Skip to main content
skill CX Codex

daily-coding — Claude Code skill: a checklist for code edits

A checklist skill for everyday coding: it makes the agent read a file before editing, keep changes minimal and check for security holes.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Galaxy-Dawn/claude-scholar --skill daily-coding -a claude-code
Open on GitHub

What daily-coding does

The skill kicks in whenever the agent writes or modifies source code — new features, added code, edits to existing files. It triggers on requests like "write a…", "implement…", "add…", "modify…" and on any task that touches the Edit or Write tools.

Inside are three groups of items. Before starting: read the target file with Read and confirm you understand the existing logic. While coding: keep changes minimal, no over-engineering; add type hints in Python and avoid any in TypeScript; check for command injection, XSS and SQL injection. After finishing: make sure the code runs without syntax errors, strip print/console.log debug lines and temp files, then give a short summary of what changed.

The reference section shows common mistakes — a mutable default argument, a bare except — and security checkpoints: validate user input, use pathlib for file paths, never hardcode API keys or passwords. Skip it for pure reading tasks, config-only changes and work already handled by bug-detective, architecture-design or verification-loop.

What it helps with

  • read a file before editing instead of changing it blind
  • keep an edit inside its minimal scope without over-engineering
  • add type hints in Python and drop any in TypeScript
  • check code for command injection, XSS and SQL injection
  • strip debug output and temp files once the work is done

Example prompts for the agent

  • implement an endpoint for avatar uploads
  • modify process — it breaks on an empty list
  • add type hints to parser.py

How to install daily-coding

1Skills CLI (Vercel)

npx skills add Galaxy-Dawn/claude-scholar --skill daily-coding -a claude-code

2Manually: put the files in place

~/.claude/skills/daily-coding/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/daily-coding/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about daily-coding

How do I install daily-coding in Claude?

Run npx skills add Galaxy-Dawn/claude-scholar --skill daily-coding -a claude-code. The skill lands in ~/.claude/skills/daily-coding/SKILL.md.

What does daily-coding do?

It is a code quality checklist: the agent reads a file before editing, limits changes to what is needed, checks typing and security, then runs the code and cleans up debug leftovers.

When does the skill not apply?

Not for reading code without edits, config-only changes, or tasks already covered by bug-detective, architecture-design or verification-loop.

Source text

SKILL.md · MIT
---
name: daily-coding
description: Use for everyday coding tasks that involve writing or modifying source code.
version: 1.0.0
tags: [Coding, Daily, Checklist]
---

# Daily Coding Checklist

A minimal coding quality assurance checklist ensuring every code modification follows best practices.

## When to Use

Use this skill for:
- Implementing new features
- Adding code or modifying existing code
- User requests like "write a...", "implement...", "add...", or "modify..."
- Any coding task that involves Edit or Write tools

## When Not to Use

Do not use this skill for:
- Pure reading or understanding tasks with no modification intent
- Work already covered by specialized skills such as `bug-detective`, `architecture-design`, or `verification-loop`
- Configuration-only changes
- Documentation-only writing

## Core Checklist

### Before Starting

- [ ] **Read before modify** - Must read target file with Read tool before making changes
- [ ] **Understand context** - Confirm understanding of existing code logic and design intent

### During Coding

- [ ] **Minimal changes** - Only change what's necessary, no over-engineering, no unrelated features
- [ ] **Type safety** - Add type hints for Python, avoid `any` in TypeScript
- [ ] **Security check** - Avoid command injection, XSS, SQL injection vulnerabilities

### After Completion

- [ ] **Verify execution** - Ensure code runs correctly with no syntax errors
- [ ] **Clean up** - Remove print/console.log debug statements and temporary files
- [ ] **Brief summary** - Inform user what was changed and the scope of impact

## Quick Reference

### Common Mistakes to Avoid

```python
# ❌ Don't
def process(data=[]):  # Mutable default argument
    pass

# ✅ Should
def process(data: list | None = None):
    data = data or []
```

```python
# ❌ Don't
except:  # Bare except
    pass

# ✅ Should
except ValueError as e:
    logger.error(f"Processing failed: {e}")
    raise
```

### Security Check Points

- User input must be validated/escaped
- Use pathlib for file paths, avoid path traversal
- Never hardcode sensitive info (API keys, passwords)

© Galaxy-Dawn · MIT · Galaxy-Dawn/claude-scholar

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set29

architecture-design Lays out the structure of an ML project built on factories and registries. Useful when adding a new dataset or model that needs a registration decorator. CX Codex +1 379installs git-workflow Enforces Git standards: Conventional Commits, branch naming, no-ff merge flows, and conflict resolution. Useful for teams needing consistent version control habits. CX Codex +1 374installs skill-development Creates and refactors agent skills directly in your local environment. It trims oversized SKILL.md files and fixes broken file references. CX Codex +1 372installs planning-with-files Stores an agent's working memory in disk files. Helpful for multi-step tasks across multiple tool calls where chat context might degrade. CX Codex +1 368installs verification-loop Runs a structured quality check before PR submission, verifying builds, types, linter rules, test coverage, exposed secrets, and diffs. CX Codex +1 367installs agent-identifier This skill helps create and configure Claude Code agents, from frontmatter to system prompts. Use it for autonomous multi-step work. CX Codex +1 344installs nature-polishing A skill that brings academic prose up to Nature-level English: it fixes section logic first, then the wording. Useful when a manuscript heads for submission. CX Codex +1 328installs obsidian-project-kb-core This skill manages a project-scoped Obsidian research vault: it builds the structure, routes notes, and keeps indexes, the registry, and checks up to date. CX Codex +1 323installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor