zero-slop 2.12.2 → 2.12.5

package/README.md

@@ -1,40 +1,19 @@
-<p align="center">
-  <a href="https://zero-slop.ai">
-    <picture>
-      <source media="(prefers-color-scheme: dark)" srcset="assets/logo/zero-slop-logo-reversed.svg">
-      <img src="assets/logo/zero-slop-logo-primary.svg" width="360" alt="Zero Slop">
-    </picture>
-  </a>
-</p>
-
-<p align="center"><strong>Edit AI-assisted writing without losing the details.</strong></p>
-
-<p align="center">
-  Zero Slop is an open-source skill that finds stock phrases, repetition, vague claims, and mechanical rhythm.<br>
-  Your AI assistant edits the draft. Local tools check its names, numbers, links, quotations, code, tables, and paths against the original.
-</p>
-
-<p align="center">
-  <a href="https://zero-slop.ai/try/"><strong>Try it in your browser</strong></a>
-  ·
-  <a href="#quick-start">Install the skill</a>
-  ·
-  <a href="#evidence-and-limits">See the evidence</a>
-  ·
-  <a href="https://github.com/manavmishra/ZeroSlop/releases/latest">Latest release</a>
-  ·
-  <a href="https://zero-slop.ai/brand/">Brand assets</a>
-</p>
-
-<p align="center">
-  <a href="https://github.com/manavmishra/ZeroSlop/actions/workflows/validate.yml"><img alt="Validate" src="https://github.com/manavmishra/ZeroSlop/actions/workflows/validate.yml/badge.svg"></a>
-  <img alt="Version 2.12.2" src="https://img.shields.io/badge/version-2.12.2-72528F?color=C15732">
-  <a href="https://www.npmjs.com/package/zero-slop"><img alt="npm version" src="https://img.shields.io/npm/v/zero-slop?color=C15732"></a>
-  <a href="https://www.npmjs.com/package/zero-slop"><img alt="npm downloads" src="https://img.shields.io/npm/dm/zero-slop?color=17634F"></a>
-  <a href="https://github.com/manavmishra/ZeroSlop/stargazers"><img alt="GitHub stars" src="https://img.shields.io/github/stars/manavmishra/ZeroSlop?style=flat&color=C15732"></a>
-  <a href="LICENSE"><img alt="MIT license" src="https://img.shields.io/badge/license-MIT-141412"></a>
-  <a href="https://hol.org/registry/plugins/manav-mishra%2Fzero-slop"><img alt="Listed in the HOL plugin registry" src="https://img.shields.io/badge/HOL%20registry-listed-2C6E8F"></a>
-</p>
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="assets/logo/zero-slop-logo-reversed.svg">
+  <img src="assets/logo/zero-slop-logo-primary.svg" width="180" alt="Zero Slop">
+</picture>
+
+# Zero Slop
+
+Find and remove AI slop in your writing. Get rid of workslop without losing your core intent and message.
+
+Zero Slop is a free, open-source set of instructions and checks for an AI assistant. The assistant edits your draft. The local tools flag stock language and compare names, numbers, links, quotations, code, tables, and paths with the original. If your ChatGPT setup does not support skills, [try the browser editor](https://zero-slop.ai/try/) without installing anything.
+
+<img alt="Version 2.12.5" src="https://img.shields.io/badge/version-2.12.5-72528F?color=C15732">
+
+## Why it exists
+
+An AI draft can be grammatical and still sound like everybody else's. Asking for a rewrite can also change a number or smooth away your point. Zero Slop tells your assistant what to cut, then checks the result against your original. The writing score finds patterns worth reviewing; it cannot tell who wrote the text.
 
 <a href="assets/zero-slop-demo.mp4?v=dark-shell-restored-20260906">
   <picture>
@@ -50,7 +29,7 @@ Here is a short launch draft:
 
 > We're thrilled to announce that our team has leveraged cutting-edge machine learning to deliver a seamless onboarding experience, reducing setup time by 40%.
 
-The local scorer rates it 99.3/100. Lower is better. It flags “We're thrilled
+The local scorer gives it 99.3/100. Lower is better. It flags “We're thrilled
 to,” “leveraged,” “cutting-edge,” and “seamless.”
 
 An edit that keeps the stated result:
@@ -62,13 +41,15 @@ Writing score: 9.5/100  [clear]
   Flagged phrases : 0 across 10 words
 ```
 
-The result still claims a 40% reduction in setup time. Scores describe writing patterns; they cannot identify the author. See four complete pairs in [`examples/`](examples/).
+The result still claims a 40% reduction in setup time. See four complete pairs in [`examples/`](examples/).
 
 Use it on launch posts, changelogs, emails, or research summaries. You can score drafts without editing.
 
 ## Quick start
 
-Install it in an assistant that supports skills:
+To try the browser editor, use a sample you are comfortable sending to a hosted service. Compare its edit with your original before you use it. The slash command below works only in an assistant where you have installed the skill.
+
+If you use Claude Code, Codex, or another assistant that supports skills, install Zero Slop there:
 
 ```sh
 npx skills add manavmishra/ZeroSlop --global
@@ -78,66 +59,15 @@ npx skills add manavmishra/ZeroSlop --global
 /zero-slop (your writing)
 ```
 
-To inspect without rewriting, use `/zero-slop inspect (your writing)`. Or [try the browser editor](https://zero-slop.ai/try/).
-
-### Other ways to use it
-
-| Environment | Fastest route |
-|---|---|
-| Claude Code, Codex, Cursor, OpenCode, Warp, Zed | `npx skills add manavmishra/ZeroSlop --global` |
-| Gemini CLI | `gemini extensions install https://github.com/manavmishra/ZeroSlop --auto-update` |
-| Claude Code plugin | `/plugin marketplace add manavmishra/ZeroSlop`, then `/plugin install zero-slop@zero-slop` |
-| Any assistant with file uploads | Download the [single-file bundle](https://github.com/manavmishra/ZeroSlop/releases/latest/download/zero-slop-single-file.md) |
-| Claude.ai | Upload the [latest skill ZIP](https://github.com/manavmishra/ZeroSlop/releases/latest/download/zero-slop.zip) |
-| ChatGPT, Claude, Grok, Gemini, Cursor, or another MCP client | Connect the optional [hosted MCP server](mcp/README.md) |
-
-For a local score without a model call:
-
-```sh
-npx zero-slop score draft.md
-```
-
-From a cloned checkout, check a folder against the review threshold of 25:
-
-```sh
-python3 scripts/slopscore.py --batch drafts/ --gate 25
-```
-
-Installed checks run locally; skill editing follows your assistant's privacy settings. The [hosted MCP service](mcp/README.md) and browser editor process drafts remotely with Workers AI.
-
-For an MCP client, use this endpoint:
-
-```text
-https://mcp.zero-slop.ai/mcp
-```
+To see the flagged passages without an edit, use `/zero-slop inspect (your writing)`.
 
-[Connection options and listing status](DISTRIBUTION.md).
-
-## Edit from the command line
-
-The CLI sends a file to the hosted editor without changing the file on disk:
-
-```sh
-npx --yes zero-slop@2.12.2 deslop draft.md --genre professional
-```
-
-Use `-` for stdin and `--json` for structured output. `--require-approved` prints the result but exits nonzero when review is needed. Requires Node.js 22+; offline `score` also needs Python 3. [CLI options and privacy](docs/cli.md).
-
-## Call the REST API
-
-```sh
-curl --fail-with-body --max-time 75 https://mcp.zero-slop.ai/v1/deslop \
-  -H 'Content-Type: application/json' \
-  --data '{"text":"Maya owns the pricing review.","genre":"professional"}'
-```
+The command above works with Claude Code and Codex. In Claude.ai, upload the [skill ZIP](https://github.com/manavmishra/ZeroSlop/releases/latest/download/zero-slop.zip). [Other installation paths](DISTRIBUTION.md) include Gemini CLI and remote MCP connections where your client allows them. You can also [score a file locally](#local-scoring) without a model call.
 
-REST returns the same result as MCP. Check `status` before using an edit. Shared free capacity accepts up to 20,000 Unicode code points after trimming. Hosted CLI and REST editing process drafts remotely without storing them.
-
-[API reference](docs/rest-api.md) · [OpenAPI contract](https://mcp.zero-slop.ai/openapi.json)
+The installed checks run locally, while the assistant that edits your text follows its own privacy settings. The browser editor and [hosted MCP service](mcp/README.md) send drafts to Workers AI. Check your organization's rules before using any of these with sensitive text.
 
 ## What it does
 
-The installed skill ships no model. Your AI assistant, whether Claude, GPT, or another compatible model, reads and edits the draft. The skill supplies the workflow and local tools: a 0–100 writing score, source-detail checks, and a final comparison with the original. The eight stages divide the work.
+The installed skill ships no model. Your AI assistant, whether Claude, GPT, or another compatible model, reads and edits the draft. The skill supplies the workflow and local tools: a 0 to 100 writing score, source-detail checks, and a final comparison with the original.
 
 Use the score to locate passages worth reviewing. Optional private learning records reason-labelled corrections you provide; it does not learn a complete writing style.
 
@@ -179,9 +109,7 @@ If repair fails, the editor returns the safest edit with a warning and stops the
 
 ### Optional reader review
 
-Ask: **“Review this for backend engineers. Where would they stop reading? Don't rewrite it.”** An optional skim, passage reactions, and notes-only recall return comments. Simulated reactions cannot establish human behavior. Sequential review needs isolated contexts; see the [privacy and reporting limits](references/reader-review.md). Hosted calls are unchanged.
-
-Inspired by [First Reader](bench/first-reader/), which only reviews. Zero Slop also rewrites and checks source details. Neither has established human-reader accuracy; First Reader has no invented rewrite score.
+You can ask the skill where a particular audience might stop reading without requesting an edit. The [reader-review guide](references/reader-review.md) explains the limits: simulated reactions are not evidence of what real readers prefer. This optional mode adds no hosted model calls.
 
 ## Evidence and limits
 
@@ -214,9 +142,7 @@ Zero Slop's outputs came from v2.5.9; newer versions only rescore them. The curr
 
 On 75 labelled antithesis pairs, the reading pass reached 91.2% recall across the full set, 100% recall on shapes in reach, and 100% precision. We constructed and labelled them; this is a regression test, not field accuracy.
 
-Local timings exclude AI editing. On one Apple silicon Mac, the scorer processed 1,000 documents in a median 1.9929 seconds (501.8 per second), with five runs ranging from 1.9614 to 2.0945 seconds. A 15,201-word document took a median 0.3223 seconds; the slowest stress case took 2.2932 seconds; learning from an 8,000-word edit took 0.1592 seconds. [Machine and results](bench/performance-results.json).
-
-Across 12 interleaved runs against 2.7.7, median throughput was 0.26% lower, within the 5% regression limit. The two-way replay used Zero Slop v2.6.0. These local timings are not a service-level guarantee.
+Local timings exclude AI editing. On one Apple silicon Mac, the scorer checked 1,000 documents in a median 1.9929 seconds (501.8 per second). Across 12 interleaved runs against 2.7.7, it had 0.26% lower median throughput, within the 5% regression limit. The two-way replay used Zero Slop v2.6.0. [Machine and results](bench/performance-results.json). These timings are not a service-level guarantee.
 
 The [RAID+ audit](bench/raid-plus-corpus/README.md) asks a different question: how often does the scorer flag writing from different models? The pinned sample contains 7,627 usable generations:
 
@@ -245,6 +171,56 @@ You decide whether to teach Zero Slop a preference. Give it an original output,
 
 A profile selected by name can exempt existing watchlist words. It does not learn your cadence, tone, or entire writing style.
 
+## For developers
+
+### Hosted MCP
+
+The endpoint for compatible clients is:
+
+```text
+https://mcp.zero-slop.ai/mcp
+```
+
+[Connection options](mcp/README.md).
+
+For Gemini CLI, run `gemini extensions install https://github.com/manavmishra/ZeroSlop --auto-update`. For file-upload assistants, download the [single-file bundle](https://github.com/manavmishra/ZeroSlop/releases/latest/download/zero-slop-single-file.md).
+
+### Local scoring
+
+Score a file without sending it to a model:
+
+```sh
+npx zero-slop score draft.md
+```
+
+From a cloned checkout, check a folder against the review threshold of 25:
+
+```sh
+python3 scripts/slopscore.py --batch drafts/ --gate 25
+```
+
+### Command line
+
+The CLI sends a file to the hosted editor without changing the file on disk:
+
+```sh
+npx --yes zero-slop@2.12.5 deslop draft.md --genre professional
+```
+
+Use `-` for stdin and `--json` for structured output. `--require-approved` prints the result but exits nonzero when review is needed. Requires Node.js 22+; offline `score` also needs Python 3. [CLI options and privacy](docs/cli.md).
+
+### REST API
+
+The REST API accepts the same edit request:
+
+```sh
+curl --fail-with-body --max-time 75 https://mcp.zero-slop.ai/v1/deslop \
+  -H 'Content-Type: application/json' \
+  --data '{"text":"Maya owns the pricing review.","genre":"professional"}'
+```
+
+Check `status` before using an edit. Shared free capacity accepts up to 20,000 Unicode code points after trimming. [API reference](docs/rest-api.md) · [OpenAPI contract](https://mcp.zero-slop.ai/openapi.json)
+
 ## Find the source
 
 | Path | Purpose |

package/SKILL.md

@@ -2,7 +2,7 @@
 name: zero-slop
 license: MIT
 metadata:
-  version: "2.12.2"
+  version: "2.12.5"
   author: manavmishra
 description: Edit drafts into natural prose, inspect AI-sounding patterns, or review how a specified audience might respond passage by passage. Zero Slop runs inside the user's existing AI assistant with local tools that protect source details. Use for humanizing or de-slopping writing, polishing outward-facing prose, social drafts, final editorial checks, or an explicit simulated reader review. Preserve facts, voice and format; reader simulations are hypotheses, not human feedback.
 ---

package/docs/cli.md

@@ -3,7 +3,7 @@
 Use `deslop` for hosted editing with MCP parity. Use `score` for offline checks.
 
 ```sh
-npm install --global zero-slop@2.12.2
+npm install --global zero-slop@2.12.5
 zero-slop deslop draft.md --genre professional
 zero-slop deslop - --genre email < draft.txt
 zero-slop deslop draft.md --json --require-approved

package/gemini-extension.json

@@ -1,6 +1,6 @@
 {
   "name": "zero-slop",
-  "version": "2.12.2",
+  "version": "2.12.5",
   "description": "Find and fix canned AI writing while preserving the facts, voice, and format.",
   "mcpServers": {
     "zero-slop": {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "zero-slop",
-  "version": "2.12.2",
+  "version": "2.12.5",
   "description": "An editing skill, offline writing checks, and a CLI for the hosted Zero Slop MCP pipeline. Find stock AI phrasing, rewrite, and check source details.",
   "bin": {
     "zero-slop": "bin/zero-slop.mjs"

package/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "zero-slop",
-  "version": "2.12.2",
+  "version": "2.12.5",
   "description": "Find and fix canned AI writing while preserving the facts, voice, and format.",
   "author": {
     "name": "Manav Mishra",