github-code-review

Comprehensive GitHub code review with AI-powered swarm coordination

3.69x

Quality

14%

Does it follow best practices?

Impact

85%

3.69x

Average score across 3 eval scenarios

Securityby

Critical

Do not install without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/github-code-review/SKILL.md

Quality

Discovery

22%

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 description relies heavily on buzzwords ('comprehensive', 'AI-powered', 'swarm coordination') without specifying concrete actions or when the skill should be used. While 'GitHub code review' provides some domain grounding, the lack of specific capabilities and explicit trigger guidance makes it difficult for Claude to reliably select this skill from a pool of alternatives.

Suggestions

Replace vague language with specific actions, e.g., 'Reviews pull request diffs, comments on code quality issues, suggests fixes, checks for security vulnerabilities, and summarizes PR changes.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to review a pull request, PR, GitHub diff, or wants feedback on code changes.'

Remove or clarify 'swarm coordination' — either explain what it means in concrete terms or drop it if it's an implementation detail rather than a user-facing capability.

Dimension	Reasoning	Score
Specificity	The description uses vague, buzzword-heavy language like 'comprehensive', 'AI-powered', and 'swarm coordination' without listing any concrete actions. It doesn't specify what the skill actually does (e.g., commenting on PRs, suggesting fixes, checking style).	1 / 3
Completeness	The 'what' is vaguely stated as 'GitHub code review' but lacks specifics, and there is no 'when' clause or explicit trigger guidance at all. The missing 'Use when...' clause would cap this at 2 regardless, but the weak 'what' brings it to 1.	1 / 3
Trigger Term Quality	'GitHub' and 'code review' are natural terms users might say, but the description lacks common variations like 'PR', 'pull request', 'review comments', 'diff', or 'merge request'. 'Swarm coordination' is technical jargon unlikely to be used by users.	2 / 3
Distinctiveness Conflict Risk	'GitHub code review' provides some domain specificity that distinguishes it from generic coding skills, but 'comprehensive' is vague enough that it could overlap with other GitHub-related or code review skills.	2 / 3
	Total	6 / 12 Passed

Implementation

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

This skill is an extremely bloated, marketing-style document that catalogs features of a seemingly non-existent tool rather than providing actionable, executable guidance. It violates token efficiency severely with repeated content, decorative emoji, benefit lists, and JSON schemas describing what agents check. The lack of validation steps in workflows involving auto-merging and auto-fixing code is a significant safety concern.

Suggestions

Reduce to under 100 lines by removing all marketing content (benefit lists, emoji headers, license sections), eliminating redundant command examples, and keeping only the core workflow with one concrete end-to-end example.

Add explicit validation checkpoints: before auto-merging, verify CI passes; before posting review comments, validate the output format; before pushing auto-fixes, confirm changes are correct.

Replace the catalog of `npx ruv-swarm` subcommands with actual executable examples using real, verifiable tools (gh CLI commands, standard linters, etc.) or clearly document that ruv-swarm must be installed and link to its actual documentation.

Extract the configuration reference (review-swarm.yml, triggers JSON, quality gates) and custom agent code into separate referenced files, keeping SKILL.md as a concise overview with navigation links.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at 700+ lines with massive redundancy (the 'Multi-Agent Review System' section repeats the Quick Start nearly verbatim), marketing fluff ('Benefits' bullet lists with checkmarks), explanatory JSON blocks listing what checks are performed (Claude doesn't need this), and sections like License/Last Updated that waste tokens. Much content describes capabilities rather than instructing.	1 / 3
Actionability	The commands reference a tool (`npx ruv-swarm`) with numerous subcommands and flags that appear fabricated or undocumented—none are verifiable as real CLI interfaces. The code examples look plausible but are essentially pseudocode for a non-existent tool; the webhook handler is incomplete (missing body parsing), and the custom agent class has stub implementations. Nothing is truly copy-paste executable.	1 / 3
Workflow Clarity	Despite being a multi-step process involving destructive operations (auto-merging PRs, pushing fixes, requesting changes), there are no validation checkpoints or feedback loops. The workflows are linear command sequences with no error handling, no 'verify before proceeding' steps, and the auto-merge example lacks safety checks beyond a simple review count. The overall flow between sections is unclear—it's a catalog of commands rather than a sequenced workflow.	1 / 3
Progressive Disclosure	The document uses collapsible `<details>` sections and a table of contents, which shows structural awareness. However, it's a monolithic 700+ line file with no references to external files for detailed content. The TOC links are all internal anchors, and the massive inline content (config examples, workflow YAML, custom agent code) should be split into separate reference files.	2 / 3
	Total	5 / 12 Passed

Validation

81%

Warnings & errors only

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
skill_md_line_count	SKILL.md is long (1141 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: ruvnet/agentic-flow
Commit: 8db2712

Reviewed: 26 days ago

Table of Contents

Discovery Implementation Validation

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.