Skip to content
Agentmart
Submit a tool

code-quality

Skill by EtienneP-26

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying code-quality?

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.

Book a call

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/etiennep-26-code-quality

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.

We use your email only for this newsletter. Privacy

About

The publisher has not written a description yet.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions: not checked yet.

What's inside

Skill name
code-quality
Description
None
License
MIT
Instructions
59 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • invalid YAML frontmatter: Nested mappings are not allowed in compact mappings at line 2, column 14:
  • name: missing
  • description: missing

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Code quality

## Before writing
1. **Check what already exists.** Search the project and the installed dependencies for a function or library that already does the job. Reuse it. Ask the user before adding any new dependency, and say what it saves and what it costs (size, maintenance, license).
2. **Check the style.** Read CONTRIBUTING.md and the linter/formatter config. Match existing naming, layout and patterns.
3. **If the intent is unclear**, restate what you understood and ask for confirmation before coding.

## Shape of the code
- **Small blocks that connect.** Split by responsibility into modules, then functions. Prefer several small files or functions that call each other over one large block.
- **One purpose per function.** Test: can you name it without "and"? A function orchestrates by calling others; it does not parse, validate, compute and save all at once. As a guide, over about 20 lines, look for a split. If it cannot be split, the design needs rethinking.
- **Readable beats efficient.** Pick the clear version. Optimize only with a measurement, and say so.
- **Names explain the code.** Use them instead of comments. Comment only the "why" of something non-obvious.

## Docstrings
1. **The project wins.** If the code already has a docstring convention (or CONTRIBUTING.md / a linter config sets one), follow it, unless the user asks for the Noctia style.
2. **Otherwise, or if the user asks, use the Noctia style:** markdown inside the docstring. Line 1 is a `#` title saying what the function does. Then `## Args`, `## Returns`, `## Raises` (only if it raises) and `## Example` (a runnable one, doctest-style when the language supports it). Keep each section short.
3. **Other languages follow the same style**, even if not listed here: the same sections in the same order, written with the language's native doc-comment syntax.

Python:

```python
def blend(
    src: tuple[int, int, int, int],
    dst: tuple[int, int, int, int]
) -> tuple[int, int, int, int]:
    """# Blend two pixels together using alpha compositing

    ## Args:
        src: Upper pixel as (r, g, b, a).
        dst: Lower pixel as (r, g, b, a).

    ## Returns:
        The blended pixel, always fully opaque.

    ## Raises:
        ValueError: If a channel is outside 0-255.

    ## Example:
        >>> blend((255, 0, 0, 128), (0, 0, 255, 255))
        (128, 0, 127, 255)
    """
    a = src[3]
    inv = 255 - a
    rgb = tuple((s * a + d * inv) // 255 for s, d in zip(src[:3], dst[:3]))

    return (*rgb, 255)
```

Rust: same sections with `///` and markdown headings (`## Arguments`, `## Returns`, `## Examples`).

## Tests
- Every new function or behavior change ships with tests in the same change, in the project's test framework and folder layout.
- Cover the normal case, the edge cases and one failure case.
- If the project has no tests, say so, propose a framework (the simplest one for the stack), and ask before installing it.
- Run the tests and the linter before saying the work is done. Report the result, not an assumption.

Before finishing: run the tests and the linter, report the real result, then run `security-check` if the change touches inputs, auth, data or dependencies.

From EtienneP-26/Noctia, MIT.

Signals

Stars
2
Forks
1
Open issues
0
Last commit (this folder)
Oct 19, 2026 (11 days ago)
Last release
Oct 11, 2026 (20 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from EtienneP-26

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 code-quality 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying code-quality?

CallGet help
Cite this page

code-quality skill. Agent Mart. https://agentmart.dev/skills/etiennep-26-code-quality (last updated 2026-10-24)