Character Lora
Use when the user wants to build a consistent-identity LoRA for an original character — defining the character, generating a face/body-consistent multi-angle dataset (via the gpt-image-gen skill for codex image generation), captioning it, doing base-specific homework, training on a chosen base (Pony / Z-Image / others) on a local GPU, and producing a usable LoRA. This skill ORCHESTRATES the end-to-end pipeline and gates every expensive/irreversible step; it delegates actual image generation to gpt-image-gen and never improvises training settings from memory.
Install
npx skills add KerberosClaw/kc_ai_skills --skill character-loragit clone --depth 1 https://github.com/KerberosClaw/kc_ai_skills.git /tmp/kc_ai_skills
mkdir -p ~/.claude/skills
cp -r /tmp/kc_ai_skills/character-lora ~/.claude/skills/character-loraPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# character-lora You are a **character-LoRA pipeline orchestrator**. You take an original character from "an idea + a reference look" to a trained, usable LoRA that reproduces its identity across angles, framings and scenes. You drive a multi-stage pipeline, **delegate image generation to the `gpt-image-gen` skill**, **gate every expensive / irreversible step on explicit user approval**, and **never improvise training settings from memory** — you do the base-specific homework first. > 完整方法論(每 stage 的 why、決策樹、per-base 配方知識、完整失敗對策)在同目錄 **`playbook.md`**。本檔是操作骨架。 ## 🔴 Red lines(即使讀過下面 step 也別忘) 1. **MANDATORY:跑任何新 base 的訓練前,先讀該 base 的官方訓練文件 + 社群討論** — caption 規範 / trigger 命名 / 蒸餾(Turbo)變體 vs 完整版的訓練差異 / 環境依賴。憑印象配參數 = 角色「抽籤」/ 飄。 2. **沒驗證的不寫進 playbook/recipe** — 設定要實跑驗過才當「配方」;沒測的標 `proposed / 待驗`。 3. **生圖 / 訓練 = 花 user 的錢與算力 → 先拿明確 go 才跑**(pilot 給看 → OK 才整批;訓練前報設定)。**不要自己上 API key**。 4. **LoRA 綁架構** — train base family = infer base family,絕不跨(Pony LoRA ≠ Z-Image LoRA,互不相容)。 5. **標「會變」、留「identity」** — caption 只標可變(場景/角度/服裝/toggle 配件);臉/體型/招牌特徵留白 → 烤進 trigger word。 ## 圖生成(單張 delegate / 批量自跑 / 本機自生) - **單張(定版 Stage 1b、sheet Stage 2)→ 走 `gpt-image-gen` skill**(互動擬 prompt + 單張拍板 + codex text2img/img2img)。⚠️ **明確要它保留無損 PNG** — gpt-image-gen 預設交 jpg q85 且刪 png,但訓練/canonical 要 PNG,delegate 時講「留無損 png」。
Details
- Skill name
character-lora- Repository
- KerberosClaw/kc_ai_skills
- Path
character-lora/SKILL.md- License
- MIT
- Repo updated
- 14 November 2026
- Listed in
- BehiSecc/awesome-claude-skills
FAQ
What does the Character Lora skill do?
Use when the user wants to build a consistent-identity LoRA for an original character — defining the character, generating a face/body-consistent multi-angle dataset (via the gpt-image-gen skill for codex image generation), captioning it, doing base-specific homework, training on a chosen base (Pony / Z-Image / others) on a local GPU, and producing a usable LoRA. This skill ORCHESTRATES the end-to-end pipeline and gates every expensive/irreversible step; it delegates actual image generation to gpt-image-gen and never improvises training settings from memory.
How do I install the Character Lora skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add KerberosClaw/kc_ai_skills --skill character-lora. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Character Lora popular?
It lives in KerberosClaw/kc_ai_skills, which has 80 GitHub stars and 13 forks, and is included in 1 curated skill list.
Related skills
Adr
80KerberosClaw/kc_ai_skills
Use when a durable technical decision was just made in conversation and should be recorded, or when user asks to write/record an ADR (開 ADR / 記個決策 / 這要不要 ADR). Runs a three-gate check FIRST and actively talks the user out of writing one when the decision doesn't qualify — then writes a lightweight (title + 1-3 sentences) ADR following the repo's own ADR conventions if any exist. Repo conventions always override this skill's defaults. NOT for requirement specs (spec / prd-create) or rewriting historical decisions; preserve their text, allow evidence-backed current-state notes, and record change
Align
80KerberosClaw/kc_ai_skills
Reconcile existing repository documentation with the current implementation, especially after verified hotfixes or after QA in an unattended task. A manual run first asks whether to align only the docs a specific change touched (trigger scope) or rescan the whole repo; unattended runs use the scope the dispatch states and default to the whole repo. Follow cross-repo references for evidence; edit only documentation in the authorized repo, annotating conflicting historical records. Not for fixing code, deploying, inventing requirements, or building a new documentation suite.
Conference Report
80KerberosClaw/kc_ai_skills
Use when the user attended one or more sessions of a conference (with audio recordings + slide photos) and needs help building (1) faithful per-session reconstructions in markdown (slide visuals + speaker transcript with Whisper hallucination annotations), and (2) a downstream report deliverable whose scope and format are decided interactively with the user. Pipeline phase (raw → mlx_whisper Chinese SRT → per-slide multimodal reconstruction → official agenda cross-check via Playwright if available) is deterministic. Report phase is interactive — always quiz user on scope (single-session / sing
Gpt Image Gen
80KerberosClaw/kc_ai_skills
Use when the user asks to generate OR edit an image via GPT/Codex (e.g. 「叫 gpt 生圖」「幫我用 gpt 生圖」「gpt 畫一個 X」「幫我去背」「把這張圖的背景去掉」). The skill drafts a Chinese + English prompt pair and waits for explicit approval. After approval it uses the host-native executor: Codex calls its built-in image_gen tool directly, while Claude Code keeps the Codex CLI background workflow. Supports text-to-image, img2img, and precise EDIT mode with preservation constraints and verification where local artifacts are available.
Video Catcher
49Weikezi-AI/video-catcher
当用户要求下载视频、保存网页中的视频、下载 mp4/m3u8/mpd、下载 YouTube/Bilibili/抖音/TikTok/X/Instagram 等平台视频、批量下载视频、下载字幕/封面、检查网页中有哪些媒体资源、查看视频有哪些可下载清晰度、指定 360p/720p/1080p/2K/4K 清晰度、继续中断的视频下载时使用。面向 Codex、Claude Code 等本地 Agent:用户只需提供链接和目标,skill 自动执行 yt-dlp、YouTube PO Token Provider、浏览器指纹重试、静态发现、隔离持久浏览器网络嗅探、请求上下文继承、音视频合并、DRM 检查、断点续传、验证与报告;默认不依赖用户正在运行的 Chrome/Edge Cookie 数据库,也不在下载过程中要求用户选择技术路线。
Searxng
80KerberosClaw/kc_ai_skills
Use when the user wants privacy-respecting web, image, news, or video search through a configured local SearXNG instance instead of external search APIs. Calls the bundled script against SEARXNG_URL, supports result limits/categories/language/time range, and can return human-readable or JSON output. NOT for searches when no SearXNG instance is configured or when authenticated/private data retrieval is required.
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.