CtrlK
BlogDocsLog inGet started
Tessl Logo

github-code-review

Comprehensive GitHub code review with AI-powered swarm coordination

58

3.69x
Quality

42%

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
SKILL.md
Quality
Evals
Security

Quality

Content

35%

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

The body is feature-rich with concrete gh CLI commands and complete code samples, but it is far too verbose and repetitive, leans on unverified ruv-swarm subcommands, and ships as a monolithic file with no progressive disclosure or bundle references. Verification checkpoints are missing for the destructive/batch workflows.

Suggestions

Cut repetition: collapse the near-identical per-agent review command sections into one parameterized example plus a short agent list, and remove 'Benefits' checklists and marketing prose.

Add explicit validation/verification steps before destructive or batch operations (e.g. validate review output and run tests before `--push-changes` or `gh pr merge --auto`).

Move detailed reference material (agent check lists, config schemas, templates) into separate files under references/ and link to them from a concise overview, so SKILL.md acts as a lean entry point.

DimensionReasoningScore

Conciseness

At ~1138 lines the body is heavily padded with a large table of contents, 'Benefits' checklists, repeated near-identical `npx ruv-swarm` command blocks across agent sections, and feature-marketing JSON lists, much of which restates the product's capabilities rather than adding what Claude does not already know.

1 / 3

Actionability

Provides many concrete, real `gh` commands and complete code blocks, but the central `npx ruv-swarm` subcommands (e.g. review-security, review-learn, pr-topology) appear unverified/aspirational rather than confirmed-executable, leaving key details uncertain.

2 / 3

Workflow Clarity

Multi-step workflows are present and sequenced (e.g. the security review branch on severity, the GitHub Actions pipeline), but destructive/batch operations like auto-fix-with-push and auto-merge lack explicit validation checkpoints, capping this dimension at 2.

2 / 3

Progressive Disclosure

The skill is a single monolithic file with no bundle references (references/, scripts/, assets/ are absent); collapsible <details> blocks and a ToC offer some structure, but large amounts of content that belong in separate reference files remain inline.

2 / 3

Total

7

/

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 is third-person and names a specific domain, but it is padded with marketing buzzwords, lacks an explicit 'Use when...' trigger, and does not enumerate concrete actions or common trigger terms like 'pull request'. It sits at the middle of the scale across all dimensions.

Suggestions

Replace buzzwords ('Comprehensive', 'AI-powered', 'swarm coordination') with concrete actions, e.g. 'Run multi-agent security, performance, and style reviews on pull requests and post inline comments'.

Add an explicit trigger clause, e.g. 'Use when reviewing a GitHub pull request or when the user asks for a code review, PR review, or merge-readiness check.'

Include natural trigger variations users actually say: 'code review', 'PR review', 'pull request', 'review my changes'.

DimensionReasoningScore

Specificity

Names the domain ('GitHub code review') and one action, but leans on fluff and buzzwords ('Comprehensive', 'AI-powered', 'swarm coordination') rather than listing multiple concrete actions; not a level-3 multi-action list, but above the level-1 'Helps with documents' vagueness.

2 / 3

Completeness

Weakly answers 'what' (GitHub code review with swarm coordination) but provides no 'Use when...' clause or explicit trigger guidance; per the judging guidelines a missing trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

Includes natural terms like 'GitHub code review' that a user might say, but omits common variations such as 'pull request', 'PR', 'review a PR'; matches the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

Narrowed to GitHub code review with a swarm-coordination angle, but 'code review' alone could still overlap with generic or other review skills, matching the 'somewhat specific but could still overlap' anchor rather than a clear distinct 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/agentic-flow
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.