Codesplain
Use when working in a coding project owned by a non-coder - when the project root contains CODESPLAIN.md, when the user invokes /codesplain (to bootstrap a project or ask a question), when a consequential technical decision comes up during building, or when explaining a bug or fix to the owner in plain language.
Install
npx skills add opitaru-sys/codesplain --skill codesplaingit clone --depth 1 https://github.com/opitaru-sys/codesplain.git /tmp/codesplain
mkdir -p ~/.claude/skills
cp -r /tmp/codesplain/. ~/.claude/skills/codesplainPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Codesplain
## Overview
Maintain `CODESPLAIN.md`: a living plain-language map plus decision log that lets a non-coder owner understand their own project, check the AI's work, and learn over time. The doc is a witness, not documentation. It only works if it stays short, current, and honest.
## The file (structure contract)
`CODESPLAIN.md` lives in the project root and has exactly three sections:
1. **Map** - 5 to 10 functional areas, each one something the owner would name when describing the product to a friend ("Turn resolution", "Saving games"), never a file or folder name. Each area gets one plain-language paragraph: what it does, why it exists, which files it lives in (as pointers), what it talks to. Hard cap: the whole Map fits in about 2 screens of text. Never go per-file; that produces an unreadable monument. If an area is genuinely huge, its paragraph ends with: "This is the biggest part - ask me to codesplain it if you need the layer below." Content inferred from existing code (not from a live decision) is marked *(inferred)*.
2. **Decision Log** - append-only, newest last. Each entry: date, area tag in bold, then **3 to 5 sentences maximum**: what was decided, why, the main alternative, what could break or bite later. At 6 sentences, cut the weakest one.
3. **Glossary** - every technical term the doc uses, defined once in plain language. Add a term the first time an entry needs it.
## ModesDetails
- Skill name
codesplain- Repository
- opitaru-sys/codesplain
- License
- MIT
- Repo updated
- 7 July 2026
FAQ
What does the Codesplain skill do?
Use when working in a coding project owned by a non-coder - when the project root contains CODESPLAIN.md, when the user invokes /codesplain (to bootstrap a project or ask a question), when a consequential technical decision comes up during building, or when explaining a bug or fix to the owner in plain language.
How do I install the Codesplain skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add opitaru-sys/codesplain --skill codesplain. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Codesplain popular?
It lives in opitaru-sys/codesplain, which has 6 GitHub stars and 0 forks.
Related skills
Coding Quality Loop
6zaingz/coding-quality-loop
Use when a coding agent must turn a software goal, bug, issue, or refactor into a small, verified, independently reviewed code change.
Code Forge
6tercel/code-forge
Complete Codex development workflow for turning requirements, feature docs, or prompts into working code. Use when the user asks to plan implementation work, execute tasks, enforce TDD, review source code, fix bugs, debug failures, verify completion, manage worktrees or branch finishing, dispatch parallel agents, port a project to another language, check progress, or run an end-to-end build flow. Supports complex orchestration across plan -> impl -> review -> fix -> verify, plus build, forge smart dispatch, worktree, finish, parallel, port, tdd, debug, and status workflows. Every workflow here
Contributor Codebase Analyzer
6anivar/contributor-codebase-analyzer
Deep-dive code analysis with periodic saving. Contributor mode reads every commit diff for annual reviews, accuracy rates, and promotion readiness. Codebase mode maps repository structure, cross-repo relationships, and enterprise governance. Works with GitHub (gh) and GitLab (glab). Saves checkpoints incrementally for resume across sessions.
Code Animations
5beriki770-ship-it/code-animations
Make "code-rendered" animated videos where a program draws every frame (Canvas 2D + procedural Web Audio), rendered headless to MP4 in 16:9 / 9:16 / 4:5 from one timeline. Use for animated explainers, technical walkthroughs, diagrams in motion, and procedural sound or music, where the output should be editable code and not generated pixels.
Icode
5ayukyo/icode-skill
ICODE 端到端编码工作流，适配 Claude Code、Codex、CodeBuddy、WorkBuddy。用户调用 /icode、$icode，或说“使用 ICODE”“用 icode 帮我”“让 ICODE”“Use ICODE”完成开发、日志分析、设计/代码审查、证据验证、独立复评、文档/Word/PPT、学习、工单管理等任务时使用；也用于已绑定 ICODE 工单的续接。Use when users explicitly request ICODE for an AI coding workflow, ticket-based development, code review, log analysis, documentation, or evidence verification; also use to resume a bound ICODE ticket. 支持自然语言目标与限制，不要求背命令；能力咨询只解释不执行。保留全部 /icode 子命令，复用既有步骤与安全门禁，不接管未指定 ICODE 的普通请求。
Audit Codebase
6bogenc/audit-codebase
Audit a codebase for security vulnerabilities by first mapping its attack surface (reconnaissance), then spawning specialized parallel sub-agents that hunt for specific vulnerability classes, each armed with the matching reference file bundled in this skill. Use this whenever the user wants a security review, a vulnerability scan, an audit, a pentest-style pass, or asks "is this code safe / exploitable", "check X for vulnerabilities", "review the auth", or points at a repo, service, or directory and asks what could go wrong. Trigger even when the user names only a stack ("audit my Django API")
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.