Produces a token-efficient overview of an unfamiliar codebase using the TLDR stack's tree, structure, call graph and complexity commands.
- What it does
- This skill guides an agent through a four-step reconnaissance pass over a project: listing the file tree, extracting code structure (functions, classes, imports), building a cross-file call graph to find entry points, and measuring cyclomatic complexity of key functions. It then assembles the results into a fixed overview report with sections for structure, key components, architecture and complexity hot spots, plus a token-cost comparison. It also documents a programmatic Python API for the same steps.
- When to use it
- Use it when starting work on an unfamiliar project, when asked for an overview of a project or what is in a codebase, or via the /overview or /tldr-overview triggers. It is not intended for projects you already know, single-file work, or test files.
- Requirements
- Requires the TLDR command-line tool (tldr tree, structure, calls, cfg) and, for the programmatic path, the tldr Python package with tldr.api functions such as get_file_tree, get_code_structure, build_project_call_graph and get_cfg_context. No scripts ship with the skill; it is instructions only.
TLDR Project Overview
Get a token-efficient overview of any project using the TLDR stack.
Trigger
/overview or /tldr-overview- "give me an overview of this project"
- "what's in this codebase"
- Starting work on an unfamiliar project
Execution
1. File Tree (Navigation Map)
2. Code Structure (What Exists)
Returns: functions, classes, imports per file
3. Call Graph Entry Points (Architecture)
Returns: cross-file relationships, main entry points
4. Key Function Complexity (Hot Spots)
For each entry point found:
Output Format
When NOT to Use
- Already familiar with the project
- Working on a specific file (use targeted tldr commands instead)
- Test files (need full context)
Programmatic Usage
