CtrlK
BlogDocsLog inGet started
Tessl Logo

coderabbit-performance-tuning

Optimize CodeRabbit review speed, relevance, and signal-to-noise ratio. Use when reviews take too long, contain too many irrelevant comments, or when teams are experiencing review fatigue. Trigger with phrases like "coderabbit performance", "optimize coderabbit", "coderabbit slow", "coderabbit noise", "coderabbit too many comments", "coderabbit relevance".

68

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A highly actionable, well-sequenced tuning guide with executable configs and a measurement feedback loop. Its weaknesses are token efficiency (long inline config blocks) and progressive disclosure (an unsignaled, non-existent cross-reference and content that could be split out).

Suggestions

Move the large path_instructions, path_filters, and CI workflow examples into reference files under references/ and link to them one level deep, keeping SKILL.md a concise overview.

Either create the referenced coderabbit-core-workflow-b file or replace the bare "see coderabbit-core-workflow-b" with a real, signaled link (or remove it) so navigation is not a dead end.

Tighten the prose in Steps 1, 2, and 5 (e.g. the PR-size rationale table and the learnings narrative) to reduce tokens without losing the actionable configs.

DimensionReasoningScore

Conciseness

The body is mostly lean and CodeRabbit-specific rather than explaining concepts Claude already knows, but it runs ~250 lines with several large inline config blocks (full path_instructions, path_filters, CI workflow) that could be tightened or split into references, so it is not fully token-efficient.

2 / 3

Actionability

It provides copy-paste-ready, executable artifacts: a GitHub Actions PR-size workflow, multiple concrete .coderabbit.yaml config blocks, and a working gh-based bash metrics script with specific thresholds and recommendations.

3 / 3

Workflow Clarity

Steps 1–6 are clearly sequenced, culminating in a measure-improvement feedback loop (Step 6) and supported by an Error Handling table mapping symptoms to causes and fixes; the operations are config tuning rather than destructive/batch ops, so the absence of a validate-retry loop is not disqualifying.

3 / 3

Progressive Disclosure

Sections are well organized, but content that could live in separate references (large config examples) is inline, and the only cross-reference ("see coderabbit-core-workflow-b") is not a clearly signaled one-level link and has no corresponding bundle file in references/scripts/assets.

2 / 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.

A strong, well-triggered description with explicit what/when guidance and natural, distinctive trigger phrases. Its only weakness is specificity: it states tuning outcomes rather than the concrete levers the skill actually manipulates.

Suggestions

Replace the abstract "Optimize ... speed, relevance, and signal-to-noise ratio" with concrete actions, e.g. "Tune review profile, path instructions, path filters, and learnings to control CodeRabbit review speed and comment relevance."

DimensionReasoningScore

Specificity

It names the CodeRabbit domain and several tuning targets ("review speed, relevance, and signal-to-noise ratio") but relies on a single abstract verb ("Optimize") over outcomes rather than listing concrete actions like tuning profiles or adding path instructions, so it falls short of the score-3 anchor.

2 / 3

Completeness

It explicitly answers both what ("Optimize CodeRabbit review speed, relevance, and signal-to-noise ratio") and when ("Use when reviews take too long, contain too many irrelevant comments, or when teams are experiencing review fatigue"), with explicit triggers.

3 / 3

Trigger Term Quality

It provides six natural phrases a user would actually say ("coderabbit performance", "optimize coderabbit", "coderabbit slow", "coderabbit noise", "coderabbit too many comments", "coderabbit relevance"), matching the good coverage anchor.

3 / 3

Distinctiveness Conflict Risk

The triggers are all CodeRabbit-specific ("coderabbit ...") and clearly scoped to review tuning, making it unlikely to fire for an unrelated skill.

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.