원클릭으로
refactor-safe
Safe refactor in bounded scope (1-10 files, no behavior change). Use proactively for safe, bounded refactoring tasks.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Safe refactor in bounded scope (1-10 files, no behavior change). Use proactively for safe, bounded refactoring tasks.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
Create blog posts — from a topic (writes content) or with provided content (scaffolding). Use proactively when creating new blog posts or articles.
Pre-publication audit for blog posts — comprehensive final review of SEO, AEO, accessibility, images, content quality, i18n parity, and project conventions before publishing. Use proactively before publishing any blog post.
Pre-publication audit for blog series — validates series definition, post ordering, cross-post consistency, navigation, and runs individual post audits for all posts in the series. Use proactively before publishing any blog series.
Audit the blog tag taxonomy — frequency analysis, orphan detection, hierarchy validation, and proposals for new subtopic tags. Read-only — proposes, never modifies tags or posts. Use proactively before each release cycle or after a content drop of 5+ posts.
Optional DeepWorkPlan addon that connects an AI-first repo to the developer's Dailybot team — installing (with consent) the Dailybot agent skill (DailybotHQ/agent-skill) and/or the Dailybot CLI (DailybotHQ/cli), wiring the plan lifecycle into best-effort agent updates - kickoff when a plan starts, significant task completions, a blocked report when an unattended run halts, and a milestone on plan completion - with payloads derived from the plan's state layer, and optionally committing the Dailybot skill's deterministic hook enforcement (dailybot hook lifecycle hooks, CLI >= 1.12.0) so the agent harness itself reminds agents about unreported work. Opt-in, never required, never blocks the work, reconciles existing setups instead of clobbering them, and defers all auth to the Dailybot skill's own consent flow. Use when the developer or team already uses Dailybot and wants DWP progress visible to humans.
Optional DeepWorkPlan addon that safely upgrades a repo's dependencies — reasoning about the repo's ACTUAL package manager (npm/pnpm/yarn + ncu, pip/poetry/uv, cargo, go mod, bundler, composer, and more) rather than assuming npm — with a batched, validated, revertible workflow that detects the manager and manifests/lockfiles, classifies upgrades (patch/minor/major), upgrades in safe batches, runs the repo's real validation gate after each batch, reverts a failing batch, and summarizes. Opt-in, never required, reconciles with the repo's existing tooling. Use when the developer wants to bring dependencies up to date without breaking the build.
SOC 직업 분류 기준
| name | refactor-safe |
| description | Safe refactor in bounded scope (1-10 files, no behavior change). Use proactively for safe, bounded refactoring tasks. |
| disable-model-invocation | false |
| allowed-tools | Read, Write, Edit, Glob, Grep, Bash |
| model | sonnet |
| tier | 2 |
| intent | execute |
| max-files | 10 |
| max-loc | 500 |
Refactor code in a bounded scope (1-10 files, up to ~500 LOC) without changing observable behavior. Extract functions, rename for clarity, reorder imports, split modules. Adapted for this repo: Astro, Svelte, TypeScript; follow docs/STANDARDS.md and AGENTS.md.
Tier: 2 - Standard
Reasoning: Moderate reasoning (dependencies, component impact); scope 1-10 files, 100-500 LOC; safe, reversible refactors only.
$TARGET: File(s) or directory to refactor (e.g., src/components/blog/)$GOAL: What to refactor (e.g., "extract helper", "rename for clarity", "split into smaller components")$CONSTRAINTS: What not to change (e.g., "keep component props unchanged")Before running this skill, ensure:
pnpm run build)pnpm run biome:check and pnpm run astro:check after each steppnpm run biome:check
pnpm run astro:check
pnpm run build
## ✅ Refactor Safe Complete
### Target
{What was refactored}
### Changes
- `{file1}`: {what changed}
- `{file2}`: {what changed}
### Behavior
- No intentional behavior change
- Build passes
### Validation
- pnpm run biome:check: ✅
- pnpm run astro:check: ✅
- pnpm run build: ✅
### Commit Message
refactor: {brief description}
Stop and escalate if:
pnpm run biome:check passespnpm run astro:check passespnpm run build passesEscalate to architect if: cross-module design, API changes, or large-scale restructure needed.
Input:
$TARGET: src/components/blog/BlogGrid.svelte
$GOAL: Extract date formatting to lib/
Execution:
src/lib/date.ts with formatDate functionBlogGrid.svelte to import from lib/refactor: extract date formatting to lib/Input:
$TARGET: src/components/home/HeroSection/HeroSection.astro
$GOAL: Split into smaller subcomponents
Execution:
HeroTitle.astro, HeroActions.astro)refactor: split HeroSection into subcomponents