CtrlK
BlogDocsLog inGet started
Tessl Logo

github-code-review

Comprehensive GitHub code review with AI-powered swarm coordination

56

3.69x
Quality

39%

Does it follow best practices?

Impact

85%

3.69x

Average score across 3 eval scenarios

SecuritybySnyk

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

SKILL.md
Quality
Evals
Security

Quality

Content

28%

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

The content is a sprawling, marketing-toned monolith: rich in concrete command examples but burdened by heavy redundancy, no progressive file structure, and workflows missing validation for destructive operations. It is actionable in places but far from token-efficient or well-organized.

Suggestions

Cut the body drastically: collapse the five near-identical agent sections and duplicate review-init examples into a concise quick-start plus a reference table, removing marketing language and emoji headers.

Add validation checkpoints to destructive/batch workflows — verify review output and test status before auto-merge or pr-fix --push-changes, with explicit fix-and-retry loops.

Split detailed material (config schemas, webhook handler code, full agent definitions) into separate reference files under references/ and link to them one level deep from a lean overview.

DimensionReasoningScore

Conciseness

The body runs ~1100 lines with redundant overlapping examples, marketing tone ('AI-Powered Code Review', emoji section headers, 'Benefits' checklists), and repeated near-identical review-init command blocks, padding context Claude does not need.

1 / 3

Actionability

It provides many concrete bash/code examples that are largely copy-paste ready, but they rely on an unverified 'ruv-swarm' toolchain and some examples contain bugs (e.g. the webhook handler references an undefined 'body' variable), so guidance is concrete but incomplete/unverified.

2 / 3

Workflow Clarity

Multi-step workflows are sequenced (auto-review, comment generation, auto-merge) but lack explicit validation checkpoints, and destructive/batch operations (pr-fix --commit-fixes --push-changes, auto-merge) proceed without verification, capping workflow clarity at 2.

2 / 3

Progressive Disclosure

It is a monolithic single-file wall of text with no bundle/reference files; everything is inline with only collapsible <details> blocks rather than content split into one-level-deep referenced files.

1 / 3

Total

6

/

12

Passed

Description

50%

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 identifies a clear domain but relies on vague marketing language ('Comprehensive', 'AI-powered swarm coordination') instead of concrete capabilities, and omits any explicit usage trigger. It scores as adequate rather than strong across all dimensions.

Suggestions

Replace 'AI-powered swarm coordination' with concrete actions, e.g. 'Run specialized review agents (security, performance, style) on pull requests, post findings, and enforce quality gates.'

Add an explicit 'Use when...' trigger clause: 'Use when reviewing GitHub pull requests or when the user asks for a code review.'

Drop the buzzwords ('Comprehensive', 'AI-powered') and include natural terms like 'PR review' and 'pull request' that users actually say.

DimensionReasoningScore

Specificity

The description names the domain ('GitHub code review') and approach ('AI-powered swarm coordination') but lists no concrete actions such as spawning agents, posting comments, or enforcing gates, falling short of the multiple-specific-actions anchor.

2 / 3

Completeness

It states what the skill does but provides no 'Use when...' clause or equivalent trigger guidance for when Claude should invoke it, capping completeness at 2 per the rubric.

2 / 3

Trigger Term Quality

'code review' and 'GitHub' are natural user terms, but 'AI-powered swarm coordination' is jargon/buzzword users would not naturally say, and common variations like 'PR review' or 'pull request' are missing.

2 / 3

Distinctiveness Conflict Risk

'GitHub code review' is a recognizable niche but the buzzword-laden framing could overlap with general GitHub/PR-management skills, so it is only somewhat distinct rather than clearly niche.

2 / 3

Total

8

/

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.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.