Skip to content
Agentmart
Submit a tool

desloppy

Use when cleaning or refactoring existing code to remove accidental complexity, duplication, needless indirection, weak types, or overengineering without…

Skill by isp-insoft-gmbh

IndexedMIT
Write a review

Chalk Labs

Need help deploying desloppy?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/isp-insoft-gmbh-desloppy

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when cleaning or refactoring existing code to remove accidental complexity, duplication, needless indirection, weak types, or overengineering without changing behavior.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/desloppy

What's inside

Skill name
desloppy
Description
Use when cleaning or refactoring existing code to remove accidental complexity, duplication, needless indirection, weak types, or overengineering without changing behavior.
License
MIT
Instructions
49 lines in SKILL.md · view on GitHub

Files (12)

  • SKILL.md
  • complexity.md · references/
  • deep-nesting.md · references/
  • duplication.md · references/
  • legacy-overengineering.md · references/
  • long-functions.md · references/
  • magic-values.md · references/
  • missing-types-docs.md · references/
  • overengineered-error-handling.md · references/
  • poor-error-handling.md · references/
  • poor-patterns.md · references/
  • single-use-functions.md · references/

SKILL.md (first lines)

# Desloppy

Slop works, but costs too much to read, change, or trust.

## Boundary

- Existing code only.
- Preserve observable behavior, public APIs, error meaning, security boundaries, accessibility, and relevant performance behavior.
- No features, unrelated bug fixes, weakened tests, or scope creep.
- Deletion beats addition.

## Scope

- One scope is one place or one cross-cutting seam.
  Never both.
- State scope in one sentence.
- Cannot enumerate callers, tests, and affected boundaries → shrink scope.

## Work

1. Read scope in full, then callers, tests, public API, and project instructions.
2. Read only references triggered by code:
   - `references/deep-nesting.md` → flatten control flow
   - `references/long-functions.md` → separate jobs only when separation helps
   - `references/single-use-functions.md` → remove single-use indirection
   - `references/magic-values.md` → expose hidden meaning or relationships
   - `references/missing-types-docs.md` → sharpen types; remove noisy comments
   - `references/poor-error-handling.md` → preserve useful error information
   - `references/overengineered-error-handling.md` → remove excess machinery
   - `references/legacy-overengineering.md` → verify compatibility claims
   - `references/complexity.md` → disentangle dependencies
   - `references/duplication.md` → unify knowledge that must change together
   - `references/poor-patterns.md` → remove unearned ceremony
3. Run smallest project-defined gates covering scope.
   Keep pre-existing failures visible.
4. Choose highest-impact behavior-preserving cleanup inside scope.
5. Existing tests do not prove preserved behavior → add focused proof before refactoring.
   Never change test expectations merely to make refactor pass.
6. Make smallest surgical change.
   Second scope appears → leave it.
7. Run relevant project-defined gates again.

## Authority

- Project instructions, source, tests, and project-defined gates outrank this skill.
- `references/*.md` provide local, conditional guidance.
- No other skill required.

From isp-insoft-gmbh/isp-insoft-ai-skills, MIT.

More from isp-insoft-gmbh/isp-insoft-ai-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 19, 2026 (12 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from isp-insoft-gmbh

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get desloppy running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying desloppy?

CallGet help
Cite this page

desloppy skill. Agent Mart. https://agentmart.dev/skills/isp-insoft-gmbh-desloppy (last updated 2026-10-24)