본문으로 건너뛰기
cccskills
무료GitHub에 공개

elegance

Iteratively study and apply elegant coding patterns. Each iteration - understand the code, research what simple and elegant code looks like, apply learnings, verify with CI. Use as a standalone refactoring pass or when the user asks to make code more elegant, simple, or idiomatic.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md2.4 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Elegance

Iteratively study and apply elegant coding patterns. Each iteration: understand the code, research what simple & elegant code looks like, apply learnings, verify with CI.

Run for 3 iterations (or as specified by the user — can be a number or a duration like 2h).

0. Determine Scope

  • Before starting, use the AskUserQuestion tool to ask: should this operate on the whole codebase or only on changes in the current branch/PR?
  • If scoped to current branch/PR, use git diff main...HEAD (or the appropriate base branch) to identify changed files and limit all subsequent steps to those files only.

For each iteration (1 to N):

1. Understand

  • Read through the relevant source files.
  • Note patterns, repetition, unnecessary complexity, non-idiomatic code.

2. Research

  • Use WebSearch/WebFetch to research what simple, elegant (yet readable!) code looks like for the relevant technology.
  • Look for idiomatic patterns, standard simplifications, and community best practices.
  • Focus on: simplicity, readability, removing unnecessary abstraction, leveraging language features.

3. Apply

  • Refactor based on what you learned.
  • This can include: edits, code reorganization, or even rewrites where simplicity demands it.
  • Prefer fewer lines, clearer intent, and idiomatic style.
  • Don't add abstractions — remove them.

4. Verify

  • Run tests/CI to check edits.
  • If CI fails, fix the issues before proceeding to the next iteration.

5. Log Progress

  • Briefly note what changed in this iteration and why.

After all iterations

  • Do not git commit. Leave all changes in the working directory for the user to review.
  • Present a summary of what changed across all iterations.

Principles

  • Simple over clever: Elegant code is simple code.
  • Readable over terse: Brevity is good, but not at the cost of clarity.
  • Idiomatic over generic: Use the language's strengths. Write TypeScript like TypeScript, not like Java.
  • Each iteration builds on the last: Don't undo previous improvements. Deepen them.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

be

무료

Modern, interactive alternative to `/do` — clarify intent up front, then take a task end-to-end with a serial AI review gauntlet (lens debate (lowy ⇄ hickey) → codex debate → simplify → code-police, each editing the branch in turn) → CI → evidence. ONLY invoke when the user explicitly types `/be` or `$be`; never auto-select from a natural-language request.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

srid/emanote9662026년 7월 26일 업데이트

be-review

무료

Run /be's review gauntlet SERIALLY — /lens-debate (lowy ⇄ hickey), then /codex-debate, then /simplify, then code-police, each editing and committing on the live branch in turn. Use from /be §4, or when the user asks to "run the review gauntlet". Requires Claude Code's Skill tool.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

srid/emanote9662026년 7월 26일 업데이트

ci

무료

Reference for the `odu` runner — how to invoke a full pipeline, a single recipe, or a platform-pinned node, and how to attach to a live run, from a project whose CI odu runs. Trigger when the user asks to "run CI", "run the pipeline", "re-run a check", to run named lanes or recipes (e.g. "run fmt and nix", "just the e2e lane", bare selectors like `fmt`/`nix`/`e2e`), or names a recipe by `<recipe>@<platform>`. This skill — not a repo's local `just ci` / `just <recipe>` — is how an odu-run request is served.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

srid/emanote9662026년 7월 26일 업데이트

Review code for quality, simplicity, and common mistakes before declaring work complete.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

srid/emanote9662026년 7월 26일 업데이트

Run an automated codex⇄Claude debate to consensus — no round cap, no deadlock exit. Two explicit subcommands. `review` (also the bare/back-compat default) — codex (reviewer) critiques the current diff and a Claude subagent (author) fixes/disputes, looping until they agree. `answer` — Claude and codex each answer a freeform prompt in parallel, then cross-check until they agree, and a unified answer is returned. Use when the user types `/codex-debate`, asks to "have codex review this", "run the codex debate", "review this PR with codex", "argue this with codex until you agree", or passes a question to "have Claude and codex debate/answer until they agree".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

srid/emanote9662026년 7월 26일 업데이트

do

무료

Do a task end-to-end — implement, PR, CI loop, ship. ONLY invoke when the user explicitly types `/do` or `$do`; never auto-select from a natural-language request, even one that sounds like an end-to-end task.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

srid/emanote9662026년 7월 26일 업데이트

srid의 스킬 모두 보기

이 스킬의 문제 신고