Solidifier
SOLID refactoring with restraint — measurably less abstraction bloat
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 17, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 2a12fb1
Refactored the same tangled Python billing service twice: without the skill the result was 178 lines and 14 classes of ABC-and-factory ceremony; following the skill produced a behavior-identical 111-line, 3-class version, with equivalence proven by a shared test harness run against the original. The skill's restraint rules measurably prevented abstraction bloat while keeping the pure logic testable without any I/O mocks. It also correctly left an already-clean helper file untouched, exactly as its docs promise. Install command verified verbatim from a bare HOME with no ~/.claude.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What Solidifier does
Applies SOLID principles and design patterns to backend code with explicit restraint rules: prefer a function over a class, a class over an interface, and no pattern without a named axis of variation. Triggers on refactoring, design review, coupling, testability, and 'hard to change' requests in any backend language, with a .solidifier.json config for rigor level, scope globs, and pattern allow/deny lists.
How to install Solidifier
git clone https://github.com/FernandoJRR/solidifier
mkdir -p ~/.claude/skills
cp -r solidifier/claude-code/plugins/solidifier/skills/solidifier ~/.claude/skills/solidifier
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Solidifier
-
/solidifierSOLID refactoring with restraint — measurably less abstraction bloat
It also activates on plain-language prompts like these:
-
Refactor this billing service so it's easier to test and change -
This class is hard to change, apply SOLID without overdoing it -
Clean up the coupling in this module but don't add interfaces
Frequently asked questions
- Is the Solidifier skill free?
- Yes. The skill itself is free from FernandoJRR/solidifier. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Solidifier work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Tested · Works. Refactored the same tangled Python billing service twice: without the skill the result was 178 lines and 14 classes of ABC-and-factory ceremony; following the skill produced a behavior-identical 111-line, 3-class version, with equivalence proven by a shared test harness run against the original. The skill's restraint rules measurably prevented abstraction bloat while keeping the pure logic testable without any I/O mocks. It also correctly left an already-clean helper file untouched, exactly as its docs promise. Install command verified verbatim from a bare HOME with no ~/.claude.
- What is the Solidifier SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install Solidifier?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Solidifier with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.