一键导入
agenticskills
">"
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
">"
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | agenticskills |
| description | > |
| compatibility | > |
| allowed-tools | Bash Read Write Edit Glob Grep WebFetch |
| metadata | {"tags":"agenticskills, oh-my-gods, god-skills, installer, bundle, agent-skills, multi-runtime","keyword":"agenticskills","version":"1.0.0","upstream":"https://github.com/akillness/oh-my-gods","installer":"https://raw.githubusercontent.com/akillness/oh-my-gods/main/install.sh"} |
Keywords:
AgenticSkills·agenticskills·oh-my-gods·god-skillsUse this skill when the user wants to drop the entire oh-my-gods bundle (80+ curated agent skills) onto their machine without picking each one individually.
This skill is a thin, declarative wrapper around the official install.sh
that ships with akillness/oh-my-gods.
It pins the installer URL, exposes the canonical environment knobs, and
documents how to target a subset of runtimes from a single command.
SKIP_BACKUP=true).WITH_LANGCHAIN=true)..god-skills/<name>/ directory instead, or use npx skills add with
--skill <name>.curl | bash) — fall back
to git clone + manual review.Before running the installer, confirm:
claude, codex, gemini, opencode, or all (default).WITH_LANGCHAIN=true) or not.~/.agent-skills backup (default) or skip.Pipe the upstream installer through bash with the chosen knobs:
# Default: install everything across every detected runtime, backup previous install
curl -fsSL https://raw.githubusercontent.com/akillness/oh-my-gods/main/install.sh | bash
# Claude Code only, with LangChain skills
PLATFORM=claude WITH_LANGCHAIN=true \
curl -fsSL https://raw.githubusercontent.com/akillness/oh-my-gods/main/install.sh | bash
# Quiet re-install without backup (CI / scripted use)
INSTALL_MODE=silent SKIP_BACKUP=true \
curl -fsSL https://raw.githubusercontent.com/akillness/oh-my-gods/main/install.sh | bash
For a security-conscious flow, download, review, then run:
curl -fsSLO https://raw.githubusercontent.com/akillness/oh-my-gods/main/install.sh
less install.sh # human review
bash install.sh
ls ~/.agent-skills | head
ls ~/.claude/skills 2>/dev/null | head
ls ~/.codex/skills 2>/dev/null | head
ls ~/.gemini/skills 2>/dev/null | head
ls ~/.opencode/skills 2>/dev/null | head
You should see directories such as agent-browser, agent-workflow,
agentation, ai-research-skills, api-design, and the rest of the
.god-skills/ catalog mirrored into each detected runtime.
The installer is idempotent. To refresh:
curl -fsSL https://raw.githubusercontent.com/akillness/oh-my-gods/main/install.sh | bash
A backup of the previous ~/.agent-skills is written next to the directory
unless SKIP_BACKUP=true is set.
| Variable | Default | Purpose |
|---|---|---|
INSTALL_GLOBAL | true | Install to canonical ~/.agent-skills |
INSTALL_MODE | silent | silent · auto · interactive |
SKIP_BACKUP | false | Skip backup of an existing install |
WITH_LANGCHAIN | false | Also install langchain-ai/langchain-skills |
PLATFORM | all | claude · gemini · codex · opencode · all |
oh-my-gods currently ships 80+ skills under .god-skills/, including:
agent-browser, agentation, agent-configuration, agent-development-principlesagent-evaluation, agent-manager, agent-principles, agent-workflowagents-cli, ai-research-skills, api-design, api-documentationSee oh-my-gods tree for the full list at any time.
curl | bash when the user has a security policy.main in the
installer URL with a tag or commit SHA.akillness/jeo-skills; there are no destructive
overlaps as the destination namespaces differ.README.md → Infrastructure tableAssist with Colibri: pure-C LLM inference engine for running GLM-5.2 (744B MoE) on consumer machines with ~25 GB RAM. Use when setting up, building, converting models, running inference, configuring expert streaming and caching, optimizing speculative decoding (MTP), GPU integration, and integrating Colibri into production pipelines. Includes build setup, model download & conversion, chat/inference modes, performance tuning, and API integration patterns.
Discover and apply curated prompts from the prompts.chat collection to optimize AI interactions. Use when refining prompt engineering, finding domain-specific prompt templates, improving response quality, or building prompt-based workflows. Triggers on: prompt optimization, prompt templates, prompt engineering, prompt library, curated prompts, prompt discovery, and AI prompt patterns.
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage", a narrated explainer or short ad built from AI-generated collage posters, a scrapbook-style tribute, or wants to turn a topic / product / person into a punchy narrated collage video — even if they don't say the word "Vox". Also use when reproducing Stav Zilber / rom1trs / Higgsfield-style collage ad workflows, or when the user asks for a motion collage or a scrapbook-style tribute. Triggers: "vox video", "collage video", "motion collage", "paper collage explainer", "make a collage ad", "turn this topic into a collage video".
Assist with Motion Previs Studio v4: a cross-platform desktop app for AI-film previsualization. Use when setting up, configuring, troubleshooting, or extending motion-previs-studio for pose extraction, depth mapping, camera motion solving, control layer export, and bundle production for AI-video workflows (Seedance, ComfyUI, Blender, Runway, Kling). Includes build setup, feature integration, UI/logic debugging, and export pipeline optimization.
Work with Lapian Notes / 拉片笔记 (github.com/bkingfilm/lapian-notes) — a local- first React/Vite tool that turns a film into an editable shot-by-shot study notebook: local frame extraction, AI-assisted structure analysis (bring your own AI, no API key required), story-line swimlane timeline, structure tree, and audience-emotion curve. Use when the user asks about Lapian Notes, "拉片笔记", "拉片" (shot-by-shot film analysis) tooling, cloning/running this repo (npm run dev, run.bat/run.command), the AI-analysis-package (ZIP) round-trip workflow, or contributing a PR to lapian-notes. Not for generic video editing (use `opencut` for that) or generic film-analysis theory unrelated to this codebase.
Set up, run, and contribute to TokHub (github.com/yaojingang/TokHub) — an open-source AI API relay monitoring, recommendation, and OpenAI-compatible gateway system with L1/L2/L3 channel health probing, usage metering, alerts, audit, and Docker self-hosting. Use when the user asks about TokHub, "AI API 中转站监控", cloning/running the Go + React monorepo (TOKHUB_ROLE, sqlc, TimescaleDB, NATS), the L1/L2/L3 probe algorithm, the OpenAI-compatible `/gateway/v1/*` endpoint, or contributing a PR to TokHub. Do not use for connecting a running agent to a live TokHub instance's own API (that is covered by the project's own bundled `agent-skills/tokhub` skill inside the TokHub repo, not this one).