refactor-safely
Refactor code without behavior changes using small mechanical steps and verification.
Skill by s-hiraoku
Chalk Labs
Need help deploying refactor-safely?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/s-hiraoku-refactor-safely-d49039
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. Checked Oct 25, 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/refactor-safely
What's inside
- Skill name
refactor-safely- Description
- Refactor code without behavior changes using small mechanical steps and verification.
- License
- MIT
- Instructions
- 18 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Refactor Safely Use this workflow when improving structure without changing behavior. ## Workflow 1. Identify the current behavior and public interfaces. 2. Avoid broad rewrites unless they are explicitly justified. 3. Make small mechanical changes. 4. Preserve public APIs, data formats, and user-visible behavior. 5. Run tests after meaningful steps. 6. Update docs only if structure, commands, or contributor guidance changes. ## Final Report Clearly state that behavior should be unchanged. Include changed files, verification run, and any areas that need extra review.
From s-hiraoku/claude-harnesses, MIT.
More from s-hiraoku/claude-harnesses
- 0.505score
autopilot
s-hiraoku
Explicitly keep a GitHub pull request moving until it is merge-ready by delegating to PR Guardian.
SkillBFreshness: BClaude Code +9 - 0.465score
adviser
s-hiraoku
Route an independent, review-only Claude process to a deterministically stronger model or effort when native Advisor is unavailable.
SkillCFreshness: CClaude Code +9 - 0.465score
jina-reader
s-hiraoku
Fetch public web pages with Jina AI Reader API and convert them into LLM-friendly Markdown.
SkillCFreshness: CClaude Code +9 - 0.462score
pr-guardian
s-hiraoku
Monitor a pull request after opening it or resume a stalled PR, fix CI failures and reviewer feedback, push updates, reply to and resolve review…
SkillCFreshness: CClaude Code +9 - 0.462score
no-slop
s-hiraoku
MODIFIER skill that removes AI slop from prose without losing source facts or uncertainty.
SkillCFreshness: CClaude Code +9 - 0.460score
meta-packager
s-hiraoku
Analyze recent Claude Code work and package repeated patterns as the smallest useful skill, custom subagent, slash command, hook, or automation.
SkillCFreshness: CClaude Code +9 - 0.458score
goal-manager
s-hiraoku
Manage durable task goals for long-running Claude Code work using the project ledger, including objective writing, success criteria, resumption, and…
SkillCFreshness: CClaude Code +9 - 0.457score
implement-to-merge-ready
s-hiraoku
Run an end-to-end Claude Code delivery workflow from user request to merge-ready pull request, including planning, implementation, tests, self-review…
SkillCFreshness: CClaude Code +9 - 0.457score
fix-ci
s-hiraoku
Diagnose and repair failing CI checks on the current PR by parsing logs, reproducing locally when possible, and pushing focused fixes in batches.
SkillCFreshness: CClaude Code +9 - 0.457score
kaizen-loop
s-hiraoku
Run a continuous product improvement loop: evaluate a product or codebase, present prioritized recommendations for approval, then implement only approved…
SkillCFreshness: CClaude Code +9 - 0.457score
long-running-orchestrator
s-hiraoku
Run multi-hour or multi-session work safely by combining the ledger, checkpoints, cost-ceiling guard, and resumable progress notes so context loss does not…
SkillCFreshness: CClaude Code +9 - 0.457score
deslop
s-hiraoku
Remove AI-generated boilerplate (vague comments, unused try/except, defensive validation, restated docstrings) from changed code without changing behavior.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- May 8, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/s-hiraoku/claude-harnesses
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.270score
refactor-safely
s-hiraoku
Refactor code without behavior changes using small mechanical steps and verification.
SkillCFreshness: CClaude Code +9 - 0.267score
refactor-safely
s-hiraoku
Refactor code without behavior changes using small mechanical steps and verification.
SkillCFreshness: CClaude Code +9 - 0.267score
refactor-safely
s-hiraoku
Refactor code without behavior changes using small mechanical steps and verification.
SkillCFreshness: CClaude Code +9
More from s-hiraoku
- 0.523score
Secondary Terminal
s-hiraoku
Sidebar terminal for VS Code with AI agent awareness (Claude Code, Copilot, Gemini, Codex, Antigravity), split views, session persistence, and full IME support.
PluginBFreshness: B★ 22VS Code +3 - 0.510score
pr-guardian
s-hiraoku
Monitor or resume GitHub pull requests, fix CI failures and actionable CodeRabbit, Codex, bot, or human review feedback, push focused updates, and stop only…
SkillBFreshness: BClaude Code +9 - 0.508score
autopilot
s-hiraoku
Run the PR Guardian workflow when the user explicitly invokes $autopilot to keep a GitHub pull request moving toward merge-ready without merging it.
SkillBFreshness: BClaude Code +9 - 0.505score
autopilot
s-hiraoku
Explicitly keep a GitHub pull request moving until it is merge-ready by delegating to PR Guardian.
SkillBFreshness: BClaude Code +9 - 0.465score
jina-reader
s-hiraoku
Fetch public web pages with Jina AI Reader API and convert them into LLM-friendly Markdown.
SkillCFreshness: CClaude Code +9 - 0.465score
adviser
s-hiraoku
Route an independent, review-only Claude process to a deterministically stronger model or effort when native Advisor is unavailable.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get refactor-safely running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
refactor-safely skill. Agent Mart. https://agentmart.dev/skills/s-hiraoku-refactor-safely-d49039 (last updated 2026-10-24)