review-pr

Review an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working tree.

Quality

76%

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 ./plugins/review/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.

A thorough, well-sequenced PR review workflow with strong validation checkpoints and actionable templates, undermined by repeated inline-comment guidance and a lack of file-based progressive disclosure.

Suggestions

Dedupe the inline-comment posting guidance: state the /reviews vs /comments endpoint choice once and reference it from the Templates and Notes sections instead of repeating the full instructions.

Move the comment templates and per-agent prompt boilerplate into reference files (e.g. references/templates.md) and link to them, so SKILL.md stays a lean overview.

Replace placeholder agent-prompt fragments like "[pass proper git command that he can use]" with the concrete git commands the agent should run.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational and avoids explaining concepts Claude already knows, but the inline-comment posting guidance and the gh api /reviews vs /comments endpoints are repeated across Phase 3, the Notes block, and the Templates section, so it could be tightened.	3 / 5
Actionability	Concrete commands (git diff --stat, gh api endpoints, MCP tool names) and copy-paste-ready comment templates are provided, but a few agent-prompt blocks use placeholders like "[pass proper git command that he can use]" and "[list of files]" that are not directly executable.	4 / 5
Workflow Clarity	A clearly sequenced three-phase workflow with explicit validation checkpoints (eligibility checks, confidence/impact thresholds, a re-check before posting) and feedback loops ("If there are no issues that meet this criteria, do not proceed").	5 / 5
Progressive Disclosure	No bundle files exist and all content is inlined in SKILL.md; section headers provide structure, but material that could live in separate references (agent-prompt boilerplate, comment templates) is not split out or signaled as one-level-deep references.	3 / 5
	Total	15 / 20 Passed

Description

82%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.

A concise, well-constructed description that clearly states both capability and trigger conditions with a distinct niche. Minor room to broaden trigger synonyms and enumerate more review actions.

Dimension	Reasoning	Score
Specificity	The description names the domain and two concrete actions ("Review an existing GitHub pull request and post inline review comments on its diff"), but does not enumerate the broader set of review activities, matching the 1-2 concrete actions anchor.	3 / 5
Completeness	It explicitly answers both what ("Review... and post inline review comments on its diff") and when ("Use when the changes are on an opened PR rather than your local working tree") with concrete trigger phrasing, in third person.	5 / 5
Trigger Term Quality	Natural terms users would say are present ("pull request", "diff", "inline review comments", "opened PR") with good coverage, though a few synonyms (e.g. the bare abbreviation "PR", "code review") are not explicitly included.	4 / 5
Distinctiveness Conflict Risk	The "opened PR rather than your local working tree" carve-out gives it a clear niche distinct from local-diff review skills, minimizing conflict risk.	5 / 5
	Total	17 / 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: NeoLabHQ/context-engineering-kit
Path: plugins/review/skills/review-pr/SKILL.md
Commit: 8539779

Reviewed: 5 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.