Get the FREE Ultimate OpenClaw Setup Guide →

tldr-deep

npx machina-cli add skill parcadei/Continuous-Claude-v3/tldr-deep --openclaw
Files (1)
SKILL.md
2.6 KB

TLDR Deep Analysis

Full 5-layer analysis of a specific function. Use when debugging or deeply understanding code.

Trigger

  • /tldr-deep <function_name>
  • "analyze function X in detail"
  • "I need to deeply understand how Y works"
  • Debugging complex functions

Layers

LayerPurposeCommand
L1: ASTStructuretldr extract <file>
L2: Call GraphNavigationtldr context <func> --depth 2
L3: CFGComplexitytldr cfg <file> <func>
L4: DFGData flowtldr dfg <file> <func>
L5: SliceDependenciestldr slice <file> <func> <line>

Execution

Given a function name, run all layers:

# First find the file
tldr search "def <function_name>" .

# Then run each layer
tldr extract <found_file>              # L1: Full file structure
tldr context <function_name> --project . --depth 2  # L2: Call graph
tldr cfg <found_file> <function_name>  # L3: Control flow
tldr dfg <found_file> <function_name>  # L4: Data flow
tldr slice <found_file> <function_name> <target_line>  # L5: Slice

Output Format

## Deep Analysis: {function_name}

### L1: Structure (AST)
File: {file_path}
Signature: {signature}
Docstring: {docstring}

### L2: Call Graph
Calls: {list of functions this calls}
Called by: {list of functions that call this}

### L3: Control Flow (CFG)
Blocks: {N}
Cyclomatic Complexity: {M}
[Hot if M > 10]
Branches:
  - if: line X
  - for: line Y
  - ...

### L4: Data Flow (DFG)
Variables defined:
  - {var1} @ line X
  - {var2} @ line Y
Variables used:
  - {var1} @ lines [A, B, C]
  - {var2} @ lines [D, E]

### L5: Program Slice (affecting line {target})
Lines in slice: {N}
Key dependencies:
  - line X → line Y (data)
  - line A → line B (control)

---
Total: ~{tokens} tokens (95% savings vs raw file)

When to Use

  1. Debugging - Need to understand all paths through a function
  2. Refactoring - Need to know what depends on what
  3. Code review - Analyzing complex functions
  4. Performance - Finding hot spots (high cyclomatic complexity)

Programmatic API

from tldr.api import (
    extract_file,
    get_relevant_context,
    get_cfg_context,
    get_dfg_context,
    get_slice
)

# All layers for one function
file_info = extract_file("src/processor.py")
context = get_relevant_context("src/", "process_data", depth=2)
cfg = get_cfg_context("src/processor.py", "process_data")
dfg = get_dfg_context("src/processor.py", "process_data")
slice_lines = get_slice("src/processor.py", "process_data", target_line=42)

Source

git clone https://github.com/parcadei/Continuous-Claude-v3/blob/main/.claude/skills/tldr-deep/SKILL.mdView on GitHub

Overview

tldr-deep delivers a comprehensive, five-layer examination of a single function to aid debugging and deep understanding. It analyzes the function’s AST, call graph, control flow, data flow, and dependencies to reveal structure and behavior.

How This Skill Works

You provide a function name; the tool locates the file and executes five layers in sequence: AST (structure), Call Graph (navigation), CFG (control flow), DFG (data flow), and Slice (dependencies). Each layer surfaces specific insights to help pinpoint issues and understand how the function operates within the codebase.

When to Use It

  • Debugging a hard-to-trace bug in a specific function
  • Understanding a function's data flow to support refactoring
  • Code review of a complex function in a critical path
  • Performance tuning by identifying hotspots and branches
  • Onboarding new teammates by documenting a function's behavior

Quick Start

  1. Step 1: tldr search "def <function_name>" .
  2. Step 2: Run the five layers: tldr extract <found_file>, tldr context <function_name> --project . --depth 2, tldr cfg <found_file> <function_name>, tldr dfg <found_file> <function_name>, tldr slice <found_file> <function_name> <target_line>
  3. Step 3: Review the layered outputs to identify issues and dependencies

Best Practices

  • Start with L1 AST to locate the function signature and docstring
  • Proceed to L2 Context to map callers and callee relationships
  • Examine L3 CFG to identify branching and hot paths
  • Review L4 DFG to understand variable definitions and usage
  • Use L5 Slice to isolate dependencies at a specific line and verify impact

Example Use Cases

  • Debugging a legacy Python function where bugs traverse multiple modules
  • Understanding an authentication-related function with complex control flow
  • Refactoring a data processing function with many conditional branches
  • Auditing a critical function to ensure no unintended side effects
  • Documenting function behavior for onboarding new engineers

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers