code-overview
Produces a human-readable, progressive-disclosure overview of unfamiliar code or a pull request's changes — why it exists (the real problem it solves or goal it serves for the business or a user), and from there what it does, how it flows, and where to start — so you can get up to speed before working on or reviewing it. Use when you want to understand, get oriented in, make sense of, explain, or get up to speed on a chunk of code, a file, a directory, a symbol, or a PR's changes. Writes the overview to a scratch file and changes no code. Does not review code quality or raise findings — use co
npx skills add testdouble/han --skill code-overview --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Produces a human-readable overview of unfamiliar code or a PR's changes, explaining why the code exists (the real problem or business/user goal), what it does, how it flows, and where to start. It writes the overview to a scratch file and changes no code. It does not review code quality or raise findings.
How it works
The skill operates in stages including:
- Determine target and mode (PR, code, or symbol) based on explicit input and available tools. It classifies size (default small) and announces the chosen mode and size.
- Gather input for the chosen mode: read target and nearby context for code mode; collect change set, diff, and PR intent for PR mode.
- Start a context ledger to record sources consulted.
- Dispatch exploration with han-core:codebase-explorer agents scaled to the size, to discover surrounding code and context that explain why the code exists and how it flows.
- Apply validation and readability polishing passes without editing the target code, culminating in a scratch overview file that describes the code at a high level (why, what, flow, start points).
When to use it
Use when you want to understand, get oriented in, make sense of, explain, or get up to speed on a chunk of code, a file, a directory, a symbol, or a PR's changes. The overview is written to a scratch file and does not modify code.
What it can touch
The skill reads the target and surrounding context and uses codebase explorers to gather evidence. It does not modify the target code. It relies on tools and agents listed in the project context.
Caveats
Does not produce durable feature or system documentation, does not assess architecture or structural risk, and does not diagnose bugs. The overview is an orientation aid grounded in code intent and visible behavior, not a quality judgment or a PR change advisory.
## Project Context - git installed: !`which git 2>/dev/null || echo "not installed"` - gh installed: !`which gh 2>/dev/null || echo "not installed"` - CLAUDE.md: !`find . -maxdepth 1 -name "CLAUDE.md" -type f` - project-discovery.md: !`find . -maxdepth 3 -name "project-discovery.md" -type f` - personal config directory: !`echo "${CLAUDE_CONFIG_DIR:-$HOME/.claude}"` - project .han/config.md: !`cat .han/config.md 2>/dev/null || echo ""` As your first action, use the Read tool on `.han/config.md` inside the `personal config directory` path above. A read that returns no file is no personal configuration: continue silently. When that file or the `project .han/config.md` probe supplies content, apply it per [config-rule.md](../../references/config-rule.md), which governs precedence between the two files, relative-path resolution, and what to do with a file that reads but cannot be used. ## Operating Principles Read these before doing anything. They constrain every step below. - **"Why" is the organizing question.** The overview exists to answer one question first: _why does this code exist?_ — and the answer is the real problem it solves or the goal it accomplishes for the business or a
- Project Context
- Operating Principles
- Step 1: Resolve the Target and Select the Mode
- Step 2: Classify Size and Announce
- Step 3: Gather the Input
- Step 4: Dispatch Exploration Scaled to Size
- Step 5: Synthesize the Overview
- Step 6: Resolve the Destination and Write the File
- Step 7: Validate Accuracy, then Rewrite for Readability
- Step 8: Present
What does the code-overview skill do?
Produces a human-readable, progressive-disclosure overview of unfamiliar code or a pull request's changes — why it exists (the real problem it solves or goal it serves for the business or a user), and from there what it does, how it flows, and where to start — so you can get up to speed before working on or reviewing it. Use when you want to understand, get oriented in, make sense of, explain, or get up to speed on a chunk of code, a file, a directory, a symbol, or a PR's changes. Writes the overview to a scratch file and changes no code. Does not review code quality or raise findings — use co
How do I install it?
Run `npx skills add testdouble/han --skill code-overview --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From testdouble/han, a repository with 154 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.