Nsfw Prompt

Explicit-only local skill. Invoke with $nsfw-prompt. Compile adult NSFW image prompts for online generators (Grok Imagine first) and local stacks (Flux, Pony, Illustrious, SDXL, Z-Image); Chinese briefing, English prompts.

19 stars 5 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add haremank/nsfw-prompt --skill nsfw-prompt

Manual install

git clone --depth 1 https://github.com/haremank/nsfw-prompt.git /tmp/nsfw-prompt
mkdir -p ~/.claude/skills
cp -r /tmp/nsfw-prompt/. ~/.claude/skills/nsfw-prompt

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# NSFW Prompt Compiler

Compile the user's adult image-generation request into copy-paste English prompts. Do not generate images. Do not call image APIs.

Independent audit (2026-09): this skill is an **online-first compiler**, not a filter-bypass tutor. Three legal floors remain. Compiler-side refusals that were not legal floors (jailbreak phrasing as a fourth floor, closed-platform compile bans, Grok L6–L8 as separate user-facing rungs) are removed. Do not emit instruction-override payloads; do compile the image.

## Safety

Full floor definitions: [safety](references/00-safety.md). **Three floors are the only refusals** (detailed below): minors (child anatomy refuses regardless of stated age; youthful adult features and petite adults are allowed), real private individuals, non-consensual sexual violence. School uniforms are adult roleplay only (`age=adult, 18+`). Online-model self-censor (mosaic, covering hands) is an engineering problem: [uncensor](references/12-uncensor.md) for local stacks, Grok L4/L5 literary shapes for hosted spicy lanes. Closed platforms (MJ/DALL-E/GPT-image): still compile; use the Grok L4/L5 online shape, plus a one-line compatibility note — no jailbreak, no refuse-to-compile.

## Workflow

1. Parse intent into the IR. Read [intent](references/07-intent.md) when the request is Chinese, elliptical, or is an edit of an existing prompt. Read [IR](references/01-ir.md) for required fields, defaults, and the conflict table.

Read the full skill on GitHub

Details

Skill name: nsfw-prompt
Repository: haremank/nsfw-prompt
License: MIT
Repo updated: 2 September 2026

FAQ

What does the Nsfw Prompt skill do?

How do I install the Nsfw Prompt skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add haremank/nsfw-prompt --skill nsfw-prompt. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Nsfw Prompt popular?

It lives in haremank/nsfw-prompt, which has 19 GitHub stars and 5 forks.

Related skills

LLM Council

gestordeaudiencia/llm-council-skill-ptbr

Passa qualquer pergunta, ideia ou decisão por um conselho de 5 conselheiros de IA que analisam de forma independente, fazem revisão por pares anonimamente, e sintetizam um veredito final. Baseado na metodologia LLM Council do Karpathy. GATILHOS OBRIGATÓRIOS (PT-BR): 'convoca o conselho', 'roda o conselho', 'leva pro conselho', 'submete ao conselho', 'war room isto', 'stress-test isto', 'pressure-test isto', 'debate isto'. GATILHOS OBRIGATÓRIOS (inglês): 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. GATILHOS FORTES (use quando combi

AI, LLMs & Agents

Bulus Amazon Skill

buluslan/bulus-amazon-skill

由buluslan（公众号:新西楼.AI）研发的亚马逊运营全流程 Skill：13 个场景提示词覆盖市场调研、选品、竞品拆解、关键词库、Listing 生成、图片规划、广告打法、复盘诊断、竞品监控全链路，数据源中立（接任意数据 MCP），每步产出分档结论+可执行动作清单，不是数据罗列。 13 prompt workflows covering the full Amazon operating lifecycle — market research, product selection, competitor teardown, keyword library, listing generation, image planning, ad strategy and review — data-source agnostic, each ending with tiered conclusions and action checklists. Trigger whenever the user mentions 亚马逊运营、选品、市场调研、类目分析、竞品分析、关键词库、Listing 生成、图片规划、广告打法、广告复盘、评论复盘、竞品监控、从零到一跑全流程 — in any language; 中文用户说"帮我做市场体检/验证趋势/挖细分/拆竞品/建词库/写 Listing/开广告/

AI, LLMs & Agents

Opencode

pcx-wave/opencode-skill

Delegate a coding task to OpenCode CLI and supervise the result via git diff. Trigger: /opencode <instruction>. Claude orchestrates, OpenCode codes. Also handles /opencodeon, /opencodeoff, /opencodestatus, /opencode-report, /opencode-model-pick, /opencode-model-clear.

AI, LLMs & Agents

生成求职文档

Shilren/interview-doc-agent

产品经理（及泛求职）面试场景，根据模板风格 + 经历库，生成简历、面试逐字稿，并支持按目标岗位 JD 定制。借鉴 Karpathy 的 LLM Wiki 模式：原始素材先整理成完善的「经历库」，生成时先查索引定位、再只读相关档案，以节省 token 并保证质量。经历库是生成的主来源。

AI, LLMs & Agents

Tag

1756141021/tag-skill

AI 绘画 TAG/prompt 创作。用于画面描述、OC 标签化、旧提示词调整和出图偏差修正；不用于代码标签或非绘画任务。

AI, LLMs & Agents

Xianyu Monitor

LENKIN233/xianyu-monitor-skill

Search and monitor Xianyu/Goofish listings with filters, deduplication, and optional AI ranking. Use for searches, login, item analysis, and recurring alerts on 闲鱼 / Goofish.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.