New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Deslop

by jtaroreh in jtaroreh/agystack

Clean AI slop and defensiveness out of code and diffs before commit.

MITAuto-check passedWriting & Content

Install Deslop

skills CLI
$ npx skills add jtaroreh/agystack --skill deslop -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jtaroreh/agystack deslop --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jtaroreh/agystack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/deslop .claude/skills/deslop && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deslop
GitHub stars
112
Token cost
~890 tokens
SKILL.md length
382 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Clean AI slop and defensiveness out of code and diffs before commit.

  • Works in 5 steps: Defensive Over-Engineering → Speculative Flexibility → Narrating and Placeholder Comments → …
  • Tasks that involve Humanizing AI text
  • SKILL.md covers Process, Code Slop Patterns to Detect… and Output / Reply
  • Calls git

What it does

Deslop is an agent skill from jtaroreh/agystack. Clean AI slop and defensiveness out of code and diffs before commit. Strips narrating comments, redundant guards, speculative error handling, unused abstractions, and dead compatibility code.

Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Humanizing AI text. The repository describes itself as: Closed-loop engineering workflow and agentic swarm orchestration plugin for Google Antigravity. The licence is MIT.

When your agent uses it

  • Tasks that involve Humanizing AI text

Example prompts

  • “/deslop”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Defensive Over-Engineering
  2. Speculative Flexibility
  3. Narrating and Placeholder Comments
  4. Artificial AI Code Tells
  5. Lingering Debug and Scratch Artifacts

What it can do on your machine

Read from SKILL.md and the folder at commit d1a0466. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deslop loads about 890 tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 382 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~890

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jtaroreh/agystack at commit d1a0466, republished under its MIT licence (© jtaroreh). 382 words, ~890 tokens.

Download SKILL.mdSave it as .claude/skills/deslop/SKILL.md (or your agent's skills folder).
name
deslop
description
Clean AI slop and defensiveness out of code and diffs before commit. Strips narrating comments, redundant guards, speculative error handling, unused abstractions, and dead compatibility code.

Deslop

Clean AI patterns, excessive defensiveness, and unnecessary bloat out of code and git diffs before committing.

While /unslop cleans human/agent prose and /no-comments strips comments before review, /deslop operates directly on application code and diffs.

Process

  1. Inspect the diff. Run git diff against your base branch or HEAD~1. Focus on newly added or modified lines.
  2. Scan for code slop patterns (see checklist below).
  3. Refactor and simplify. Delete defensive bloat, eliminate speculative layers, and restore direct, obvious code.
  4. Verify correctness. Run tests, typechecks, or linters to prove the streamlined code still works.

Code Slop Patterns to Detect and Fix

1. Defensive Over-Engineering
  • Redundant null/undefined checks: Checking variables that internal types or preceding guards guarantee cannot be null. Trust internal invariants; concentrate validation at external boundaries (principle-boundary-discipline).
  • Try-catch swallows: Wrapping synchronous or infallible calls in try...catch blocks that swallow errors or return fallback values silently.
  • Speculative error handling: Catching errors that cannot happen in normal flow rather than letting real failures surface (principle-fix-root-causes).
2. Speculative Flexibility
  • Unrequested configuration: Adding options objects, configurable flags, or generalized plugin systems for single-use logic (principle-laziness-protocol).
  • One-caller abstractions: Creating helper functions, interfaces, or wrapper classes used in exactly one place with no likelihood of reuse (principle-minimize-reader-load).
  • Premature type parameterization: Introducing complex generic type parameters where concrete types suffice.
Show full SKILL.md (176 more words)Show less
3. Narrating and Placeholder Comments
  • Obvious narration: // check if user exists, // return the result, // loop through items. Delete them immediately.
  • Section banner comments: // ===================== HELPERS =====================. Remove them.
  • Commented-out code: Dead code blocks left "just in case". Delete them; git history preserves past code (principle-subtract-before-you-add).
4. Artificial AI Code Tells
  • Intermediate variable churn: Assigning a value to a temporary variable only to immediately return or pass it once:
    ts
    // Slop
const result = calculateTotal(items);
return result;

// Clean
return calculateTotal(items);
  • Redundant type assertions: Overusing as any, as unknown as T, or unnecessary non-null assertions ! when proper typing or narrowing makes the code type-safe (principle-type-system-discipline).
  • Verbose conditional boilerplate: Using 10-line if/else ladders where a simple ternary, dictionary lookup, or early return is cleaner.
5. Lingering Debug and Scratch Artifacts
  • Leftover console.log, print(), dbg!(), or ad-hoc benchmark timers.
  • Temporary test fixtures or scratch files committed by mistake.

Output / Reply

State:

  • Files cleaned and line delta (e.g. -45 lines).
  • Types of slop removed (e.g., redundant null guards, one-caller helper collapsed, narrating comments stripped).
  • Verification command run to confirm tests and types remain green.

© jtaroreh, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/deslop of jtaroreh/agystack.

Open the folder on GitHubat commit d1a0466

Compare with similar skills

Deslop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deslop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deslop this skilljtaroreh/agystack112—~890Automated safety check: PassMIT
SepiaNanako0129/sepia3.1k—~3.6kAutomated safety check: PassMIT
Noslopmarin-community/marin3.9k—~1.1kAutomated safety check: PassApache-2.0
Unslop ReviewMohamedAbdallah-14/unslop1553 repos~980Automated safety check: PassMIT
Korean Commit Message Polisherepoko77-ai/im-not-ai5.9k—~504Automated safety check: PassMIT
Chinese Technical Writingleter/zh-tech-writing352—~656Automated safety check: PassMIT

Similar skills

  • Sepia

    Nanako0129/sepia

    Make AI-generated writing read as human-written, in fiction and in professional prose.

    3.1k GitHub stars~3.6k tokensUpdated yesterday
    Writing & ContentAuto-check passed

  • Noslop

    marin-community/marin

    Deslop, simplify, or review low-value tests and prose only when explicitly requested for a branch or diff.

    3.9k GitHub stars~1.1k tokensUpdated today
    Writing & ContentAuto-check passed

  • Unslop Review

    MohamedAbdallah-14/unslop

    Rewrites code review comments so they read like a human teammate wrote them.

    155 GitHub starsUsed in 3 repos~980 tokens
    Writing & ContentAuto-check passed

  • Korean Commit Message Polisher

    epoko77-ai/im-not-ai

    Rewrites Korean commit messages that read like office jargon or translation into natural wording, leaving the type, scope and meaning untouched.

    5.9k GitHub stars~504 tokensUpdated 14 days ago
    Writing & ContentAuto-check passed

  • Chinese Technical Writing

    leter/zh-tech-writing

    Sets writing rules for Chinese technical docs: short plain sentences, consistent typography and a checklist for removing AI-sounding filler.

    352 GitHub stars~656 tokensUpdated 16 days ago
    Writing & ContentAuto-check passed

  • Deslop

    MrZoyo/deslop-GPT

    Audit or apply evidence-backed, test-first subtractive cleanup for accumulated agent-created test bloat, verification theater, and defensive or fallback bloat while preserving independent external…

    138 GitHub stars~4k tokensUpdated 4 days ago
    Writing & ContentAuto-check passed

More from jtaroreh/agystack

  • agystack Runtime Setup

    jtaroreh/agystack

    Configures agystack's model tiers per role and its execution runtime, choosing between local subagents and Cloud Run jobs for large parallel swarms.

    112 GitHub stars~1.7k tokensUpdated 8 days ago
    Auto-check passed

  • Loop Until Verified

    jtaroreh/agystack

    Runs an iterative verification loop on Google Antigravity: make one edit, run a test command, and reschedule until the command passes or the iteration budget runs out.

    112 GitHub stars~607 tokensUpdated 8 days ago
    Auto-check passed

  • agystack Engineering Framework

    jtaroreh/agystack

    agystack's agentic engineering framework and rigor mode. Runs poteto-mode playbooks, isolated subagents, and cloud swarms. Use for /agystack, agystack, or…

    112 GitHub stars~322 tokensUpdated 8 days ago
    Auto-check passed

  • Principle Attack The Premise

    jtaroreh/agystack

    Apply when handed a problem, constraint, or design you are tempted to accept as given.

    112 GitHub stars~489 tokensUpdated 8 days ago
    Auto-check passed

Categories

Questions about Deslop

What does Deslop do?

Clean AI slop and defensiveness out of code and diffs before commit. Deslop is an agent skill from jtaroreh/agystack. Clean AI slop and defensiveness out of code and diffs before commit.

When should I use Deslop?

Deslop fits situations like: tasks that involve Humanizing AI text.

How do I install Deslop in Claude Code?

Run `npx skills add jtaroreh/agystack --skill deslop -a claude-code`. Or copy the skill folder (skills/deslop in jtaroreh/agystack) into .claude/skills/deslop in your project. Claude Code loads it when a task matches its description.

How do I install Deslop in Codex?

Run `npx skills add jtaroreh/agystack --skill deslop -a codex`. Or copy the skill folder (skills/deslop in jtaroreh/agystack) into .agents/skills/deslop in your project. Codex loads it when a task matches its description.

Can I use Deslop in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jtaroreh/agystack --skill deslop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deslop, .gemini/skills/deslop, .github/skills/deslop and .opencode/skills/deslop in your project.

What does Deslop need to run?

Going by SKILL.md and its folder, Deslop needs the command-line tools its instructions call (git).

Does Deslop access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Deslop safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deslop use?

Deslop is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deslop use?

About 890 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deslop?

Skills that share tags, products or a category with Deslop: Sepia (Nanako0129/sepia, 3.1k stars), Noslop (marin-community/marin, 3.9k stars), Unslop Review (MohamedAbdallah-14/unslop, 155 stars) and Korean Commit Message Polisher (epoko77-ai/im-not-ai, 5.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deslop?

jtaroreh (a GitHub user) maintains it in jtaroreh/agystack, which has 112 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 1, 2026.

Source: jtaroreh/agystack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.