tidy
Small, safe code cleanups kept separate from feature work (Tidy First).
Skill by dayjobdoor
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/dayjobdoor-tidy
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/tidy
What's inside
- Skill name
tidy- Description
- Small, safe code cleanups kept separate from feature work (Tidy First). Use for tidy, "tidy this", "clean this up", rename, extract, clarify. Not for multi-hour refactors or redesigns.
- License
- MIT
- Instructions
- 33 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Tidy First Inspired by Kent Beck's _Tidy First?_ **Tidying** is a tiny, low-risk cleanup you can land on its own — rename, extract, clarify. Not a multi-hour refactor or redesign. ## What counts as tidying All of these must hold: 1. Done in minutes 2. Safe to apply alone without debate 3. One kind of cleanup — no feature work or unrelated edits mixed in If you would hesitate to ship it by itself, it is not tidying. **Extract boundary:** one extract moves a small cohesive unit with no logic change. Restructuring most of a large function is normal refactor work, not tidying. ## Rules 1. **Name the tidying** when you describe the change 2. **One tidying at a time** 3. **Stay in scope** — only that cleanup 4. **Tests pass** after the change — run the relevant test command and report the result; if you cannot run tests, say why ## Agent instructions - Keep **tidying separate** from behavior changes - Do not bundle drive-by tidies with feature work unless the user asked - State the tidying name; keep the diff minimal - If a cleanup is not shippable on its own, propose it as normal work — not tidying
From dayjobdoor/hotmilk, MIT.
More from dayjobdoor/hotmilk
- 0.611score
comfortzone
dayjobdoor
苫米地理論 TCZ で AI エージェントをコーチング/セルフコーチングする。Use for comfortzone, TCZ, "coach the agent", "self-coach", "diagnose stall", エージェントをコーチングして, セルフコーチングで進めて, 行き詰まりを診断して.
SkillAFreshness: A★ 4Claude Code +9 - 0.609score
pioneer
dayjobdoor
Roadmap-anchored W-model change flow: pair each build level (requirements, system, detailed design, code) with its test design, run tests bottom-up, fix at…
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
pioneer-review
dayjobdoor
Review a diff against its pioneer W table: every changed line traces to a requirement, every requirement to an observed check.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
skill-eval
dayjobdoor
A/B-measure and harden a skill, prompt, or AGENTS.md section with fresh subagents (baseline vs target, one edit per iteration, hold-out).
SkillAFreshness: A★ 4Claude Code +9 - 0.601score
translate
dayjobdoor
Translate text between English and Japanese, auto-detecting direction.
SkillAFreshness: A★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Oct 21, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/dayjobdoor/hotmilk
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dayjobdoor
- 0.611score
comfortzone
dayjobdoor
苫米地理論 TCZ で AI エージェントをコーチング/セルフコーチングする。Use for comfortzone, TCZ, "coach the agent", "self-coach", "diagnose stall", エージェントをコーチングして, セルフコーチングで進めて, 行き詰まりを診断して.
SkillAFreshness: A★ 4Claude Code +9 - 0.609score
pioneer
dayjobdoor
Roadmap-anchored W-model change flow: pair each build level (requirements, system, detailed design, code) with its test design, run tests bottom-up, fix at…
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
pioneer-review
dayjobdoor
Review a diff against its pioneer W table: every changed line traces to a requirement, every requirement to an observed check.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
skill-eval
dayjobdoor
A/B-measure and harden a skill, prompt, or AGENTS.md section with fresh subagents (baseline vs target, one edit per iteration, hold-out).
SkillAFreshness: A★ 4Claude Code +9 - 0.601score
translate
dayjobdoor
Translate text between English and Japanese, auto-detecting direction.
SkillAFreshness: A★ 4Claude Code +9
Cite this page
tidy skill. Agent Mart. https://agentmart.dev/skills/dayjobdoor-tidy (last updated 2026-10-24)