review-pr

Use when reviewing a pull request - security-focused review following repo agent guidance for breaking changes, malicious patterns, and backward compatibility

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/review-pr/SKILL.md

Quality

Content

70%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 body is highly actionable with strong workflow sequencing and mandatory validation gates, making it excellent for execution. Its main weakness is progressive disclosure: substantial policy content is inlined in one monolithic file rather than split into referenced subfiles.

Suggestions

Move the contributor-credit rules, integrate-and-fix flow, and contributor-messaging policy into separate reference files and link to them from SKILL.md.

Trim redundant re-explanation in the policy sections to improve conciseness.

Provide concrete default values or examples for branch/train placeholders (e.g., <train>, <target>) in the integration commands.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and task-relevant, but policy-heavy sections ('Preserve Contributor Credit', 'One Terminal Contributor Message') and some re-explanation of the workflow add padding that could be tightened.	3 / 5
Actionability	Provides concrete, copy-paste-ready gh/terraform/git commands and output templates covering the common cases, with only minor gaps around branch-name placeholders.	4 / 5
Workflow Clarity	A clear 9-step sequence with a flowchart, an explicit MANDATORY independent-verification gate, CI truth-checking with stop conditions, and feedback loops for error recovery.	5 / 5
Progressive Disclosure	Header structure is reasonable, but the skill is a single ~460-line file with no bundle files and inlines bulk policy/reference content (e.g., MIGRATION.md is mentioned but not split out) that belongs in separate files.	3 / 5
	Total	15 / 20 Passed

Description

75%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 specific, third-person, and provides an explicit 'Use when' trigger alongside a clear statement of what the skill does. It is solid across all dimensions but stops short of fully comprehensive keyword coverage and trigger breadth.

Suggestions

Add natural synonyms like 'PR' and 'audit a diff' to broaden trigger-term coverage.

Expand the 'when' clause to name additional trigger situations (e.g., 'when the user asks to review or audit a PR') for maximum completeness.

Consider naming one or two more concrete actions (e.g., 'release classification') to push specificity to a 5.

Dimension	Reasoning	Score
Specificity	Names the security-review domain and several concrete actions ('breaking changes, malicious patterns, and backward compatibility'), with only minor coverage gaps versus a fully comprehensive list.	4 / 5
Completeness	Explicitly answers both what (security-focused review) and when ('Use when reviewing a pull request'); the when clause is concrete but could list additional trigger situations to reach a 5.	4 / 5
Trigger Term Quality	Includes the natural phrase 'reviewing a pull request' plus relevant terms (security-focused, breaking changes, backward compatibility), though synonyms like 'PR' or 'audit a diff' are absent.	4 / 5
Distinctiveness Conflict Risk	The security-focused PR-review framing with breaking-change and malicious-pattern triggers carves a distinct niche with only minor overlap risk against generic code-review skills.	4 / 5
	Total	16 / 20 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: mysticaltech/terraform-hcloud-kube-hetzner
Path: .claude/skills/review-pr/SKILL.md
Commit: bb1622c

Reviewed: 1 day 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.