodeRabbit App has access to the repo) with a fix-and-retry loop, since Step 3 performs a destructive/irreversible PR-creating action.

Avoid re-pasting the full reviews/chat YAML in Step 2 and the Step 3 heredoc; reference the base config from Step 1 and show only the diff being added to tighten conciseness.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete YAML/bash blocks and an overview that avoids restating what CodeRabbit is, but several sections (path-specific instructions re-pasting the whole config, a redundant Step 3 cat heredoc duplicating earlier YAML) repeat content that could be trimmed.

2 / 3

Actionability

Provides fully executable YAML configs, a copy-paste bash block that creates the file, commits, pushes, and opens a PR via gh, plus concrete @coderabbitai command examples and cr CLI invocations with flags.

3 / 3

Workflow Clarity

The five-step sequence is clear and ordered, but there is no validation checkpoint between config creation and PR push (e.g., verifying YAML syntax or that the App has repo access before pushing), and the destructive/PR-creating batch block has no validate-then-proceed feedback loop.

2 / 3

Progressive Disclosure

A well-organized self-contained SKILL.md overview with sectioned steps; no external bundle files exist and no nested references are used, which is appropriate for a simple quickstart skill.

3 / 3

Total

10

/

12

Passed

Description

90%

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 answers both 'what' and 'when' with explicit, natural trigger phrases and a distinct CodeRabbit niche. It is held back only by a relatively narrow set of concrete actions rather than a comprehensive action list.

Suggestions

List one or two additional concrete actions (e.g., 'configure path-specific review rules', 'interact with @coderabbitai on a PR') to lift specificity toward the top anchor.

Tighten the description into a single flowing sentence and trim the extra blank lines; the current formatting pads the description without adding clarity.

DimensionReasoningScore

Specificity

Names a concrete action ('Create a minimal working CodeRabbit configuration') and an outcome ('trigger your first AI review'), but the action set is narrow and not a comprehensive list of multiple specific actions.

2 / 3

Completeness

Explicitly states what it does (create config and trigger a review) and when to use it via 'Use when starting with CodeRabbit, testing your setup, or learning basic .coderabbit.yaml patterns' plus concrete trigger phrases.

3 / 3

Trigger Term Quality

Provides natural trigger phrases users would actually say ('coderabbit hello world', 'coderabbit example', 'coderabbit quick start', 'first coderabbit review') with good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (minimal CodeRabbit setup / first review) with CodeRabbit-specific triggers unlikely to conflict with other skills; explicit pointer to companion skill also aids boundary clarity.

3 / 3

Total

11

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.