“coding”

Creative coding: p5.js sketches and Manim math/algorithm animations for visual art, generative graphics, and educational videos.

Suede AI code review and A-F ship grade for a diff, PR, branch, or commit range: findings ranked P0-P3 with file:line evidence and a fix path, an A-F grade…

Default code-quality route for broad code review, PR review, maintainability, correctness, and regression-risk checks.

Drive the Code stage one plan step at a time with persistent progress, enforce the fix-loop limit, and guard agent branches.

Perform a comprehensive DRY (Don't Repeat Yourself) code review on a codebase.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along three axes: Standards (does the code follow this repo's documented coding…

Guides authored Bash script deliverables.

Compile a bounded objective or code-intake change set into a dependency-safe Runx execution plan, with deterministic checks for evidence preservation…

Build and maintain a living trace of a codebase — the domain flow plus the underlying code structure and patterns — as curated Markdown that gives a coding…

Interactively debug source code — set breakpoints, step through execution line by line, inspect live variable state, evaluate expressions against the running…

Run an independent Claude Code review of local code changes, verify its findings, and fix confirmed issues.

Transfer code between files with line-based precision.

Clean up entropy on two tracks.

Executa agentes de código (Codex CLI, Claude Code, Pi) via processo em background para controle programático.

Build, review, or harden AI agents, LLM apps, RAG, tool-calling, coding agents, and agentic workflows with secure-by-default controls.

Generate a 512x512 QR code PNG for a given URL.

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.

MANDATORY CORE SKILL: Enforces the Autonomous Coding & Self-Correction Loop for Antigravity in every session.

Use when implementing, modifying, refactoring, or debugging code and the main goal is disciplined execution with reuse of existing structure, clear…

Performs a comprehensive, multi-step code review of pull requests or local code changes, using iterative refinement (generation, critique, synthesis) to…

Use when making a short promo, explainer, ad or social video (Reels, TikTok, Shorts, 9:16 or 1:1) whose visuals are typography and shapes drawn by code — no…

Write SOLID-compliant code with principle rules loaded as constraints.

Claude Code adapter for the auto-capture skill.

Use this skill when you need a risk-driven code review of a PR/diff with severity-ranked findings and actionable fixes; triggers include 代码审查, 代码评审, code…