nic-code-review

Workflow, guardrails, and output format for reviewing NIC pull requests. Use when reviewing a PR locally (Copilot Chat, Claude, or other agent), when running the pr-review prompt, or when acting as the GitHub Copilot Code Review bot. Delegates codebase-specific detail to the domain skills (nic-structure, nic-add-feature, nic-add-policy, nic-docker-images, nic-ci-pipelines, nic-testing) rather than duplicating them.

Quality

90%

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

92%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 high-quality instruction skill body: concise and directive, rich with executable commands and a copy-paste output template, a clearly sequenced workflow with verification feedback loops, and exemplary progressive disclosure via delegation to named domain skills. The only lever is轻度 deduplication across the three caution-related sections.

Suggestions

Merge overlapping guidance across 'Verify before flagging', 'Confidence downgrades', and 'Common AI false-positive patterns' — several bullets restate the same 'read the config / cite a caller before claiming' idea and could be consolidated to tighten conciseness.

The 'Local invocation examples' section lists only two near-identical examples; either expand with genuinely distinct invocations or fold them into the 'When this skill applies' section to avoid redundancy.

Dimension	Reasoning	Score
Conciseness	Lean, directive prose that assumes Claude's competence and avoids explaining basic concepts; held below 5 because the 'Verify before flagging', 'Confidence downgrades', and 'Common AI false-positive patterns' sections overlap thematically and a few bullets could be merged.	4 / 5
Actionability	Provides concrete executable commands ('git diff origin/main...HEAD', 'gh pr diff <n>', 'make lint', 'make test', 'make update-codegen'), specific file paths, and a copy-paste-ready output format template covering the common cases.	5 / 5
Workflow Clarity	A numbered 7-step workflow with explicit verification checkpoints ('Verify claims before commenting', the 'Verify before flagging' table) and feedback loops (downgrade to Question when a claim cannot be verified), matching the top anchor.	5 / 5
Progressive Disclosure	Acts as a well-organized overview that delegates codebase-specific depth to clearly signaled one-level-deep domain skills (nic-structure, nic-add-feature, etc.) rather than inlining it, with clean section headers throughout.	5 / 5
	Total	19 / 20 Passed

Description

87%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 strong, third-person description that states both what the skill does and when to invoke it with concrete trigger phrases, while clearly carving out its niche via delegation to named domain skills. Minor tightening could add a couple of natural synonyms to the description itself.

Dimension	Reasoning	Score
Specificity	Names the domain (NIC PR review) and several concrete invocation contexts ('reviewing a PR locally', 'running the pr-review prompt', 'acting as the GitHub Copilot Code Review bot') plus guardrails and output format, with only minor coverage gaps; not a 5 because the actions are framed as trigger contexts rather than an exhaustive action list.	4 / 5
Completeness	Explicitly answers both what ('Workflow, guardrails, and output format for reviewing NIC pull requests') and when ('Use when reviewing a PR locally... when running the pr-review prompt, or when acting as the GitHub Copilot Code Review bot') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('reviewing a PR locally', 'pr-review prompt', 'GitHub Copilot Code Review bot') with good keyword coverage; not a 5 because synonyms like 'review the diff' or 'review my branch' (which appear only in the body) are absent from the description itself.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (NIC PR review) with distinct triggers and explicitly names the domain skills it delegates to, minimizing overlap/conflict risk with those sibling skills.	5 / 5
	Total	18 / 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
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: nginx/kubernetes-ingress
Path: .github/skills/nic-code-review/SKILL.md
Commit: 0eb3072

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.