deslop
Diff-scoped AI-slop cleanup pass: strip comment slop, defensive-check slop, type-laundering, and style drift from the current branch diff before autoreview.
Skill by Elogic360
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/elogic360-deslop
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.
About
Reviews
Write a reviewNo 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/deslop
What's inside
- Skill name
deslop- Description
- Diff-scoped AI-slop cleanup pass: strip comment slop, defensive-check slop, type-laundering, and style drift from the current branch diff before autoreview.
- License
- MIT
- Instructions
- 21 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Deslop Clean only the current branch diff before review. Preserve behavior absolutely. ## Checklist 1. Scope the pass to `git diff` against `origin/main`, or the branch merge base when it differs. Never run a repo-wide cleanup. 2. Inspect every changed hunk for: - comments a human maintainer would not write, including narration, syntax explanation, and prose that merely restates the code; - defensive checks or `try`/`catch` blocks that are abnormal for the surrounding module or protect only imagined states; - casts that launder types, especially `as any`, `as unknown as T`, and widen-then-assert flows. Oxlint already rejects the latter two patterns in governed code; - redundant intermediate variables or one-use helpers that do not add domain meaning, reduce duplication, or simplify control flow; - compatibility shims, aliases, retries, and fallback branches without a named shipped contract and removal plan; - naming, control flow, imports, formatting, and other style that conflicts with the surrounding file. 3. Make no functional edits. If cleanup could change behavior, leave it alone and report it instead. 4. Fix a finding inline only when the cleanup is trivial and behavior-neutral. Otherwise note it for the author. 5. Report the result in 1–3 sentences, including whether anything changed and any non-trivial item left for review. Run `$deslop` before `$autoreview`, never instead of it. Autoreview remains the required correctness and safety review gate.
From Elogic360/imClaw, MIT.
More from Elogic360/imClaw
- 0.565score
control-ui-e2e
Elogic360
Use when designing, testing, fixing, or extending the OpenClaw Control UI GUI, including UI stress-test galleries with feedback inputs, Vitest + Playwright…
SkillAFreshness: AClaude Code +9 - 0.564score
autoreview
Elogic360
Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.
SkillAFreshness: AClaude Code +9 - 0.557score
openclaw-debugging
Elogic360
Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before…
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 8, 2026 (20 days ago)
- Last release
- Oct 12, 2026 (16 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Elogic360/imClaw
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from Elogic360
- 0.565score
control-ui-e2e
Elogic360
Use when designing, testing, fixing, or extending the OpenClaw Control UI GUI, including UI stress-test galleries with feedback inputs, Vitest + Playwright…
SkillAFreshness: AClaude Code +9 - 0.564score
autoreview
Elogic360
Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.
SkillAFreshness: AClaude Code +9 - 0.557score
openclaw-debugging
Elogic360
Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before…
SkillAFreshness: AClaude Code +9 - 0.472score
skill-creator
Elogic360
Create new skills, modify and improve existing skills, and measure skill performance.
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
mcp-builder
Elogic360
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
pdf
Elogic360
Use this skill whenever the user wants to do anything with PDF files.
SkillCFreshness: C★ 1Claude Code +9
Cite this page
deslop skill. Agent Mart. https://agentmart.dev/skills/elogic360-deslop (last updated 2026-10-24)