Name: github-code-review
Rating: 60.2 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

github-code-review

Comprehensive GitHub code review with AI-powered swarm coordination

3.69x

Quality

45%

Does it follow best practices?

Impact

85%

3.69x

Average score across 3 eval scenarios

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/github-code-review/SKILL.md

The canonical home for this skill is github-code-review in ruvnet/agentic-flow

Quality

Content

46%Weight 40%Scale 1-5

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

The content is an extensive, mostly-executable feature catalog for ruv-swarm, rich in concrete commands but severely verbose and monolithic with no reference files or progressive disclosure. Destructive/batch workflows also lack consistent validation feedback loops.

Suggestions

Split the monolith into reference files (e.g. references/agents.md, references/ci-cd.md, references/configuration.md) and keep SKILL.md as a concise overview with one-level-deep pointers.

Cut decorative emoji headers, benefits checklists, and the repeated `npx ruv-swarm github review-*` variations down to the canonical command plus a few representative examples.

Add explicit validate-then-retry feedback loops for destructive/batch operations (auto-fix commit/push, auto-merge, batch comment posting) before those steps proceed.

Dimension	Reasoning	Score
Conciseness	The body runs ~1140 lines with decorative emoji headers, repeated near-identical `npx ruv-swarm github review-*` command blocks, benefits checklists, and feature-catalog prose that a reviewing Claude largely does not need, fitting 'Noticeably verbose; several unnecessary explanations or padded sections'.	2 / 5
Actionability	Most sections give concrete, copy-pasteable bash/JS/YAML examples covering common cases (security review, auto-review workflow, comment posting), but comment templates still contain placeholder text and the webhook sample references an undefined `body`, leaving minor gaps.	4 / 5
Workflow Clarity	Sequenced workflows exist (auto-review Actions job, conditional security handling, auto-merge with status checks), but the destructive/batch operations (auto-fix --commit-fixes --push-changes, batch comment posting) lack systematic validate-then-retry feedback loops, capping clarity at 3.	3 / 5
Progressive Disclosure	No bundle files exist and the entire skill is a single monolithic SKILL.md; large blocks that clearly belong in separate references (config YAML, CI workflows, custom-agent JS, full command catalog) are inlined with no 'see X.md' pointers, matching 'Minimal structure; content that clearly belongs in separate files is inlined'.	2 / 5
	Total	11 / 20 Passed

Description

45%Weight 40%Scale 1-5

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 is a concise but buzzword-heavy one-liner that names the domain without concrete actions or any 'when to use' guidance. It is recognizable but underspecified for triggering.

Suggestions

Replace 'Comprehensive' and 'AI-powered swarm coordination' with concrete actions, e.g. 'Runs multi-agent security, performance, and style reviews on pull requests and posts inline comments'.

Add an explicit trigger clause such as 'Use when reviewing a GitHub pull request, managing PR comments, or enforcing review quality gates'.

Include natural trigger terms users actually say — 'PR', 'pull request', 'code review comments' — to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("GitHub code review") but the only actions are the generic "review" and the buzzword "swarm coordination" — no concrete actions are listed, matching the anchor 'Names the domain but actions are minimal or generic'.	2 / 5
Completeness	It gives a clear-ish 'what' (GitHub code review with swarm coordination) but has no 'Use when...' or equivalent trigger guidance, so completeness is capped at 3 per the missing-trigger-clause rule.	3 / 5
Trigger Term Quality	"GitHub" and "code review" are natural keywords a user would say, but common variations like "PR", "pull request", or "code review comments" are missing, fitting 'Some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	"GitHub code review with AI-powered swarm coordination" is somewhat specific, but the broad "code review" term risks overlap with generic review skills, fitting 'Somewhat specific but could still overlap with similar skills'.	3 / 5
	Total	11 / 20 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 — 13 / 16 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
relative_links	Relative link issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: ruvnet/ruvector
Path: .claude/skills/github-code-review/SKILL.md
Commit: 74d2a60

Reviewed: 3 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.