code-refactor-executor
Overview
This skill is the "execution hand" for the code-quality-audit skill. It transforms strategic advice into concrete code changes by:
- Contextual Analysis: Synthesizing the "Why" (from
audit.md) and "How" (fromimprovements.md) with the current source code state. - Implementation Planning: Creating a detailed
refactor-plan.mdthat outlines each atomic step. - Safe Execution: Applying changes only after user review and verifying each step with tests or build checks.
Activation Rules
Triggers ONLY when the user asks to:
- "Implement the refactorings"
- "Execute the improvements roadmap"
- "Plan and apply refactors from the audit"
- "Fix the issues listed in improvements.md"
Prerequisites:
audit.mdandimprovements.mdmust already exist in the workspace.- Access to the source code files mentioned in the roadmap.
More from harshitsinghbhandari/domain-expansion
architecture-audit
Comprehensive architecture audit that combines ruthless analysis with solution-focused improvement planning. Reads architecture Markdown files, produces a brutal audit report with file/component scores, and generates a prioritized improvements roadmap.
10code-quality-audit
Comprehensive code quality audit that combines ruthless analysis with a solution-focused refactoring roadmap. Reads source code files, produces a brutal audit report with per-file quality scores, and generates prioritized refactoring improvements.
8pr-review
Comprehensive PR review focusing on code quality, test coverage, security, backward compatibility, and what CI cannot check. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
7itemized-functions
Generate exhaustive integration functions with comprehensive test suites for all 3rd-party APIs and external services. Automatically creates function wrappers, individual test files, integrated test runners, and a detailed report of API behavior, response signatures, latency, and failure modes.
7test-coverage-audit
Comprehensive test suite audit that combines ruthless analysis with a solution-focused roadmap. Reads test suites (unit, integration, e2e) and source code, produces a brutal audit report of test quality and gaps, and generates prioritized testing improvements.
7llm-council
Convene an LLM Council for high-stakes decisions requiring multiple perspectives. Use when the user says "council this", "run the council", "get council input", or asks for multi-perspective analysis on strategic decisions like pricing, positioning, pivots, hiring, or any question where being wrong is expensive. Do NOT use for simple factual questions, writing tasks, or summarization.
6