Sap Cloud SDK AI
secondsky/sap-skills
Integrates SAP Cloud SDK for AI into JavaScript/TypeScript and Java applications.
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…
Install Agents And Middleware
$ npx skills add VectorSpaceLab/AREX-Skill --skill agents-and-middleware -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill agents-and-middleware --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/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware .claude/skills/agents-and-middleware && 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 "agents-and-middleware" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware into .claude/skills/agents-and-middleware/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-and-middleware", 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/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/langchain/sub-skills/agents-and-middlewareType 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 VectorSpaceLab/AREX-Skill --skill agents-and-middleware -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill agents-and-middleware --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware .agents/skills/agents-and-middleware && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agents-and-middleware" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware into .agents/skills/agents-and-middleware/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-and-middleware", 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 VectorSpaceLab/AREX-Skill --skill agents-and-middleware -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill agents-and-middleware --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware .cursor/skills/agents-and-middleware && 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 "agents-and-middleware" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware into .cursor/skills/agents-and-middleware/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-and-middleware", 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/VectorSpaceLab/AREX-Skill.git --path skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware--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 VectorSpaceLab/AREX-Skill --skill agents-and-middleware -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill agents-and-middleware --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware .gemini/skills/agents-and-middleware && 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 "agents-and-middleware" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware into .gemini/skills/agents-and-middleware/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-and-middleware", 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 VectorSpaceLab/AREX-Skill agents-and-middlewareInstalls 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 VectorSpaceLab/AREX-Skill --skill agents-and-middleware -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware .github/skills/agents-and-middleware && 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 "agents-and-middleware" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware into .github/skills/agents-and-middleware/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-and-middleware", 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 VectorSpaceLab/AREX-Skill --skill agents-and-middleware -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill agents-and-middleware --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware .opencode/skills/agents-and-middleware && 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 "agents-and-middleware" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware into .opencode/skills/agents-and-middleware/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-and-middleware", 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
agents-and-middleware- GitHub stars
- 330
- Token cost
- ~1.2k tokens
- SKILL.md length
- 463 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 159
- Repo updated
- First seen
- Licence
- MIT
At a glance
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…
- Works in 5 steps: Confirm the target package is… → Inspect the nearest v1 public API files… → Prefer tests under… → …
- Libs/langchainv1 agent workflows and route low-level core primitives
- SKILL.md covers When to Use, Route Elsewhere, Reference Map and Fast Workflow, plus 2 more sections
- Runs Python scripts from its folder; calls uv and python
What it does
Agents And Middleware is an agent skill from VectorSpaceLab/AREX-Skill. Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime customization. Use for libs/langchainv1 agent workflows and route low-level core primitives or provider implementation details to sibling skills.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/agent-workflows.md`, `references/middleware-reference.md` and `references/troubleshooting.md`).
It sits in AI & LLM Engineering, covering Building AI agents, Embeddings and Structured output and tool calling. It works with LangChain. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is MIT.
When your agent uses it
- Libs/langchainv1 agent workflows and route low-level core primitives
- Provider implementation details to sibling skills
Example prompts
- “/agents-and-middleware”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Confirm the target package is libs/langchain_v1; its distribution name is langchain and its package imports are langchain.*.
- Inspect the nearest v1 public API files first: langchain/chat_models/base.py, langchain/agents/factory.py…
- Prefer tests under tests/unit_tests/agents, tests/unit_tests/chat_models, tests/unit_tests/tools, and tests/unit_tests/embeddings for…
- For package validation, use uv from libs/langchain_v1; do not use pip, poetry, or conda directly for this monorepo.
- Skip network-backed model invocations unless credentials, provider packages, and user permission are present; use fake models or import…
What it can do on your machine
Read from SKILL.md and the folder at commit ac3fe1a. 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 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
uvpython
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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Agents And Middleware loads about 1.2k tokens when it runs, and up to ~9.8k if it reads all its reference files. Until then it costs about 90 tokens; SKILL.md has 463 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); the scripts in this folder are not scanned.
SKILL.md
The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its MIT licence (© VectorSpaceLab). 463 words, ~1,225 tokens.
Download SKILL.mdSave it as
.claude/skills/agents-and-middleware/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- agents-and-middleware
- description
- Work on the actively maintained LangChain v1 agent package: init_chat_model, create_agent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime customization. Use for libs/langchain_v1 agent workflows and route low-level core primitives or provider implementation details to sibling skills.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- MIT
Agents and Middleware
Use this sub-skill for practical work in the actively maintained langchain package around v1 agents, middleware, model initialization, structured output, tools, and embeddings. This guidance is distilled from the LangChain v1 source and tests and is self-contained for future coding agents.
When to Use
- User asks about
init_chat_model,create_agent,response_format, tool schemas, injected tool runtime, or configurable chat models. - User asks to add, configure, or debug middleware such as retry, fallback, human-in-the-loop, summarization, tool/model call limits, PII redaction, file search, shell execution, todo planning, provider tool search, tool retry, or tool selection.
- User asks why provider resolution fails for a chat or embedding model, especially when optional integration packages or credentials are missing.
- User asks to customize agent state, runtime context, checkpointer/store usage, interrupts, streaming, or debug behavior at the
langchainv1 layer.
Route Elsewhere
- For low-level runnable, message, tool, callback, language-model, or embedding primitives from
langchain_core, use../core-primitives/SKILL.md. - For provider implementation packages such as
langchain-openai,langchain-anthropic,langchain-ollama, or provider-specific parameters/classes, use../integrations/SKILL.md. - For legacy
langchain-classicimports, chains, retrievers, or classic agents, use the sibling skill that owns classic APIs instead of rewriting v1 guidance.
Reference Map
- Start with references/agent-workflows.md for source layout, import paths, common edit workflows, validation commands, structured output, tools, embeddings, and provider initialization.
- Use references/middleware-reference.md for middleware families, exported classes, hook styles, ordering, state/context patterns, and safety constraints.
- Use references/troubleshooting.md for missing provider packages, credentials/network skips, structured output/tool validation, middleware ordering, HITL/shell/file-search safety, and v1-vs-classic confusion.
- Run scripts/agent_import_smoke.py as a safe import-only smoke check when an environment is available.
Show full SKILL.md (207 more words)Show less
Fast Workflow
- Confirm the target package is
libs/langchain_v1; its distribution name islangchainand its package imports arelangchain.*. - Inspect the nearest v1 public API files first:
langchain/chat_models/base.py,langchain/agents/factory.py,langchain/agents/structured_output.py,langchain/agents/middleware/,langchain/tools/, andlangchain/embeddings/base.py. - Prefer tests under
tests/unit_tests/agents,tests/unit_tests/chat_models,tests/unit_tests/tools, andtests/unit_tests/embeddingsfor expected public behavior. - For package validation, use
uvfromlibs/langchain_v1; do not usepip,poetry, orcondadirectly for this monorepo. - Skip network-backed model invocations unless credentials, provider packages, and user permission are present; use fake models or import checks for local validation.
Safe Validation
From libs/langchain_v1, use targeted package tests when uv is available:
uv run --group test pytest tests/unit_tests/chat_models/test_chat_models.py tests/unit_tests/agents/test_response_format.py tests/unit_tests/tools/test_imports.py tests/unit_tests/embeddings/test_base.pyFrom this sub-skill directory, use the bundled smoke script with any Python environment that already has langchain installed:
python scripts/agent_import_smoke.pyThe smoke script imports public APIs only and does not call providers, networks, shell commands, or external files.
Guardrails
- Keep v1 import paths explicit:
langchain.chat_models,langchain.agents,langchain.agents.middleware,langchain.tools, andlangchain.embeddings. - Do not add provider-specific hard dependencies to
langchaincore code unless the package metadata intentionally lists them as optional extras. - Do not run shell/file-search/HITL examples as unattended validation; these require user-reviewed safety decisions.
- Do not link future runtime instructions to source-checkout docs, examples, tests, or absolute local paths; distill facts into this sub-skill or bundled references.
© VectorSpaceLab, 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 4 other files (scripts, references) in skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/agent-workflows.md
- references/middleware-reference.md
- references/troubleshooting.md
- scripts/agent_import_smoke.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Agents And Middleware 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 |
|---|---|---|---|---|---|---|
| Agents And Middleware this skillVectorSpaceLab/AREX-Skill | 330 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Sap Cloud SDK AIsecondsky/sap-skills | 462 | — | ~3.2k | Automated safety check: Pass | GPL-3.0 | |
| Routerbase Model Routingaiskillstore/marketplace | 430 | — | ~964 | Automated safety check: Pass | None | |
| AI SDKvercel-labs/ai-facts | 168 | 20 repos | ~1.2k | Automated safety check: Pass | None | |
| Llmobs IntegrationDataDog/dd-trace-js | 837 | — | ~1.4k | Automated safety check: Pass | Custom licence | |
| LangGraph Decision Modelslangchain-ai/langchain-skills | 1.3k | — | ~2.3k | Automated safety check: Pass | MIT |
Similar skills
Routerbase Model Routing
aiskillstore/marketplace
Choose RouterBase model IDs and routing strategies for chat, image, video, audio, and embeddings workloads.
- Official
AI SDK
vercel-labs/ai-facts
Answer questions about the AI SDK and help build AI-powered features.
- Official
Llmobs Integration
DataDog/dd-trace-js
A skill your agent uses when adding, debugging, or modifying LLMObs plugins for an LLM library in dd-trace-js.
- Official
LangGraph Decision Models
langchain-ai/langchain-skills
Routes LangGraph agents with typed decision models that return probabilities, and finds LLM calls that only exist to produce a routing decision.
Tool Design
agentailor/fullstack-langgraph-nextjs-agent
Design and verify tools that AI agents can actually use — for any framework or language (MCP servers, LangChain/LangGraph, function-calling, raw JSON schema; TypeScript, Python, or otherwise).
More from VectorSpaceLab/AREX-Skill
All 159 skills in this repoAgent Lightning
VectorSpaceLab/AREX-Skill
Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…
Agent Tools
VectorSpaceLab/AREX-Skill
A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…
Agents And Awel
VectorSpaceLab/AREX-Skill
Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.
Agents Workflows
VectorSpaceLab/AREX-Skill
A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.
Alphafold3
VectorSpaceLab/AREX-Skill
A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
App Callback Workflows
VectorSpaceLab/AREX-Skill
A skill your agent uses for Plotly Dash app layouts, callbacks, pages, assets, configuration, clientside callbacks, Jupyter display, CSP, and app-level debugging.
Related
Works with
Categories
Questions about Agents And Middleware
What does Agents And Middleware do?
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…. Agents And Middleware is an agent skill from VectorSpaceLab/AREX-Skill. Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime customization.
When should I use Agents And Middleware?
Agents And Middleware fits situations like: libs/langchainv1 agent workflows and route low-level core primitives; provider implementation details to sibling skills.
How do I install Agents And Middleware in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill agents-and-middleware -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware in VectorSpaceLab/AREX-Skill) into .claude/skills/agents-and-middleware in your project. Claude Code loads it when a task matches its description.
How do I install Agents And Middleware in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill agents-and-middleware -a codex`. Or copy the skill folder (skills/repositories/repo-skills/langchain/sub-skills/agents-and-middleware in VectorSpaceLab/AREX-Skill) into .agents/skills/agents-and-middleware in your project. Codex loads it when a task matches its description.
Can I use Agents And Middleware 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 VectorSpaceLab/AREX-Skill --skill agents-and-middleware -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agents-and-middleware, .gemini/skills/agents-and-middleware, .github/skills/agents-and-middleware and .opencode/skills/agents-and-middleware in your project.
What does Agents And Middleware need to run?
Going by SKILL.md and its folder, Agents And Middleware needs Python for the scripts in its folder and the command-line tools its instructions call (uv and python). Our summary lists: Python 3.
Does Agents And Middleware 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 Agents And Middleware 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Agents And Middleware use?
Agents And Middleware is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agents And Middleware use?
About 1.2k tokens (SKILL.md is roughly 4.9k 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 8.6k tokens, read only when the agent opens those files.
What are the alternatives to Agents And Middleware?
Skills that share tags, products or a category with Agents And Middleware: Sap Cloud SDK AI (secondsky/sap-skills, 462 stars), Routerbase Model Routing (aiskillstore/marketplace, 430 stars), AI SDK (vercel-labs/ai-facts, 168 stars) and Llmobs Integration (DataDog/dd-trace-js, 837 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agents And Middleware?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 330 GitHub stars. The repository holds 159 skills in this directory. The repository was last updated on September 3, 2026.
Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.