Agent skill

Bridgic LLMs

LLM provider initialization for bridgic projects. An agent skill from bitsky-tech/bridgic.

MITAuto-check: notesAI & LLM Engineering

Install Bridgic LLMs

skills CLI

$ npx skills add bitsky-tech/bridgic --skill bridgic-llms -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install bitsky-tech/bridgic bridgic-llms --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/bitsky-tech/bridgic.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/bridgic-llms .claude/skills/bridgic-llms && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "bridgic-llms" agent skill from https://github.com/bitsky-tech/bridgic/tree/main/skills/bridgic-llms into .claude/skills/bridgic-llms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bridgic-llms", 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

$skill-installer install https://github.com/bitsky-tech/bridgic/tree/main/skills/bridgic-llms

Type 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.

skills CLI

$ npx skills add bitsky-tech/bridgic --skill bridgic-llms -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install bitsky-tech/bridgic bridgic-llms --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/bitsky-tech/bridgic.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/bridgic-llms .agents/skills/bridgic-llms && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "bridgic-llms" agent skill from https://github.com/bitsky-tech/bridgic/tree/main/skills/bridgic-llms into .agents/skills/bridgic-llms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bridgic-llms", 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.

skills CLI

$ npx skills add bitsky-tech/bridgic --skill bridgic-llms -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install bitsky-tech/bridgic bridgic-llms --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/bitsky-tech/bridgic.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/bridgic-llms .cursor/skills/bridgic-llms && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "bridgic-llms" agent skill from https://github.com/bitsky-tech/bridgic/tree/main/skills/bridgic-llms into .cursor/skills/bridgic-llms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bridgic-llms", 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

$ gemini skills install https://github.com/bitsky-tech/bridgic.git --path skills/bridgic-llms

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add bitsky-tech/bridgic --skill bridgic-llms -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install bitsky-tech/bridgic bridgic-llms --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/bitsky-tech/bridgic.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/bridgic-llms .gemini/skills/bridgic-llms && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "bridgic-llms" agent skill from https://github.com/bitsky-tech/bridgic/tree/main/skills/bridgic-llms into .gemini/skills/bridgic-llms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bridgic-llms", 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.

GitHub CLI

$ gh skill install bitsky-tech/bridgic bridgic-llms

Installs 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).

skills CLI

$ npx skills add bitsky-tech/bridgic --skill bridgic-llms -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/bitsky-tech/bridgic.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/bridgic-llms .github/skills/bridgic-llms && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "bridgic-llms" agent skill from https://github.com/bitsky-tech/bridgic/tree/main/skills/bridgic-llms into .github/skills/bridgic-llms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bridgic-llms", 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.

skills CLI

$ npx skills add bitsky-tech/bridgic --skill bridgic-llms -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install bitsky-tech/bridgic bridgic-llms --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/bitsky-tech/bridgic.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/bridgic-llms .opencode/skills/bridgic-llms && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "bridgic-llms" agent skill from https://github.com/bitsky-tech/bridgic/tree/main/skills/bridgic-llms into .opencode/skills/bridgic-llms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bridgic-llms", 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: bridgic-llms
GitHub stars: 155
Token cost: ~839 tokens
SKILL.md length: 213 words
Files: 6 (incl. scripts, references)
Skills in repo: 1
Repo updated: Aug 4, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

LLM provider initialization for bridgic projects. An agent skill from bitsky-tech/bridgic.

Initializing OpenAILlm
SKILL.md covers Dependencies, Quick Start, Provider Selection Guide and Basic Interfaces, plus 2 more sections
Runs Shell scripts from its folder; calls uv and bash; needs LLM_API_KEY
Configuring OpenAIConfiguration (model

What it does

Bridgic LLMs is an agent skill from bitsky-tech/bridgic. LLM provider initialization for bridgic projects. Use when: (1) initializing OpenAILlm, OpenAILikeLlm, or VllmServerLlm, (2) configuring OpenAIConfiguration (model, temperature, maxtokens, timeout), (3) choosing the right provider package for a task, (4) using chat/stream interfaces or advanced protocols (StructuredOutput, ToolSelection).

Its SKILL.md is about 840 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `references/llm-integration.md` and `scripts/install-deps.sh`).

It sits in AI & LLM Engineering, covering Structured output and tool calling. It works with OpenAI, Python, DeepSeek and Google Gemini. The repository describes itself as: Bridgic is the next-generation agent development framework for building intelligent systems. The licence is MIT.

When your agent uses it

Initializing OpenAILlm
Configuring OpenAIConfiguration (model
Choosing the right provider package for a task
Using chat/stream interfaces

Example prompts

“/bridgic-llms”

Requirements

Python 3
A Bash shell
A credential in LLM_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 2cca118. 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 4 files in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
- uv
- bash
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:
- LLM_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bridgic LLMs loads about 839 tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 89 tokens; SKILL.md has 213 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~89
When it runs · the whole SKILL.md, loaded when a task matches: ~839
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~2k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NoteMentions a .env fileSKILL.md:24

`python-dotenv` is required for loading `.env` configuration.

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); the scripts in this folder are not scanned.

SKILL.md

The full file from bitsky-tech/bridgic at commit 2cca118, republished under its MIT licence (© bitsky-tech). 213 words, ~839 tokens.

Download SKILL.mdSave it as .claude/skills/bridgic-llms/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.

name: bridgic-llms
description: LLM provider initialization for bridgic projects. Use when: (1) initializing OpenAILlm, OpenAILikeLlm, or VllmServerLlm, (2) configuring OpenAIConfiguration (model, temperature, max_tokens, timeout), (3) choosing the right provider package for a task, (4) using chat/stream interfaces or advanced protocols (StructuredOutput, ToolSelection).

Bridgic LLMs

Model-neutral LLM integration with protocol-driven capability declaration.

Dependencies

Package	`BaseLlm`	`StructuredOutput`	`ToolSelection`
`bridgic-llms-openai`	yes	yes	yes
`bridgic-llms-openai-like`	yes	no	no
`bridgic-llms-vllm`	yes	yes	yes
`python-dotenv`	—	—	—

Install only the LLM provider package you need. python-dotenv is required for loading .env configuration.

Installation: Run the install script to set up all dependencies:

bash

bash "skills/bridgic-llms/scripts/install-deps.sh" "$PWD" [PROVIDER]

Supported providers: openai (default), openai-like, vllm. The script checks uv availability, initializes a uv project if needed, installs any missing packages via uv add, and runs uv sync to finalize the environment. When it exits successfully the project is fully initialized and ready to use — no manual uv add / uv sync follow-up is required.

Quick Start

python

import os
from dotenv import load_dotenv
from bridgic.llms.openai import OpenAILlm, OpenAIConfiguration

load_dotenv()

llm = OpenAILlm(
    api_key=os.environ.get("LLM_API_KEY"),
    api_base=os.environ.get("LLM_API_BASE"),
    configuration=OpenAIConfiguration(
        model=os.environ.get("LLM_MODEL", "gpt-4o"),
        temperature=0.0,
        max_tokens=16384,
    ),
    timeout=180.0,
)

Provider Selection Guide

Provider	When to Use
`OpenAILlm`	Production use, need structured output or tool calling. Works with OpenAI API.
`OpenAILikeLlm`	Third-party OpenAI-compatible APIs (DashScope, etc.), only need basic chat/stream.
`VllmServerLlm`	Self-hosted vLLM inference server, full capability.

Common pitfall: Do NOT use OpenAILikeLlm when you need structured output or tool selection — it does not implement those protocols. Use OpenAILlm instead.

Basic Interfaces

All providers implement BaseLlm:

python

from bridgic.core.model.types import Message, Role

messages = [
    Message.from_text("You are a helpful assistant.", role=Role.SYSTEM),
    Message.from_text("Hello!", role=Role.USER),
]

# Chat — complete response
response = llm.chat(messages=messages, model="gpt-4o", temperature=0.7)
print(response.message.content)

# Stream — real-time chunks
for chunk in llm.stream(messages=messages, model="gpt-4o"):
    print(chunk.delta, end="", flush=True)

Advanced Protocols

See references/llm-integration.md for:

StructuredOutput — generate Pydantic model instances or JSON schema conformant output
ToolSelection — function/tool calling with Tool definitions
Full code examples for all providers

Reference Files

Scenario	Load
Full API details, all providers, advanced protocols	llm-integration.md

Files

SKILL.md and 5 other files (scripts, references) in skills/bridgic-llms of bitsky-tech/bridgic.

SKILL.md
references/llm-integration.md
scripts/deps.openai-like.ini
scripts/deps.openai.ini
scripts/deps.vllm.ini
scripts/install-deps.sh

Open the folder on GitHubat commit 2cca118

Compare with similar skills

Bridgic LLMs 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.

Bridgic LLMs compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Bridgic LLMs this skillbitsky-tech/bridgic	155	—	~839	Automated safety check: Notes	MIT	2 mo ago
Mmsp PythonPrism-Shadow/model-message-stream-protocol	113	—	~1.4k	Automated safety check: Pass	Apache-2.0	4 days ago
Gemini Interactions APIAyuilos/Miffan	192	—	~4.6k	Automated safety check: Pass	AGPL-3.0	2 days ago
Mmsp DevPrism-Shadow/model-message-stream-protocol	113	—	~7.2k	Automated safety check: Pass	Apache-2.0	4 days ago
ModLens Image Vision Bridgeliustack/modlens	4.2k	1 repos	~1.3k	Automated safety check: Notes	MIT	4 days ago
Gemini API Devgoogle-gemini/gemini-skills	4.3k	—	~5.1k	Automated safety check: Pass	Apache-2.0	2 days ago

Similar skills

Mmsp Python
Prism-Shadow/model-message-stream-protocol
Guidance for using the MMSP Python SDK (mmsp). An agent skill from Prism-Shadow/model-message-stream-protocol.
113 GitHub stars~1.4k tokensUpdated 4 days ago
AI & LLM EngineeringAuto-check passed
Gemini Interactions API
Ayuilos/Miffan
A skill your agent uses when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, streaming responses…
192 GitHub stars~4.6k tokensUpdated 2 days ago
Media & CreativeAuto-check passed
Mmsp Dev
Prism-Shadow/model-message-stream-protocol
Fixed workflow for developing MMSP itself — adding or updating model support, and changing its pages.
113 GitHub stars~7.2k tokensUpdated 4 days ago
Testing & QAAuto-check passed
ModLens Image Vision Bridge
liustack/modlens
Gives text-only models sight by running the modlens CLI on an image path or URL and returning structured JSON evidence with transcribed text, layout and semantics.
4.2k GitHub starsUsed in 1 repo~1.3k tokens
AI & LLM EngineeringAuto-check: notes
Gemini API Dev
google-gemini/gemini-skills
Official
A skill your agent uses when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, speech generation (TTS), voice…
4.3k GitHub stars~5.1k tokensUpdated 2 days ago
AI & LLM EngineeringAuto-check passed
Embeddings via 9Router
decolua/9router
Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.
30k GitHub stars~604 tokensUpdated 7 days ago
AI & LLM EngineeringAuto-check passed

Works with

Questions about Bridgic LLMs

What does Bridgic LLMs do?

LLM provider initialization for bridgic projects. An agent skill from bitsky-tech/bridgic. Bridgic LLMs is an agent skill from bitsky-tech/bridgic. LLM provider initialization for bridgic projects.

When should I use Bridgic LLMs?

Bridgic LLMs fits situations like: initializing OpenAILlm; configuring OpenAIConfiguration (model; choosing the right provider package for a task; using chat/stream interfaces.

How do I install Bridgic LLMs in Claude Code?

Run `npx skills add bitsky-tech/bridgic --skill bridgic-llms -a claude-code`. Or copy the skill folder (skills/bridgic-llms in bitsky-tech/bridgic) into .claude/skills/bridgic-llms in your project. Claude Code loads it when a task matches its description.

How do I install Bridgic LLMs in Codex?

Run `npx skills add bitsky-tech/bridgic --skill bridgic-llms -a codex`. Or copy the skill folder (skills/bridgic-llms in bitsky-tech/bridgic) into .agents/skills/bridgic-llms in your project. Codex loads it when a task matches its description.

Can I use Bridgic LLMs 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 bitsky-tech/bridgic --skill bridgic-llms -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bridgic-llms, .gemini/skills/bridgic-llms, .github/skills/bridgic-llms and .opencode/skills/bridgic-llms in your project.

What does Bridgic LLMs need to run?

Going by SKILL.md and its folder, Bridgic LLMs needs a shell for the scripts in its folder, the command-line tools its instructions call (uv and bash) and credentials named LLM_API_KEY. Our summary lists: Python 3; A Bash shell; A credential in LLM_API_KEY.

Does Bridgic LLMs 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 Bridgic LLMs safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Bridgic LLMs use?

Bridgic LLMs 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 Bridgic LLMs use?

About 839 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Bridgic LLMs?

Skills that share tags, products or a category with Bridgic LLMs: Mmsp Python (Prism-Shadow/model-message-stream-protocol, 113 stars), Gemini Interactions API (Ayuilos/Miffan, 192 stars), Mmsp Dev (Prism-Shadow/model-message-stream-protocol, 113 stars) and ModLens Image Vision Bridge (liustack/modlens, 4.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bridgic LLMs?

bitsky-tech (a GitHub organization) maintains it in bitsky-tech/bridgic, which has 155 GitHub stars. The repository was last updated on August 4, 2026.

Source: bitsky-tech/bridgic on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Bridgic LLMs

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Bridgic LLMs

Dependencies

Quick Start

Provider Selection Guide

Basic Interfaces

Advanced Protocols

Reference Files

Files

Compare with similar skills

Similar skills

Mmsp Python

Gemini Interactions API

Mmsp Dev

ModLens Image Vision Bridge

Gemini API Dev

Embeddings via 9Router

Related

Questions about Bridgic LLMs