agentskills.codes
TA

tapps-refactor

by wtthorntonSource

>-

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

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.

Search skills

Search the agent skills registry