melvynx/ai-maxxing-skills

code-debug

Debug hard bugs and performance regressions with a tight red-capable loop, falsifiable hypotheses, a focused fix, regression coverage, and real runtime proof.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/melvynx/ai-maxxing-skills --skill code-debug

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

Build the feedback loop first. Name one fast, deterministic, agent-runnable command that exercises the user's exact symptom, run it, and capture the red result. Tighten and minimise it until every remaining element is load-bearing.

No red-capable loop means no hypotheses. If a loop cannot be built, report what was tried and request the missing access or artifact.

Once red:

  1. Rank 3 to 5 falsifiable hypotheses, each with a prediction.
  2. Test one variable at a time; prefer a debugger, then uniquely tagged targeted logs. Measure performance regressions before changing them.
  3. Compare the viable fixes and choose the smallest one that addresses the evidenced cause. In -a or auto mode, use the recommended reversible option without waiting for confirmation.
  4. Turn the minimal repro into a failing regression test at the real seam when one exists, then implement the fix and watch it pass. Document when the architecture provides no honest seam.
  5. Re-run the original unminimised loop and exercise the real runtime path. Passing tests alone do not prove the bug is fixed.

Before finishing, remove temporary instrumentation and throwaway harnesses, state the confirmed root cause, and pass the result through the verify skill. Finish only when the original symptom is proven gone or report BLOCKED: NOT PROVEN.

タスクに関連する項目

同じリポジトリから

関連する Skills

すべての Skills
melvynx
コミュニティ

create-software

Create and deploy a public web app on Cloudflare with TanStack Start, shadcn/ui, Convex, Better Auth, Lumail and optional Stripe, with an admin area, API and CLI so AI controls it. Use when asked to build or ship a SaaS, course platform, membership or client portal people sign up to or pay for.

1時間の導入数
2
GitHub Stars
49
更新日
11月18日
melvynx
コミュニティ

connect-tool

Connect any tool (Notion, Stripe, ClickFunnels...) to every agent by installing its official CLI, or writing a one-file Python CLI over its API, then a global skill. Use for "connect-tool notion", "connect X", "make a CLI for X", "use my X API key".

1時間の導入数
1
GitHub Stars
40
更新日
11月12日
melvynx
コミュニティ

grill-me

Interview the user in batches of 10 questions with recommended answers to sharpen a plan, an idea or an app before building. Use when the user says grill me, wants a rigorous interview, or when create-software, create-internal-app or create-landing needs a confirmed brief.

1時間の導入数
1
GitHub Stars
40
更新日
11月12日
melvynx
コミュニティ

initialize

Install the base skills every agent should have, globally and in one command - /initialize itself (so it can be rerun), skill-manager, /show-me, /grill-me, /wait-what, /connect-tool, /use-style and /better, all from this kit - plus the settings that stop Claude Code and Codex from asking before each action, the cc / cx shortcuts, the usage band above the prompt in the Claude desktop app and the terminal status bar (context, cost, 5-hour and weekly limits), then asks the user which visual style t

1時間の導入数
1
GitHub Stars
40
更新日
11月12日