From 2c53cc02a250c58946a4c006511480d1cc2ec959 Mon Sep 17 00:00:00 2001 From: Amolith Date: Mon, 6 Apr 2026 12:35:14 -0600 Subject: [PATCH] chore: rename reviewing-code to getting-a-code-review --- README.md | 22 +++++++++---------- .../SKILL.md | 20 +++++++++++------ 2 files changed, 24 insertions(+), 18 deletions(-) rename skills/{reviewing-code => getting-a-code-review}/SKILL.md (56%) diff --git a/README.md b/README.md index 1b8c66a73ac12d1a0a2a6fe0f88b3ec8bb1328ef..f895794ecb5ee316e8ee8160e466eaaac148cd77 100644 --- a/README.md +++ b/README.md @@ -47,6 +47,9 @@ token count, plus overall metadata usage. I've used and tested them most with - [formatting-commits](skills/formatting-commits/SKILL.md): Detects a project's commit style from recent history and formats messages accordingly. Supports Conventional Commits and kernel-style imperative commits. +- [getting-a-code-review](skills/getting-a-code-review/SKILL.md): Gets an + external code review of changes, commits, PRs, or patches via CLI tools like + Amp, CodeRabbit, or Kodus. - [frontend-accessibility](skills/frontend-accessibility/SKILL.md): Strives to generate accessible HTML, React, and frontend code following WCAG 2.2 AA. Prioritizes semantic HTML over ARIA, keyboard navigation, and screen reader @@ -91,9 +94,6 @@ token count, plus overall metadata usage. I've used and tested them most with filling the main context window. - [resuming-work-through-lunatask](skills/resuming-work-through-lunatask/SKILL.md): Resumes deferred work from [Lunatask] handoff notes via [lune]. -- [reviewing-code](skills/reviewing-code/SKILL.md): Reviews changes, commits, - PRs, and patches using Kodus, CodeRabbit, or Amp, preferring whichever is - available in that order. - [scripting-with-go](skills/scripting-with-go/SKILL.md): Creates executable Go scripts using a shell trick (not a true shebang). For automation and tooling outside of Go projects. @@ -469,14 +469,14 @@ Token breakdown: ─────────────────────────────────────────────── Total: 782 tokens -=== reviewing-code === +=== getting-a-code-review === Token breakdown: - Name: 7 tokens - Description: 51 tokens - Body: 355 tokens (48 lines) + Name: 8 tokens + Description: 108 tokens + Body: 412 tokens (54 lines) ─────────────────────────────────────────────── - Total: 413 tokens + Total: 528 tokens === scripting-with-go === @@ -566,9 +566,9 @@ SUMMARY ============================================================ Skills: 30 -Metadata: 1837 tokens -Combined bodies: 31562 tokens -Overall: 86901 tokens +Metadata: 1895 tokens +Combined bodies: 32121 tokens +Overall: 87518 tokens Validation errors: 0 Largest skills (by total tokens): diff --git a/skills/reviewing-code/SKILL.md b/skills/getting-a-code-review/SKILL.md similarity index 56% rename from skills/reviewing-code/SKILL.md rename to skills/getting-a-code-review/SKILL.md index 7b6f8dfd58017ad998d67fc3b06f0c09fcb4b27e..6ef097d3b28de3fcb3ae8ad2618f0690ade43887 100644 --- a/skills/reviewing-code/SKILL.md +++ b/skills/getting-a-code-review/SKILL.md @@ -1,19 +1,19 @@ --- -name: reviewing-code -description: Rigorously reviews changes, commits, PRs, and patches. Use when asked to review code, a PR, a diff, changes, or when the user says "review", "code review", or "look over this" or similar. +name: getting-a-code-review +description: Gets an external code review of changes, commits, PRs, or patches via CLI tools. Use when asked to review code, a PR, a diff, changes, or when the user says "review", "code review", or "look over this" or similar. If another `code-review` tool or skill is already available, in addition to this one, prefer the other one. It'll give you and the user a better experience. Only use this if it's the only available option. license: GPL-3.0-or-later metadata: author: Amolith --- -Run a code review using the preferred tool. +Get an external review of your code/changes using the appropriate CLI without setting a timeout. ## Selection -If a native code review tool is already available, use it directly. Otherwise, prefer the following in this order: +Prefer the following in this order. ``` -command -v kodus; command -v coderabbit; command -v amp +command -v amp; command -v coderabbit; command -v kodus ``` If CodeRabbit is rate-limited, use another. If none are usable, tell the user and stop. @@ -35,10 +35,10 @@ amp review # uncommitted changes amp review "HEAD~1" amp review "main...HEAD" amp review -f src/auth.ts -amp review -i "explicit, detailed instructions to focus on something(s) in particular" +amp review "068d2222..1800e595" -i "explicit, detailed instructions to focus on something(s) in particular" -f src/auth.ts ``` -_Never_ impose a timeout. +NEVER set a timeout when running these commands. ## Output @@ -48,6 +48,12 @@ Display issues as a numbered list: 1. category (severity) - [file-basename](file-path#range): verbatim finding from the code review tool ``` +For example: + +``` +1. style (nit) - [auth.ts](src/auth.ts#L3-L5): Imports are unsorted and mix standard library, external, and internal packages in a single block without grouping or deterministic ordering +``` + Then ask: - If other code review tools are available: "Would you like me to fix any of these issues, rerun that, run it differently, or check with [Kodus, CodeRabbit, or Amp] as well?", only listing the available options