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

84%

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

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 a high-quality, actionable review playbook with a clear sequenced workflow, explicit verification checkpoints, and concrete commands and output format. The main weakness is redundancy across the verdicts, completeness-gate, and dimensions sections, which inflates length without adding decisions.

Suggestions

Consolidate the recurring template/snapshot rule into one canonical statement in the Fixed verdicts table, and have the Completeness gate and Tests dimension reference it instead of restating it.

Move the long Fixed verdicts and Completeness gate tables into a reference bundle file (e.g. references/verdicts.md) and summarize the categories inline, reducing the inline reference material.

Tighten the Common AI false-positive patterns section -- several entries (tooling-gap claims, 'might break' without a call site) overlap with the Confidence downgrades and Tie-breaks guidance.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly earns its tokens (decision tables, fixed verdicts, commands), but there is noticeable redundancy: the `.tmpl`-without-snapshots rule recurs across the Fixed verdicts table, Completeness gate table, Review dimensions (Tests), and Common false-positive patterns. Not a 2 because the content is substantive domain guidance, not concept padding; not a 4 because the cross-table repetition could be consolidated.	3 / 5
Actionability	Highly executable: concrete commands (`git diff origin/main...HEAD`, `gh pr diff <n>`, `make update-codegen`, `make update-crds`, `make telemetry-schema`, `nginx -t`), a full fixed-verdicts decision table keyed to specific paths, and a copy-paste-ready output-format template. Matches the anchor for fully executable, copy-paste-ready guidance covering common cases.	5 / 5
Workflow Clarity	A 9-step numbered review workflow with explicit verification checkpoints ('Verify before flagging', 'Run the completeness gate before writing anything'), a verify-or-drop feedback loop, and checklists (completeness gate, fixed verdicts). Matches the anchor for clear sequence with explicit validation steps and feedback loops.	5 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), so all content is inline, but the file is well-organized with clear headers and explicitly delegates codebase-specific depth to named sibling domain skills, clearly signaled in the change-type classification table. Not a 5 because the large inline fixed-verdicts and completeness-gate tables are reference material that a bundle file could offload, though they are central to this skill's purpose.	4 / 5
	Total	17 / 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.

The description is strong: it states what the skill does, gives an explicit 'Use when' clause with three concrete trigger contexts, and is clearly scoped to NIC PR review with low conflict risk. Minor room to broaden trigger synonyms within the description itself.

Dimension	Reasoning	Score
Specificity	Names the domain (reviewing NIC PRs) and several concrete actions -- 'Workflow, guardrails, and output format for reviewing NIC pull requests', 'running the pr-review prompt', 'acting as the GitHub Copilot Code Review bot' -- matching the anchor that lists several specific actions with minor coverage gaps. Not a 5 because it does not enumerate the review's own dimension coverage (security/correctness/etc.), though that is reasonably deferred to the body.	4 / 5
Completeness	Clearly answers both 'what' ('Workflow, guardrails, and output format for reviewing NIC pull requests') and 'when' with an explicit 'Use when' clause listing three concrete trigger contexts. Matches the anchor for explicit what-and-when with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of natural phrases a user would say -- 'reviewing a PR', 'pr-review', 'GitHub Copilot Code Review bot', plus 'Copilot Chat, Claude, or other agent'. Not a 5 because it lacks the broader synonym set (e.g. 'review the diff', 'review my branch') that appears only in the body, not the description.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche (NIC PR review) with distinct triggers and explicit delegation to named domain skills, minimizing overlap with generic review skills. Matches the anchor for a clear niche with minimal conflict risk.	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: 2 missing	Warning

	Total	15 / 16 Passed

Repository: nginx/kubernetes-ingress
Path: .github/skills/nic-code-review/SKILL.md
Commit: 95d3987

Reviewed: 3 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.