review-pr

Review a PR or branch diff using the knowledge graph for full structural context. Outputs a structured review with blast-radius analysis.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%Weight 40%Scale 1-3

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

The body is a tight, highly actionable workflow with concrete tool calls, a clear step sequence, and a well-structured output template. It fully earns top marks across all content dimensions.

Dimension	Reasoning	Score
Conciseness	Lean and efficient — tool calls with specific arguments and a compact output template, with no padding explaining concepts Claude already knows.	3 / 3
Actionability	Provides concrete, executable tool invocations (e.g. 'build_or_update_graph_tool(base="main")', 'query_graph_tool(pattern="callers_of", target=<func>)') plus a copy-paste output structure.	3 / 3
Workflow Clarity	A clear six-step sequence with unambiguous ordering; being a read-only review task, it does not require the validation/feedback loops mandated for destructive or batch operations.	3 / 3
Progressive Disclosure	Self-contained, well-organized into Steps/Tips with a structured template and no nested external references, which is appropriate for a skill of this size.	3 / 3
	Total	12 / 12 Passed

Description

82%Weight 40%Scale 1-3

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 specific and distinctive, clearly conveying the skill's purpose and niche. Its main gap is the absence of an explicit 'Use when...' trigger clause, which caps completeness at 2.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks to review a PR, branch diff, or pull request.' to fully answer the 'when' question.

Spell out 'pull request' alongside 'PR' to broaden natural trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names concrete actions and deliverables — 'Review a PR or branch diff', 'structured review with blast-radius analysis' — going beyond a single vague verb.	3 / 3
Completeness	Clearly states what the skill does but lacks an explicit 'Use when...' trigger clause, capping completeness per the judging guidelines.	2 / 3
Trigger Term Quality	Uses natural user terms ('PR', 'branch diff') that a user would actually say when requesting this skill.	3 / 3
Distinctiveness Conflict Risk	The knowledge-graph / blast-radius framing carves a clear niche unlikely to overlap with other review skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: tirth8205/code-review-graph
Path: skills/review-pr/SKILL.md
Commit: 805c4c6

Reviewed: 9 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.