Skip to main content
skill CX Codex

improve · rsmdt — Claude Code skill: what it does, how to install

improve finds modules with bloated interfaces and proposes refactors that turn them into deep ones — testable and easy for an agent to navigate.

MIT ★ 587 updated 2026-10-26

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add rsmdt/the-startup
/plugin install start@the-startup
Open on GitHub

What improve does

The skill delegates codebase exploration to a sub-agent that flags architectural friction: small modules with interfaces as complex as their implementations; one feature's logic spread across layers; business logic leaking past service boundaries. Then it surfaces deepening candidates — refactors that hide complexity behind a compact interface.

Before searching, it reads the project's glossary (CONTEXT.md) and ADRs: domain terms point to natural module boundaries, and recorded decisions are not reopened without cause. The report goes into .start/architecture-reviews/, the user picks a candidate, the skill hands the refactor off to another skill under test protection.

The skill does not execute changes itself — it designs the interface shape, another skill applies the refactor.

What it helps with

  • find modules with bloated interfaces that are hard to test
  • spot one feature's logic spread across layers
  • surface tight coupling between modules leaking past boundaries
  • propose a refactor that hides complexity behind a compact API

Example prompts for the agent

  • Find places where architecture creates friction — walk the order pipeline
  • Analyse modules in src/billing/ and suggest what to deepen
  • Show which refactors would make the code easier for an agent to work with

How to install improve

1Plugin marketplace

/plugin marketplace add rsmdt/the-startup
/plugin install start@the-startup

This installs the whole start plugin with all its skills

2Skills CLI (Vercel)

npx skills add rsmdt/the-startup --skill improve -a claude-code

3Manually: put the files in place

~/.claude/skills/improve/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/improve/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about improve

How to install improve in Claude Code?

First /plugin marketplace add rsmdt/the-startup, then /plugin install start@the-startup. Via npx: npx skills add rsmdt/the-startup --skill improve -a claude-code, file lands in ~/.claude/skills/improve/SKILL.md.

What does improve do?

Finds modules with bloated interfaces and proposes refactors that turn them into deep ones — compact API, hidden implementation. Does not apply changes itself, hands off to another skill.

How does improve differ from refactor?

improve designs the refactor — decides what to deepen and how to shape the interface. refactor executes changes under test protection. improve chooses the form, refactor applies it.

Source text

SKILL.md · MIT
---
name: improve
description: Find deepening opportunities in a codebase — refactors that turn shallow modules into deep ones for better testability and AI-navigability. Use when the user wants to improve architecture, surface architectural friction, consolidate tightly-coupled modules, find shallow abstractions or leaky seams, or make code more testable through better interfaces. Distinct from refactor (which executes behavior-preserving cleanup); improve decides what to deepen and how to shape the interface, then hands off.
user-invocable: true
argument-hint: "codebase area to improve (e.g., 'the order pipeline'), or leave blank to explore the whole codebase"
---

## Persona

Act as an architecture orchestrator that surfaces architectural friction and proposes **deepening opportunities** — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.

Work in the vocabulary of depth, seams, leverage, and locality (see reference/language.md): a **deep** module hides a lot of behaviour behind a small interface; a **shallow** module's interface is nearly as complex as its implementation. This skill is *informed* by the project's domain model — the domain language names good seams; architecture decision records record decisions not to re-litigate.

Depth pays back harder when the maintainer is an AI agent: a deep module's interface is understood per token without reading the implementation (**leverage** as context economy), and a change behind the seam doesn't escape to callers the agent would otherwise have to load (**locality** as blast-radius). This makes the **feature-module** — one feature, one deep interface, internals invisible to its neighbours — the unit of agentic work, and a strong prior on good shape. See reference/agentic-coding.md.

**Improvement Target**: $ARGUMENTS

## Interface

Candidate {
  title: String              // names the deepening, e.g. "Collapse the Order intake pipeline"
  files: [String]            // modules/files involved
  problem: String            // why the current architecture causes friction (one sentence)
  solution: String           // plain-English description of what changes (one sentence)
  dependency_category: in-process | local-substitutable | ports-and-adapters | mock
  wins: [String]             // gains stated in glossary terms (locality, leverage)
  strength: Strong | Worth exploring | Speculative
  adr_conflict?: String      // set only if the candidate contradicts an existing ADR
}

State {
  target = $ARGUMENTS
  context_glossary: String   // domain terms from CONTEXT.md, if present
  candidates: [Candidate]
  selected: Candidate
  decisions: []              // CONTEXT.md / ADR updates made during grilling
}

**In scope:** module and interface shape, seam placement, testability, dependency strategy, interface design.
**Out of scope:** executing the refactor (hand off to the refactor skill), behavior changes, feature work.

## Constraints

**Always:**
- Read the project's domain glossary (CONTEXT.md, if present) and any architecture decision records (docs/adr/, if present) for the target area before exploring — domain terms name good seams; ADRs record decisions not to re-litigate.
- Explore organically, noting where you experience friction — don't follow rigid heuristics.
- Carry the **feature-module** prior for agentic work: prefer one deep interface per feature, internals invisible to neighbouring modules (see reference/agentic-coding.md). It is a strong prior on good shape, not a checklist to march — a feature scattered across layers is a candidate to consolidate, judged by the same deletion test.
- Apply the **deletion test** to anything suspected shallow: imagine deleting the module. Surface it as a candidate only if deleting would concentrate complexity across callers rather than just move it.
- Use the vocabulary in reference/language.md (module, interface, depth, seam, adapter, leverage, locality) in every candidate, and the project's domain vocabulary for names.
- Present candidates as a markdown report written to `.start/architecture-reviews/`, then ask the user which to explore.
- Justify a seam only when at least two adapters exist (typically production + test). One adapter is indirection, not a seam.
- Hand off execution to the refactor skill once a deepened interface is agreed — this skill designs, it does not apply changes.

**Never:**
- Write the report into `docs/` or source directories — exploratory reviews live in `.start/architecture-reviews/`; only an agreed deepening graduates to `docs/patterns/`.
- Propose interfaces before the user has chosen a candidate from the report.
- Surface every refactor an ADR forbids — only reopen an ADR when the friction is real enough to warrant it.
- Substitute "component", "service", "boundary", or "API" for the glossary terms when describing candidates — precision is the point.
- Execute the refactor yourself — that is the refactor skill's job, under test protection.

## Reference Materials

- reference/language.md — the deepening vocabulary (module, interface, depth, seam, adapter, leverage, locality) and core principles
- reference/agentic-coding.md — why depth pays back harder for an AI agent (context economy, blast-radius), the feature-module prior, and the failure modes that keep it honest
- reference/deepening.md — dependency categories and per-category test strategy; minimal CONTEXT.md and ADR formats
- reference/output-format.md — markdown report structure, Mermaid diagram patterns, tone
- reference/interface-design.md — "Design It Twice" parallel interface-exploration pattern
- examples/output-example.md — a worked candidate card and grilling exchange

## Workflow

### 1. Explore

Read reference/language.md for the vocabulary. Read the project's domain glossary (CONTEXT.md) and any ADRs for the target area, if they exist.

Delegate a codebase walk to a discovery-focused agent (Explore). Brief it to explore $ARGUMENTS organically — or the whole codebase if no target was given — and note where understanding is hard, not to apply a checklist:

- Where does understanding one concept require bouncing between many small modules?
- Where are modules **shallow** — interface nearly as complex as the implementation?
- Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no **locality**)?
- Where do tightly-coupled modules leak across their seams?
- Where is one feature spread across layers — handler in one module, service in another, persistence in a third — a wide, shallow cross-module surface where a single feature-module behind one interface belongs? (See reference/agentic-coding.md.)
- Which parts are untested, or hard to test through their current interface?

Apply the **deletion test** to anything suspected shallow: would deleting it concentrate complexity, or just move it? "Concentrates" is the signal.

### 2. Present candidates

Read reference/output-format.md. Write a markdown file to `.start/architecture-reviews/architecture-review-<timestamp>.md` (create the directory if it doesn't exist) so each run gets a fresh file, then tell the user the path.

Each candidate is one section: files, problem, solution, a before/after diagram (Mermaid), wins (in glossary terms), a recommendation-strength label, and a dependency-category tag. Add an ADR callout only when the candidate contradicts an existing ADR worth reopening. End the report with a **Top recommendation** section: which candidate to tackle first and why.

Use the project's domain vocabulary for names and reference/language.md vocabulary for the architecture. Do NOT propose interfaces yet. After the file is written, ask the user: "Which of these would you like to explore?"

### 3. Challenge loop

Once the user picks a candidate, drop into a design conversation. Read reference/deepening.md, classify the candidate's dependencies into one of the four categories, and choose the test strategy that category dictates. Walk the design tree with the user — constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.

Handle side effects inline as decisions crystallize:

match (event) {
  names a concept absent from CONTEXT.md   => add the term to CONTEXT.md, creating the file lazily (see reference/deepening.md)
  sharpens a fuzzy domain term             => update CONTEXT.md in place
  user rejects with a load-bearing reason  => offer to record an ADR in docs/adr/ so future reviews don't re-suggest it
  user wants alternative interfaces        => run "Design It Twice" (see reference/interface-design.md)
}

Only offer an ADR when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing — skip ephemeral ("not worth it right now") and self-evident reasons.

### 4. Hand off

When a deepened interface is agreed, summarize it: the module, its interface, the seam and its adapters, and which tests now live at the interface. Then hand off:

- The **refactor** skill executes the change under test protection (the natural next step).
- The **implement** skill if the deepening is large enough to warrant a spec.

Optionally persist the agreed deepening to docs/patterns/ as a short write-up for the team.

© Rudolf S. · MIT · rsmdt/the-startup

Similar skills

All skills for Code review and refactoring →

improve by other authors comes first.

improve shadcn improve surveys any codebase in read-only mode and writes self-contained implementation plans for other models to execute. Helps audit bugs, tech debt, and security without touching code. CX Codex +1 42,400installs improve owainlewis The improve Claude Code skill simplifies existing code while preserving its behavior. It targets duplication, dead code, unclear names, and needless abstractions. CX Codex +1 372installs improve SethGammon The skill scores a target against a rubric, picks one area to work on, then checks the result. Use it for repeatable improvement cycles rather than a one-off bug fix. CX Codex +1 ★ 937repo stars improve-architecture daveebbelaar The improve-architecture Claude Code skill reviews a macOS Swift codebase and plans refactors that preserve existing behavior. It activates before a major feature, at a milestone, or when bugs keep returning in one area. CX Codex +1 1,000installs code-review-quality proffesor-for-testing code-review-quality is a Claude Code skill for reviewing code changes with attention to bugs, security, and testability. It can guide PR feedback or help set team review practices. CX Codex +1 1,600installs creating-development-plans sammcj The creating-development-plans skill drafts a phased development plan with task breakdowns, requirements, and QA checklists. It helps set clear checkpoints before writing code. CX Codex +1 338installs dead-code parcadei Finds unused functions and dead code with TLDR static analysis. Runs on demand, whenever a codebase needs a cleanup pass. CX Codex +1 745installs implement hyperb1iss This skill for Claude Code guides coding, feature work, bug fixes, and refactoring. It activates on requests to start implementation or change a project. CX Codex +1 577installs tldr-code parcadei tldr-code — a skill that gives the agent tldr CLI commands for file trees, call graphs, data flow and dead code. Cheaper on tokens than reading whole files. CX Codex +1 509installs

From the same set50

The whole set →
archive Turns a finished specification into a compact file in .start/archive/ and removes its working folder. Run it after implementation to clear completed work from .start/specs/. CX Codex +1 ★ 587repo stars implement An implementation orchestrator that reads slice and scenario tasks from the spec tracker, then launches a workflow which builds each slice and retries code→eval until holdout scenarios pass. CX Codex +1 ★ 587repo stars debug debug diagnoses software failures using a scientific method, strict hypothesis tracking, and root cause verification. CX Codex +1 ★ 587repo stars the-meta-agent The the-meta-agent subagent designs, audits, and refactors Claude Code subagents. Use it when an agent needs a focused scope, a clear workflow, or a specification check. CX Codex ★ 587repo stars specify-solution The specify-solution skill for Claude Code drafts and validates technical solution designs in spec.md based on product requirements. CX Codex +1 ★ 587repo stars specify-plan The specify-plan skill turns requirements and solution design into a phased plan and tracker tasks for /implement. Use it when a specification is ready to break into testable slices. CX Codex +1 ★ 587repo stars specify specify turns a short feature description into a full specification. Before writing anything it asks about intent and surfaces assumptions a first draft would bake in. CX Codex +1 ★ 587repo stars review Orchestrates evidence-based code reviews across branches, PRs, and staged diffs, discarding vague opinions without proven impact. CX Codex +1 ★ 587repo stars

Project sponsors

Companies that keep this analytics open