agentskills.codes
TA

tapps-refactor

by wtthorntonCodingSource

A workflow for performing safe refactoring by analyzing call graphs and dependency impact.

RefactoringCode ReviewArchitecturePython

Install

mkdir -p .claude/skills/tapps-refactor && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14593" && unzip -o skill.zip -d .claude/skills/tapps-refactor && rm skill.zip

Installs to .claude/skills/tapps-refactor

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Function-level refactor workflow using call graph tools (Epic 114). Use before changing a symbol's signature, deleting a function, or refactoring callers — maps blast radius via tapps_call_graph and diff_impact.
211 charsno explicit “when” trigger
Intermediate

Key capabilities

  • →Start a session for function-level refactoring
  • →Query callers or callees of a symbol
  • →Analyze import and symbol blast radius for a file path or symbol
  • →Perform quick checks after Python file changes
  • →Calculate impact of changes across specified file paths
  • →Generate a checklist for refactoring tasks

How it works

The skill uses call graph tools to map dependencies and calculate the impact of code changes. It provides functions to start a session, query call chains, analyze impact, and perform quick checks.

Inputs & outputs

You give it
A symbol or file-path
You get back
Call graph data, impact analysis results, or quick check results

When to use tapps-refactor

  • →Renaming functions
  • →Deleting unused code
  • →Assessing refactoring blast radius

About this skill

Symbol-level refactor workflow (Epic 114 / ADR-0017):

  1. Session bootstrap. Call mcp__nlt-build__tapps_session_start() — read data.call_graph (ready, stale, degraded). Stale is informational; graph tools auto-rebuild on first use.

  2. Before editing a function. mcp__nlt-build__tapps_call_graph(symbol='...', query='callers') — who calls this symbol? Use query='callees' for downstream dependencies or query='chain' for bounded chains.

  3. Optional module context. mcp__nlt-build__tapps_impact_analysis(file_path='...', symbol='...', granularity='both') for import + symbol blast radius.

  4. Edit loop. After each Python file change, mcp__nlt-build__tapps_quick_check(file_path='...').

  5. After edits. mcp__nlt-build__tapps_diff_impact(file_paths='...') or finish with /tapps-finish-task (include_impact default true refreshes cache).

  6. Close out. /tapps-finish-task with task_type=refactor — checklist recommends tapps_call_graph and tapps_diff_impact.

See docs/CALL_GRAPH.md for gap_rate / degraded semantics.

When not to use it

  • →When refactoring does not involve changes to a symbol's signature
  • →When deleting a function is not required
  • →When refactoring callers is not needed

Limitations

  • →The skill is designed for function-level refactoring
  • →It primarily supports Python file changes
  • →It relies on specific `mcp__nlt-build` tools

How it compares

This skill provides a structured, tool-assisted approach to refactoring by mapping code dependencies and calculating impact, which is more precise and safer than manual code analysis for complex changes.

Compared to similar skills

tapps-refactor side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
tapps-refactor (this skill)01moNo flagsIntermediate
python-design-patterns192moNo flagsIntermediate
modular-code47moNo flagsIntermediate
tldr-code17moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

python-design-patterns

wshobson

Python design patterns including KISS, Separation of Concerns, Single Responsibility, and composition over inheritance. Use when making architecture decisions, refactoring code structure, or evaluating when abstractions are appropriate.

1969

modular-code

parcadei

Modular Code Organization

431

tldr-code

parcadei

Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.

10

deepwiki-rs

sopaco

AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation. Use when Claude needs to analyze source code, understand software architecture, generate technical specs, or create professional documentation from any programming language.

25170

python-patterns

affaan-m

Pythonic 惯用法、PEP 8 标准、类型提示以及构建健壮、高效、可维护的 Python 应用程序的最佳实践。

633

ast-grep-find

parcadei

AST-based code search and refactoring via ast-grep MCP

325

Search skills

Search the agent skills registry