requesting-code-review

Pre-commit review: security scan, quality gates, auto-fix.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/software-development/requesting-code-review/SKILL.md

Quality

Content

81%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 a well-sequenced, validation-rich pipeline and strong feedback loops, scoring top marks on actionability and workflow clarity. Conciseness dips slightly from redundant security-basics examples, and progressive disclosure is good but monolithic with no external references.

Suggestions

Trim or externalize the 'Common Patterns to Flag' reference and the Step 4 checklist, which re-state security basics Claude already knows and duplicate the Step 2 automated scan.

Consider moving the large reviewer and fix-agent prompt templates into a references/ file signaled from the main body to improve progressive disclosure.

Collapse the per-language lint/test command blocks into a tighter auto-detect table to reduce token weight.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (executable commands, a literal reviewer prompt, no basic-concept explanations), but the 'Common Patterns to Flag' reference and the Step 4 self-review checklist re-teach security basics Claude already knows and overlap with the automated Step 2 scan, so it could be tightened; not a 4 because those padded sections are noticeable.	3 / 5
Actionability	Fully executable copy-paste-ready commands throughout (git diff, grep security scans, per-language test/lint commands, git commit) and a concrete delegate_task reviewer prompt with an explicit JSON return schema covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced 8-step pipeline with explicit validation (Step 6 result evaluation), a bounded feedback loop (Step 7 'Maximum 2 fix-and-reverify cycles', re-run Steps 1-6), fail-closed rules, and a checklist — matching the anchor for clear sequence with explicit validation and error-recovery loops.	5 / 5
Progressive Disclosure	Well-organized into clear section headers (Steps 1-8, Reference, Integration, Pitfalls) with no nested references and easy navigation, but it is a single ~270-line monolithic file with no bundle files, so content like the common-patterns reference is inlined rather than split out; not a 5 because no one-level-deep references exist and some content could be externalized.	4 / 5
	Total	17 / 20 Passed

Description

58%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 with a clear domain, but it lacks an explicit 'Use when' trigger clause and omits the natural trigger words users would actually say, capping completeness and trigger-term quality. Distinctiveness is good though undifferentiated from github-code-review.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user says commit, push, ship, verify, or asks to review before merge.'

Include the independent-reviewer and baseline-testing actions to raise specificity toward comprehensive coverage.

Disambiguate from github-code-review with a phrase like 'verifies YOUR staged changes before commit (vs. reviewing others' PRs).'

Dimension	Reasoning	Score
Specificity	Names the domain ('Pre-commit review') and three concrete actions ('security scan, quality gates, auto-fix'), matching the anchor listing several specific actions with minor coverage gaps; not a 5 because comprehensive actions like the independent reviewer subagent and baseline testing are omitted.	4 / 5
Completeness	The 'what' is clear (security scan, quality gates, auto-fix) but the 'when' is only weakly implied by 'Pre-commit' with no explicit 'Use when...' clause, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords exist ('pre-commit', 'review', 'security scan') but the natural phrases users actually say ('commit', 'push', 'ship', 'verify' — all listed in the body) are absent from the description, so common variations are missing rather than well covered.	3 / 5
Distinctiveness Conflict Risk	The 'pre-commit' + 'auto-fix' niche is mostly distinct with minimal conflict risk; not a 5 because the description does not disambiguate from the closely related github-code-review skill, leaving minor overlap risk.	4 / 5
	Total	14 / 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/software-development/requesting-code-review/SKILL.md
Commit: 48f69e5

Reviewed: 4 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.