Implements new features and functions while adhering to project-specific coding conventions and existing patterns.
Install
mkdir -p .claude/skills/ai-code-arcasilesgroup && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12224" && unzip -o skill.zip -d .claude/skills/ai-code-arcasilesgroup && rm skill.zipInstalls to .claude/skills/ai-code-arcasilesgroup
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Writes production code that satisfies stack-context standards on the first pass: interface-first design, backward-compatibility checks, lightweight self-review. Trigger for 'implement this', 'write the code for', 'add X to Y', 'build this function', 'make this work'. Not for tests; use /ai-test instead. Not for debugging; use /ai-debug instead. Not for refactoring; use /ai-simplify instead. Not for executing an approved plan end-to-end; use /ai-build (the gateway).Key capabilities
- →Restate the task to confirm understanding
- →Identify target files for modification or creation
- →Search for existing patterns in the codebase
- →Check `decision-store.json` for architectural decisions
- →Define public interfaces before implementation
- →Implement code following loaded context standards
How it works
The skill follows a checklist including task restatement, file identification, pattern searching, interface-first design, and code implementation according to loaded context standards.
Inputs & outputs
When to use ai-code
- →Implementing new features
- →Writing helper functions
- →Adding code to existing modules
About ai-code
Generates new code based on the project's manifest and conventions. Performs lightweight self-review at build-time to ensure standards compliance.
Writes production code that satisfies stack-context standards on the first pass: interface-first design, backward-compatibility checks, lightweight self-review. Trigger for 'implement this', 'write the code for', 'add X to Y', 'build this function', 'make this work'. Not for tests; use /ai-test inst
When not to use it
- →When writing tests; use `/ai-test` instead
- →When debugging; use `/ai-debug` instead
- →When refactoring; use `/ai-simplify` instead
Limitations
- →Not for tests
- →Not for debugging
- →Not for refactoring
How it compares
This skill enforces a structured, interface-first approach to code generation, incorporating project-specific standards and self-review, which differs from a generic code writing process.
Compared to similar skills
ai-code side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ai-code (this skill) | 0 | 2mo | No flags | Advanced |
| turborepo | 61 | 2mo | Review | Intermediate |
| upgrading-expo | 3 | 4mo | Review | Intermediate |
| node | 0 | 1mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by arcasilesgroup
View all by arcasilesgroup →You might also like
turborepo
vercel
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.
upgrading-expo
sickn33
Upgrade Expo SDK versions
node
dannybrown37
Invoke when the user is writing or debugging TypeScript or JavaScript code, working with Node.js tooling, or asking about ESLint/Prettier configuration.
react-component-patterns
HoangNguyen0403
Modern React component architecture and composition patterns.
effect-patterns-project-setup--execution
PaulJPhilp
Effect-TS patterns for Project Setup Execution. Use when working with project setup execution in Effect-TS applications.
monorepo-structure
dadbodgeoff
Set up a Turborepo + pnpm monorepo for sharing code between frontend, backend, and workers. One repo, multiple packages, shared types, parallel builds.