Agent skill

Deslop Typescript

by Consensys in Consensys/c0

Run a final de-slopping pass on nearly finished JavaScript or TypeScript work before commit or PR.

LGPL-3.0Auto-check passedWriting & Content

Install Deslop Typescript

skills CLI
$ npx skills add Consensys/c0 --skill deslop-typescript -a claude-code

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

GitHub CLI
$ gh skill install Consensys/c0 deslop-typescript --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/Consensys/c0.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/deslop-typescript .claude/skills/deslop-typescript && 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-typescript
GitHub stars
105
Token cost
~1.6k tokens
SKILL.md length
807 words
Files
3 (incl. references)
Skills in repo
11
Repo updated
First seen
Licence
LGPL-3.0

At a glance

Run a final de-slopping pass on nearly finished JavaScript or TypeScript work before commit or PR.

  • Works in 4 steps: Repo conformance → Type safety and source of truth → Simplicity → …
  • A JS/TS change is already functionally correct and you want to reduce AI-style noise
  • SKILL.md covers Goals, When To Use, Core Review Vectors and Context Bundle, plus 7 more sections
  • Calls git

What it does

Deslop Typescript is an agent skill from Consensys/c0. Run a final de-slopping pass on nearly finished JavaScript or TypeScript work before commit or PR. Use this skill when a JS/TS change is already functionally correct and you want to reduce AI-style noise, unnecessary wrappers, weak type boundaries, placeholder code, and other slop-scan hotspots without widening scope.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/slop-scan.md`).

It sits in Writing & Content, covering Humanizing AI text. It works with TypeScript and JavaScript. The repository describes itself as: c0 is an open-source AI platform built for organizational work, tools, and context. A single deployment to Cloudflare to get started. The licence is LGPL-3.0.

When your agent uses it

  • A JS/TS change is already functionally correct and you want to reduce AI-style noise
  • Unnecessary wrappers
  • Weak type boundaries
  • Placeholder code

Example prompts

  • “/deslop-typescript”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Repo conformance
  2. Type safety and source of truth
  3. Simplicity
  4. Slop hotspots

What it can do on your machine

Read from SKILL.md and the folder at commit e7a1810. 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 Typescript loads about 1.6k tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 85 tokens; SKILL.md has 807 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.1k

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 Consensys/c0 at commit e7a1810, republished under its LGPL-3.0 licence (© Consensys). 807 words, ~1,642 tokens.

Download SKILL.mdSave it as .claude/skills/deslop-typescript/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
deslop-typescript
description
Run a final de-slopping pass on nearly finished JavaScript or TypeScript work before commit or PR. Use this skill when a JS/TS change is already functionally correct and you want to reduce AI-style noise, unnecessary wrappers, weak type boundaries, placeholder code, and other `slop-scan` hotspots without widening scope.

Deslop TypeScript

Use this skill after the code works and before commit, PR, or review handoff. The goal is to leave the smallest clear diff that improves readability, type integrity, and repo fit without turning the task into a refactor.

This skill is based on the slop-scan model: deterministic slop heuristics for JS/TS repos, plus a review workflow that focuses fixes on worthwhile, local cleanup.

Goals

  • Remove obvious slop without widening scope.
  • Prefer compile-time guarantees over runtime ceremony inside typed repo-owned code.
  • Collapse unnecessary wrappers, pass-through helpers, and placeholder structure.
  • Keep repo conventions, docs, and ownership boundaries intact.

When To Use

Use this skill when:

  • the change is already functionally correct
  • the repo is primarily JavaScript or TypeScript
  • you want a final cleanup pass before commit or PR
  • code feels AI-assisted, over-abstracted, or noisier than the surrounding repo

Do not use this skill when:

  • the feature is still incomplete or behavior is still changing
  • the task is mostly non-JS/TS code
  • the user asked for a broad refactor rather than a narrow cleanup

Core Review Vectors

Review the changed area through these lenses:

  1. Repo conformance
    • Follow repo AGENTS.md, nested AGENTS.md, design docs, and established local patterns.
    • Prefer the style already present in the touched area over generic cleanup instincts.
  2. Type safety and source of truth
    • Preserve canonical types instead of re-declaring or widening them.
    • Remove unnecessary casts, redundant parsing, and boundary checks inside trusted typed code.
    • Keep validation at genuinely untrusted boundaries.
  3. Simplicity
    • Remove wrappers, factories, and helpers that only rename or pass through values.
    • Inline trivial indirection when it improves readability locally.
  4. Slop hotspots
    • Look for patterns slop-scan commonly flags: pass-through wrappers, return await noise, placeholder comments, duplicated helpers, fragmented files, weak catch blocks, and repeated setup boilerplate.

Context Bundle

Before editing, gather only the context that matters for the changed area:

  • repo root AGENTS.md
  • nearest nested AGENTS.md files for touched paths
  • relevant design docs or architecture notes
  • the changed files plus nearby callers, callees, and types
  • project scripts or config for lint, typecheck, test, and slop-scan

If an active plan or execution doc exists for the work, read it before cleanup so you do not remove intentional structure.

Scope Selection

Default to the current changed files unless the user explicitly names a branch to deslop against.

For the default scope, inspect local changed JS/TS files from the working tree and index:

bash
git diff --name-only --diff-filter=ACMR -- '*.js' '*.jsx' '*.ts' '*.tsx'
git diff --cached --name-only --diff-filter=ACMR -- '*.js' '*.jsx' '*.ts' '*.tsx'
git ls-files --others --exclude-standard -- '*.js' '*.jsx' '*.ts' '*.tsx'

If the user says to deslop against a branch, use the current checkout compared to that branch. Prefer a local ref when present, then fall back to origin/<branch>:

bash
target_branch="<branch-from-user>"
target_ref="$target_branch"
git rev-parse --verify --quiet "$target_ref" >/dev/null || target_ref="origin/$target_branch"
merge_base="$(git merge-base HEAD "$target_ref")"
git diff --name-only --diff-filter=ACMR "$merge_base" HEAD -- '*.js' '*.jsx' '*.ts' '*.tsx'

Use that branch-diff file list to choose the changed area, nearby callers/callees, and any narrow slop-scan roots. If local working tree or indexed changes also exist, include them only when they are part of the requested deslop pass or when the user asks for all current changes.

Show full SKILL.md (336 more words)Show less

Slop-Scan Workflow

Use slop-scan as a signal source, not as an absolute judge.

  1. Detect how to run it.
  2. Run a narrow scan on the repo or changed area.
  3. Use the findings to identify hotspots.
  4. Fix only the issues that are clearly worthwhile and local.
  5. Re-run the narrowest relevant validation.

Preferred command order:

bash
# Repo-installed package
nub exec slop-scan scan . --lint

# Fallback if not installed locally
nub dlx slop-scan scan . --lint

When the repo already defines a slop script, prefer that over ad hoc commands.

For machine-readable output:

bash
nub exec slop-scan scan . --json

If the repo has a slop-scan.config.* or repo-slop.config.*, trust that config as the starting point. Root .gitignore is also respected by the tool.

What To Fix Automatically

Fix these when they are local and clearly better:

  • duplicated or widened types
  • unnecessary casts
  • redundant parsing or revalidation inside trusted typed paths
  • pass-through wrappers and dead helpers
  • return await noise where it adds nothing
  • placeholder comments, TODO scaffolding, debug leftovers
  • trivial fragmentation that can be collapsed without changing behavior
  • weak catch blocks that hide errors or continue ambiguously

What To Leave Alone

Do not change these unless the user asked for deeper work:

  • stable code outside the changed area
  • abstractions that encode real ownership or API boundaries
  • speculative cleanups with unclear payoff
  • large file moves or architectural rewrites
  • subjective style changes that do not clearly improve the code

Working Pattern

  1. Read repo guidance and nearby code first.
  2. Select scope: default to current changed files, or use a branch diff when the user names a branch to deslop against.
  3. Inspect the changed area and identify the likely slop hotspots.
  4. Run slop-scan if available, plus the narrowest relevant lint/type/test checks.
  5. Apply the smallest useful fixes.
  6. Re-run the narrowest validations immediately.
  7. Keep the final diff focused on deslop work, not unrelated refactors.

Response Shape

When using this skill, summarize:

  • what looked sloppy or risky
  • what you fixed
  • what you intentionally left alone to avoid widening scope
  • what validation you ran, and what you could not run

References

Open only if needed:

  • references/slop-scan.md for the underlying tool model and command notes

© Consensys, LGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in .agents/skills/deslop-typescript of Consensys/c0.

  • SKILL.md
  • agents/openai.yaml
  • references/slop-scan.md

Open the folder on GitHubat commit e7a1810

Compare with similar skills

Deslop Typescript 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 Typescript compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deslop Typescript this skillConsensys/c0105—~1.6kAutomated safety check: PassLGPL-3.0
Install Anti Sloptrycompai/crm11k1 repos~881Automated safety check: PassMIT
Biome Anti Slopnightly-labs/openbot453—~1.5kAutomated safety check: PassCustom licence
Typescriptweb-infra-dev/rstest505—~1.3kAutomated safety check: PassMIT
Deepgram JS Text Intelligencedeepgram/deepgram-js-sdk276—~1.1kAutomated safety check: PassMIT
Azure AI Translation TSmicrosoft/skills3.1k—~2kAutomated safety check: PassMIT

Similar skills

  • Install Anti Slop

    trycompai/crm

    Install and configure the anti-slop Oxlint plugin in a local TypeScript or JavaScript repository.

    11k GitHub starsUsed in 1 repo~881 tokens
    Writing & ContentAuto-check passed
  • Biome Anti Slop

    nightly-labs/openbot

    Install and configure vendored Biome anti-slop GritQL rules in a local TypeScript or JavaScript repository.

    453 GitHub stars~1.5k tokensUpdated today
    Writing & ContentAuto-check passed
  • Typescript

    web-infra-dev/rstest

    TypeScript anti-slop guardrails. An agent skill from web-infra-dev/rstest.

    505 GitHub stars~1.3k tokensUpdated today
    Writing & ContentAuto-check passed
  • Deepgram JS Text Intelligence

    deepgram/deepgram-js-sdk

    A skill your agent uses when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Text Intelligence / Read (/v1/read) for sentiment, summarization, topic detection, and intent…

    276 GitHub stars~1.1k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Azure AI Translation TS

    microsoft/skills

    Official

    Build translation applications using Azure Translation SDKs for JavaScript (@azure-rest/ai-translation-text, @azure-rest/ai-translation-document).

    3.1k GitHub stars~2k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed
  • Code Translation

    ArabelaTso/Skills-4-SE

    Convert code between programming languages while preserving functionality and semantics.

    253 GitHub stars~3.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

More from Consensys/c0

All 11 skills in this repo
  • Debug deployed Cloudflare Workers using the cfobservability MCP, Wrangler, D1/R2 state, repo evidence, and safe live reproduction.

    105 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check: notes
  • A skill your agent uses when adding, changing, or reviewing Workflow Nodes in the c0 agent repo, including shared node catalog metadata, Workflow Node options and ports, runtime node Adapters…

    105 GitHub stars~943 tokensUpdated 1 mo ago
    Auto-check passed
  • Guidance for safely changing the c0 Workflow runtime ABI, manifest ABI, runtime kernels, manifest migrations, workflow artifact compatibility, and audit/backfill tooling.

    105 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Agent Eval Loop

    Consensys/c0

    Run and improve the c0 agent evaluation loop using the local and remote Cloudflare MCP harness, versioned history notes, and current Cloudflare product updates.

    105 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Alchemy Env Types

    Consensys/c0

    Derive Cloudflare worker env types from Alchemy resource Env types instead of hand-writing env shapes.

    105 GitHub stars~707 tokensUpdated 1 mo ago
    Auto-check passed
  • C0 Config

    Consensys/c0

    A skill your agent uses when changing c0 deployment configuration, runtime-editable global settings, auth providers, AI providers, MCP Context Forge, discovered registries, secret references, or…

    105 GitHub stars~2.1k tokensUpdated 1 mo ago
    Auto-check: notes

Questions about Deslop Typescript

What does Deslop Typescript do?

Run a final de-slopping pass on nearly finished JavaScript or TypeScript work before commit or PR. Deslop Typescript is an agent skill from Consensys/c0. Run a final de-slopping pass on nearly finished JavaScript or TypeScript work before commit or PR.

When should I use Deslop Typescript?

Deslop Typescript fits situations like: A JS/TS change is already functionally correct and you want to reduce AI-style noise; unnecessary wrappers; weak type boundaries; placeholder code.

How do I install Deslop Typescript in Claude Code?

Run `npx skills add Consensys/c0 --skill deslop-typescript -a claude-code`. Or copy the skill folder (.agents/skills/deslop-typescript in Consensys/c0) into .claude/skills/deslop-typescript in your project. Claude Code loads it when a task matches its description.

How do I install Deslop Typescript in Codex?

Run `npx skills add Consensys/c0 --skill deslop-typescript -a codex`. Or copy the skill folder (.agents/skills/deslop-typescript in Consensys/c0) into .agents/skills/deslop-typescript in your project. Codex loads it when a task matches its description.

Can I use Deslop Typescript 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 Consensys/c0 --skill deslop-typescript -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-typescript, .gemini/skills/deslop-typescript, .github/skills/deslop-typescript and .opencode/skills/deslop-typescript in your project.

What does Deslop Typescript need to run?

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

Does Deslop Typescript 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 Typescript 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 Typescript use?

Deslop Typescript is published under the LGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deslop Typescript use?

About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 439 tokens, read only when the agent opens those files.

What are the alternatives to Deslop Typescript?

Skills that share tags, products or a category with Deslop Typescript: Install Anti Slop (trycompai/crm, 11k stars), Biome Anti Slop (nightly-labs/openbot, 453 stars), Typescript (web-infra-dev/rstest, 505 stars) and Deepgram JS Text Intelligence (deepgram/deepgram-js-sdk, 276 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deslop Typescript?

Consensys (a GitHub organization) maintains it in Consensys/c0, which has 105 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on August 18, 2026.

Source: Consensys/c0 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.