github-code-review

Review PRs: diffs, inline comments via gh or REST.

Quality

61%

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 ./skills/github/github-code-review/SKILL.md

Quality

Content

82%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 content is highly actionable with executable commands throughout and clear sequenced workflows for both local and PR review, supported by a real reference file. Minor verbosity from duplicated gh/curl variants and lighter validation gating keep it from the top band.

Suggestions

Collapse the repeated gh-vs-curl variants into a single canonical path with a brief fallback note, or move one variant into a reference file, to cut token cost.

Add an explicit validation checkpoint in the PR workflow (e.g. re-run tests and confirm inline comments posted before approving/requesting changes) to strengthen feedback loops.

Move the large atomic multi-comment review JSON payloads into the references file alongside the output template to keep SKILL.md as an overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with copy-paste-ready bash/curl blocks and no padding explaining what git or GitHub is; the main drag is the gh/curl duplication across nearly every operation, which inflates length without teaching Claude anything new.	4 / 5
Actionability	Every step is backed by concrete, executable commands — git diff invocations, curl API calls with auth headers, and a complete multi-comment review JSON payload — covering the common cases copy-paste ready.	5 / 5
Workflow Clarity	Section 5 lays out a clear 9-step end-to-end PR review sequence and Section 4 gives a pre-push recipe, with a cleanup step; however validation checkpoints are light (running tests is 'if applicable' with no verify-before-submitting gate), keeping it just short of a 5.	4 / 5
Progressive Disclosure	The body is well-sectioned into numbered workflows and offloads the output template to references/review-output-template.md (a real, one-level-deep file); some reference-style detail (the full inline-comment curl payloads) could live in the reference, but structure and navigation are good.	4 / 5
	Total	17 / 20 Passed

Description

41%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 concise and names concrete actions but lacks an explicit 'Use when' trigger clause and broader natural terminology, capping completeness and trigger quality. It is recognizable but under-specified for confident invocation.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when reviewing local changes before pushing or reviewing open GitHub PRs (e.g. review PR #N, check before pushing)'.

Expand natural trigger terms and synonyms — include 'pull request', 'code review', 'PR #N', and 'pre-push review' so users' phrasings match.

Mention the formal-review outcomes (approve / request changes / comment) to broaden capability coverage beyond diffs and inline comments.

Dimension	Reasoning	Score
Specificity	The description names the domain (PR reviews) and two concrete actions ('diffs', 'inline comments') but is terse and not comprehensive — no mention of formal reviews/approvals, local pre-push review, or posting summary comments.	3 / 5
Completeness	It gives a clear 'what' (review PRs via diffs and inline comments) but there is no 'Use when...' clause or equivalent trigger guidance for when Claude should invoke the skill; the guideline caps completeness at 3 at most, and the absent 'when' pulls it to 2.	2 / 5
Trigger Term Quality	'Review PRs' is a natural phrase and 'diffs' is relevant, but common variations like 'pull request', 'code review', 'pre-push', or 'PR #N' are missing, leaving keyword coverage partial.	3 / 5
Distinctiveness Conflict Risk	The skill is anchored to GitHub PRs and inline comments, which is reasonably distinct, but the brevity leaves it overlapping with generic git/github skills and does not sharply differentiate the trigger.	3 / 5
	Total	11 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/github/github-code-review/SKILL.md
Commit: fcbd107

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.