agentsclimarketplace

Refactor

Skill broneq/bdk/skills/refactor

BDK — Broneq Dev Kit. Reusable Claude Code workflows: skills, agents, and hooks for TDD, planning, code review, and architecture documentation.

Install
npx -y skills add broneq/bdk --skill refactor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Propose better object-oriented architecture for complex, procedural code

SKILL.md

1.6 KB, as published. Nobody here has run it

Refactor

Relies on BDK foundation (STARTUP_INSTRUCTIONS.md) for project context and MCP tool preference.

For each <!-- INJECT: <name> --> marker below, run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/inject-rules.py <name> and substitute its stdout in place of the marker before acting on it.

Complex refactor needed. Code messy, needs clean class separation.

Workflow:

  1. Architecture survey:

!python3 ${CLAUDE_PLUGIN_ROOT}/scripts/inject.py --chain ${CLAUDE_PLUGIN_ROOT}/fragments/tool-tiers/explore.chain.json

Using the exploration tools above: understand current community structure, identify tightly-coupled communities, detect cross-cutting concerns, and identify dead code with refactor_tool(mode="dead_code") if graph is available. 2. Launch explorer subagent with architecture findings as context (not blind). For follow-up questions on the same exploration, prefer SendMessage(to: "<agentId>", ...) over re-spawning. See STARTUP "Continuing a Spawned Agent". 3. Propose OO architecture with well-separated classes — reference community boundaries, address surprising connections 4. Identify applicable design patterns and explain fit — see rules below 5. Create docs in .bdk/refactor/:

  • Architecture overview
  • Applicable patterns with rationale
  • Implementation plan

Problem description:

$ARGUMENTS

<!-- INJECT: design-patterns -->

Gives 0 of the 12 instructions most refactoring skills give

Counted across 521 of the 525 authors here whose files we hold, read 2026-08-06

  • run tests after each changein 59 of 521, across 56 files
  • write tests before refactoringin 27 of 521, across 24 files
  • preserve external behaviorin 26 of 521, across 22 files
  • remove dead codein 25 of 521, across 24 files
  • make small incremental changesin 20 of 521, across 17 files
  • break the implementation into tiny commitsin 18 of 521, across 5 files
  • ask the user about alternative optionsin 17 of 521, across 4 files
  • create a GitHub issue with the planin 17 of 521, across 4 files
  • explore the repository to verify assertionsin 17 of 521, across 4 files
  • interview the user about the refactorin 16 of 521, across 3 files
  • check the codebase for test coveragein 16 of 521, across 3 files
  • refactor one thing at a timein 16 of 521, across 12 files

Said here and by no other author read

  • Run the injection script for each marker
  • Explore current architecture using the specified tools
  • Detect tightly-coupled communities and dead code
  • Launch the explorer subagent with architecture findings
  • Prefer messaging the existing agent over re-spawning
  • Propose well-separated classes referencing community boundaries

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.