Chalk Labs
Need help deploying coding-rules?
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/utilitydelta-coding-rules
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
Use cases: design, data, writing
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/coding-rules
What's inside
- Skill name
coding-rules- Description
- Use when writing or reviewing code in any language. Data-oriented design, minimal state, no temporal coupling, library restraint, comment rules. Per-language idioms and bans in references/ for Python, TypeScript/JavaScript, C#/.NET, Rust.
- License
- MIT
- Instructions
- 43 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- dotnet.md · references/
- rust.md · references/
SKILL.md (first lines)
# Coding Rules Cross-language defaults. Per-language idioms and bans live in `references/`, loaded only for the language in use: - Rust - `references/rust.md` - C# / .NET - `references/dotnet.md` A repo's own skill overrides these where they disagree. ## Data-oriented design - Lead with the shapes the data takes and the transformations over it, not the object hierarchy. - Plain data plus functions over rich objects that hide state and behaviour together. - Lay data out for how it is accessed on the hot path. See `performance-discipline`. ## Minimal state, no temporal coupling - Minimize state held in classes. State is where bugs hide. - No methods that only work in a specific order, no init-then-use-then-teardown dance. If order matters, the types enforce it. - Construct objects fully formed. A half-initialised object is a trap. - RAII over code that must remember to clean up at the end. ## Library restraint - Use the smallest, most boring subset of a library that does the job. MobX is the standing example: kept to its boring subset because the clever features hide the data flow. - A feature that saves five lines but makes the data flow non-obvious is a bad trade. - Before adding a dependency for something small, wrap the platform instead. ## Comments - A comment explains why, not what. If it restates the line below, delete it. - A comment earns its place: the reason for an odd choice, an invariant held, a bug guarded against, a durable citation (RFC section, stable file:line mirror, invariant id). - A wrong comment is worse than none; the reader trusts it. When you change a line, read the comment above it. Out of sync means fix or cut. - Anchor comments to what changes slowly: invariants, contracts, intent. Not line behaviour. - Before done, strip build scaffolding: phase numbers, spec references, plan TODOs, links into the session folder. Keep the durable citations. Do not strip those with the scaffolding. ## Banned constructs A construct that makes code hard to reason about, hard to test in the dark, or that hides state and ordering goes on the language's banned list in `references/`. Low-state, data-oriented code is cheap to test without a heavy harness. That is what the `implementation-loop` needs. The style exists to make verification cheap, not for aesthetics.
From utilitydelta/build-method, MIT.
More from utilitydelta/build-method
- 0.563score
explainer-video
utilitydelta
Use when building an animated explainer of a real system with manim (3b1b's manimgl, pinned - not manim CE), or when asked for a video, animation, or motion…
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
writing-tests
utilitydelta
Use when writing tests, changing tests, or implementing code that needs tests.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
persona-driven-design
utilitydelta
Distill who the product is for before any design, architecture, or code.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
implementation-loop
utilitydelta
Use implementation loop to take a goal.md file and implement it in code.
SkillBFreshness: B★ 2Claude Code +9 - 0.551score
writing-style
utilitydelta
Writing style for docs, comments, commit messages, and PR text.
SkillBFreshness: B★ 2Claude Code +9 - 0.507score
performance-discipline
utilitydelta
Treat performance as a first-class invariant, measured empirically, not guessed.
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
hierarchical-context-docs
utilitydelta
How to write and maintain architecture docs that present a system to an agent in progressive detail, instead of dumping the whole codebase.
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
scout
utilitydelta
Use before handing a goal to implementation, or when a goal or UX journey is being authored or feels under-tested.
SkillCFreshness: C★ 2Claude Code +9 - 0.501score
compressed-mode
utilitydelta
Use this way in the user ask for a compressed response.
SkillCFreshness: C★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 21, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/utilitydelta/build-method
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from utilitydelta
- 0.563score
explainer-video
utilitydelta
Use when building an animated explainer of a real system with manim (3b1b's manimgl, pinned - not manim CE), or when asked for a video, animation, or motion…
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
writing-tests
utilitydelta
Use when writing tests, changing tests, or implementing code that needs tests.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
persona-driven-design
utilitydelta
Distill who the product is for before any design, architecture, or code.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
implementation-loop
utilitydelta
Use implementation loop to take a goal.md file and implement it in code.
SkillBFreshness: B★ 2Claude Code +9 - 0.551score
writing-style
utilitydelta
Writing style for docs, comments, commit messages, and PR text.
SkillBFreshness: B★ 2Claude Code +9 - 0.507score
performance-discipline
utilitydelta
Treat performance as a first-class invariant, measured empirically, not guessed.
SkillCFreshness: C★ 2Claude 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 coding-rules 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
coding-rules skill. Agent Mart. https://agentmart.dev/skills/utilitydelta-coding-rules (last updated 2026-10-24)