Humanizer
Azure-Samples/interview-coach-agent-framework
Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.
Check prose with Jev for narrow AI-writing patterns and revise from its feedback.
Install Jev Prose
$ npx skills add pchalasani/claude-code-tools --skill jev-prose -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pchalasani/claude-code-tools jev-prose --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/pchalasani/claude-code-tools.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/jev-prose/src/jev_prose .claude/skills/jev-prose && rm -rf skills-srcUse ~/.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/
Install the "jev-prose" agent skill from https://github.com/pchalasani/claude-code-tools/tree/main/packages/jev-prose/src/jev_prose into .claude/skills/jev-prose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-prose", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/pchalasani/claude-code-tools/tree/main/packages/jev-prose/src/jev_proseType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add pchalasani/claude-code-tools --skill jev-prose -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pchalasani/claude-code-tools jev-prose --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pchalasani/claude-code-tools.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/jev-prose/src/jev_prose .agents/skills/jev-prose && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "jev-prose" agent skill from https://github.com/pchalasani/claude-code-tools/tree/main/packages/jev-prose/src/jev_prose into .agents/skills/jev-prose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-prose", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pchalasani/claude-code-tools --skill jev-prose -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pchalasani/claude-code-tools jev-prose --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pchalasani/claude-code-tools.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/jev-prose/src/jev_prose .cursor/skills/jev-prose && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "jev-prose" agent skill from https://github.com/pchalasani/claude-code-tools/tree/main/packages/jev-prose/src/jev_prose into .cursor/skills/jev-prose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-prose", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/pchalasani/claude-code-tools.git --path packages/jev-prose/src/jev_prose--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add pchalasani/claude-code-tools --skill jev-prose -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pchalasani/claude-code-tools jev-prose --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pchalasani/claude-code-tools.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/jev-prose/src/jev_prose .gemini/skills/jev-prose && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "jev-prose" agent skill from https://github.com/pchalasani/claude-code-tools/tree/main/packages/jev-prose/src/jev_prose into .gemini/skills/jev-prose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-prose", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install pchalasani/claude-code-tools jev-proseInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add pchalasani/claude-code-tools --skill jev-prose -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pchalasani/claude-code-tools.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/jev-prose/src/jev_prose .github/skills/jev-prose && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "jev-prose" agent skill from https://github.com/pchalasani/claude-code-tools/tree/main/packages/jev-prose/src/jev_prose into .github/skills/jev-prose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-prose", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pchalasani/claude-code-tools --skill jev-prose -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pchalasani/claude-code-tools jev-prose --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pchalasani/claude-code-tools.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/jev-prose/src/jev_prose .opencode/skills/jev-prose && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "jev-prose" agent skill from https://github.com/pchalasani/claude-code-tools/tree/main/packages/jev-prose/src/jev_prose into .opencode/skills/jev-prose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-prose", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
jev-prose- GitHub stars
- 2k
- Token cost
- ~1.1k tokens
- SKILL.md length
- 584 words
- Files
- 7
- Skills in repo
- 18
- Repo updated
- First seen
- Licence
- MIT
At a glance
Check prose with Jev for narrow AI-writing patterns and revise from its feedback.
- Works in 5 steps: Save the exact draft in a temporary… → Run jev-prose check draft.txt --profile… → Read the report even when the command… → …
- Asked for Jev prose checks
- SKILL.md covers Setup and Bounded loop
- Runs Python scripts from its folder; calls uv; needs CLOUDFLARE_API_TOKEN
What it does
Jev Prose is an agent skill from pchalasani/claude-code-tools. Check prose with Jev for narrow AI-writing patterns and revise from its feedback. Use when asked for Jev prose checks, AI-pattern cleanup, or an ongoing check-and-rewrite loop while writing sentences or paragraphs.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files (for example `__init__.py`, `backend.py` and `cli.py`).
It sits in Writing & Content, covering Humanizing AI text. The repository describes itself as: Practical productivity tools for Claude Code, Codex-CLI, and similar CLI coding agents. The licence is MIT.
When your agent uses it
- Asked for Jev prose checks
- AI-pattern cleanup
- An ongoing check-and-rewrite loop while writing sentences
Example prompts
- “/jev-prose”
Requirements
- Python 3
- A credential in CLOUDFLARE_API_TOKEN
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Save the exact draft in a temporary UTF-8 file. Keep the original and track
- Run jev-prose check draft.txt --profile general > report.json. For papers,
- Read the report even when the command exits 1: that means findings, not a
- If status is clean, stop. Otherwise inspect the flagged questions and
- If no useful revision follows, stop and disclose the unresolved or dismissed
What it can do on your machine
Read from SKILL.md and the folder at commit bbb555c. 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
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, 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 these keys or tokens, usually read from environment variables:
CLOUDFLARE_API_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Jev Prose loads about 1.1k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 584 words of instructions outside code blocks.
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 pchalasani/claude-code-tools at commit bbb555c, republished under its MIT licence (© pchalasani). 584 words, ~1,073 tokens.
Download SKILL.mdSave it as
.claude/skills/jev-prose/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- jev-prose
- description
- Check prose with Jev for narrow AI-writing patterns and revise from its feedback. Use when asked for Jev prose checks, AI-pattern cleanup, or an ongoing check-and-rewrite loop while writing sentences or paragraphs.
Jev prose check and revision
Use the jev-prose CLI to get independent, probabilistic editorial feedback.
It checks patterns, not authorship. The writer makes the editorial decisions.
Setup
Run jev-prose --help to check availability. From a claude-code-tools checkout,
install with uv tool install ./packages/jev-prose. The package carries the
persistent question bank; no global skill source paths are needed at runtime.
If no checkout or installed CLI is available, report that prerequisite rather
than substituting self-review for a Jev result.
Default authentication is CLOUDFLARE_ACCOUNT_ID and CLOUDFLARE_API_TOKEN,
or an existing sysone account configuration and Wrangler login. The backend is
hosted Jev; the text and optional context are sent there. A configured alternative
can be selected with --backend typesafe or --url and --model. Do not print
secrets. An authentication or billing failure stops the loop.
Bounded loop
For each requested sentence, paragraph, or short section:
- Save the exact draft in a temporary UTF-8 file. Keep the original and track the revision count (initial draft is attempt 0). Preserve the user's intended facts, names, numbers, citations, caveats, voice, and literal quotations.
- Run
jev-prose check draft.txt --profile general > report.json. For papers, specifications, and formal technical prose use--profile formal. Usestrictonly when requested; it adds personal editorial preferences. Optional--audience,--voice, and--context context.txthelp avoid false positives. Keep these settings and the threshold fixed throughout the loop. - Read the report even when the command exits 1: that means findings, not a
failed call. Require
ran: true,ok: true, andanswered == expected. Exit 2, missing output, malformed JSON, or an incomplete check stops the loop as an error; never label the draft clean in those cases. - If
statusisclean, stop. Otherwise inspect the flagged questions and guidance against the actual draft. A high probability is not a command to edit: dismiss an inapplicable flag with a brief reason. Jev provides no evidence spans; locate the passage yourself without pretending it supplied an exact quote. Combine overlapping findings into one targeted revision. - If no useful revision follows, stop and disclose the unresolved or dismissed flags. Otherwise revise only the affected prose, increment the attempt count, and return to step 2. Allow at most three revisions and four checks total. Stop earlier if text repeats or feedback cycles without useful improvement. Always check the last revision; never end on an unchecked rewrite.
Show full SKILL.md (193 more words)Show less
Preserve substantive claims as well as individual facts. If addressing a finding would weaken, strengthen, remove, or otherwise change a conclusion, leave the claim intact and report the finding unresolved unless the user has authorized factual or argument changes. An unsupported claim is not permission to silently replace the author's intended claim with a different one.
Do not change thresholds to obtain a clean result. Do not add invented examples, anecdotes, feelings, measurements, sources, or stronger claims. Do not remove necessary qualifications or factual content to lower the number of flags. Check meaning against the original after each revision; undo any harmful edit.
A sentence check cannot establish document-level structure. If asked to use this while writing a document, check each completed paragraph and then the finished short section for repetition. Respect the 24,000-character input limit; do not silently truncate. This workflow runs when invoked; it installs no automatic hook.
Return the revised prose in the requested form. Briefly report the number of revisions, check outcome, and any unresolved/dismissed findings. If every finding was dismissed, say that explicitly instead of reporting a model-clean result. Keep detector reports out of published prose unless requested.
© pchalasani, MIT. 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 6 other files in packages/jev-prose/src/jev_prose of pchalasani/claude-code-tools.
- SKILL.md
- __init__.py
- backend.py
- cli.py
- detector.py
- install.py
- questions.json
Open the folder on GitHubat commit bbb555c
Compare with similar skills
Jev Prose 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Jev Prose this skillpchalasani/claude-code-tools | 2k | — | ~1.1k | Automated safety check: Pass | MIT | |
| HumanizerAzure-Samples/interview-coach-agent-framework | 173 | 38 repos | ~5.8k | Automated safety check: Pass | MIT | |
| Avoid AI Writingconorbronsdon/avoid-ai-writing | 4.9k | 3 repos | ~8.1k | Automated safety check: Pass | MIT | |
| User-Facing Text Cleanupguillaumemeyer/watermarks-remover | 24k | — | ~3.5k | Automated safety check: Pass | MIT | |
| Install Anti Sloptrycompai/crm | 11k | 1 repos | ~881 | Automated safety check: Pass | MIT | |
| Stop SlopXe/site | 732 | 8 repos | ~423 | Automated safety check: Pass | MIT |
Similar skills
- Official
Avoid AI Writing
conorbronsdon/avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms").
User-Facing Text Cleanup
guillaumemeyer/watermarks-remover
Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.
Install Anti Slop
trycompai/crm
Install and configure the anti-slop Oxlint plugin in a local TypeScript or JavaScript repository.
Stop Slop
Xe/site
Remove AI writing patterns from prose. An agent skill from Xe/site.
Chinese Text Humanizer
op7418/Humanizer-zh
Edits Chinese articles, comments and documents to remove filler, repetition and template phrasing while keeping the facts, the level of certainty and the author's voice.
More from pchalasani/claude-code-tools
All 18 skills in this repoRemove AI Patterns
pchalasani/claude-code-tools
Remove AI-writing patterns ("AI-isms") from text using the avoid-ai-writing catalog (conorbronsdon/avoid-ai-writing).
Dynamic Workflow
pchalasani/claude-code-tools
Create, review, run, inspect, pause, resume, and cancel durable JavaScript workflows that coordinate multiple headless Codex agents.
Voxtype Install
pchalasani/claude-code-tools
Guide the user through installing, configuring, and launching voxtype — local on-device voice dictation (speech-to-text that types wherever the cursor is).
Agent Style
pchalasani/claude-code-tools
Literature-backed English technical-prose writing rules (agent-style, 21 rules).
Msg
pchalasani/claude-code-tools
Inter-agent communication via the msg CLI. An agent skill from pchalasani/claude-code-tools.
Tmux CLI
pchalasani/claude-code-tools
CLI utility to communicate with other CLI Agents or Scripts in other tmux panes; use it only when user asks you to communicate with other CLI Agents or Scripts in other tmux panes.
Related
Categories
Questions about Jev Prose
What does Jev Prose do?
Check prose with Jev for narrow AI-writing patterns and revise from its feedback. Jev Prose is an agent skill from pchalasani/claude-code-tools. Check prose with Jev for narrow AI-writing patterns and revise from its feedback.
When should I use Jev Prose?
Jev Prose fits situations like: asked for Jev prose checks; AI-pattern cleanup; an ongoing check-and-rewrite loop while writing sentences.
How do I install Jev Prose in Claude Code?
Run `npx skills add pchalasani/claude-code-tools --skill jev-prose -a claude-code`. Or copy the skill folder (packages/jev-prose/src/jev_prose in pchalasani/claude-code-tools) into .claude/skills/jev-prose in your project. Claude Code loads it when a task matches its description.
How do I install Jev Prose in Codex?
Run `npx skills add pchalasani/claude-code-tools --skill jev-prose -a codex`. Or copy the skill folder (packages/jev-prose/src/jev_prose in pchalasani/claude-code-tools) into .agents/skills/jev-prose in your project. Codex loads it when a task matches its description.
Can I use Jev Prose 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 pchalasani/claude-code-tools --skill jev-prose -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jev-prose, .gemini/skills/jev-prose, .github/skills/jev-prose and .opencode/skills/jev-prose in your project.
What does Jev Prose need to run?
Going by SKILL.md and its folder, Jev Prose needs Python for the scripts in its folder, the command-line tools its instructions call (uv) and credentials named CLOUDFLARE_API_TOKEN. Our summary lists: Python 3; A credential in CLOUDFLARE_API_TOKEN.
Does Jev Prose access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Jev Prose 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 Jev Prose use?
Jev Prose 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 Jev Prose use?
About 1.1k tokens (SKILL.md is roughly 4.3k 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 Jev Prose?
Skills that share tags, products or a category with Jev Prose: Humanizer (Azure-Samples/interview-coach-agent-framework, 173 stars), Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars), User-Facing Text Cleanup (guillaumemeyer/watermarks-remover, 24k stars) and Install Anti Slop (trycompai/crm, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Jev Prose?
pchalasani (a GitHub user) maintains it in pchalasani/claude-code-tools, which has 2,012 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 9, 2026.
Source: pchalasani/claude-code-tools on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.