langchain-builder

AI Community

Repo stars 0
Author repo skills-registry

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Build LangChain chains, agents, and tool integrations with scaffolding, validation, and template generation. Use when this capab…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “What it does”, “Commands”, “Examples”, “Chain types”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name langchain-builder directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “What it does / Commands / Examples” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write / env-read; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

LangChain Builder

Build LangChain chains, agents, and tool integrations with scaffolding, validation, and template generation.

What it does

Scaffolds LangChain projects, generates chain and agent configurations, creates prompt templates, and validates chain configs for common errors. Produces ready-to-run Python files with proper imports and structure.

Commands

Command	Description
`init <project>`	Scaffold a new LangChain project with requirements.txt and project structure
`chain <type> --name <n>`	Generate a chain template: `llm`, `sequential`, `router`
`agent <tools>`	Generate an agent config with specified tools (search, calculator, python_repl)
`prompt <description>`	Create a prompt template from a natural language description
`validate <file>`	Check a chain/agent Python file for common configuration errors

Examples

python3 langchain_builder.py init my-rag-app
python3 langchain_builder.py chain llm --name summarizer
python3 langchain_builder.py agent search,calculator
python3 langchain_builder.py prompt "Summarize a document in 3 bullet points"
python3 langchain_builder.py validate my_chain.py

Chain types

llm — Single LLMChain with prompt + model
sequential — SequentialChain connecting multiple LLMChains
router — RouterChain that selects sub-chains based on input classification

Generated files include

Proper langchain imports (community packages where needed)
Environment variable loading via python-dotenv
Error handling and type hints
Runnable patterns (LangChain Expression Language where applicable)

Source: Danielhogben/hermes-skills — distributed by TomeVault.

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: AI
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @tomevault-io · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Plug-and-play
External API key: No requirement detected
Detected OS requirements: Unspecified
Runtime requirements: Python
Detected file/system behavior: Read-only
Write / modify
Env read
Detected network behavior: Local-only
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview langchain-builder.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# LangChain Builder

Build LangChain chains, agents, and tool integrations with scaffolding, validation, and template generation.

## What it does

Scaffolds LangChain projects, generates chain and agent configurations, creates prompt templates, and validates chain configs for common errors. Produces ready-to-run Python files with proper imports and structure.

## Commands

| Command | Description |
|---------|-------------|
| `init <project>` | Scaffold a new LangChain project with requirements.txt and project structure |
| `chain <type> --name <n>` | Generate a chain template: `llm`, `sequential`, `router` |
| `agent <tools>` | Generate an agent config with specified tools (search, calculator, python_repl) |
| `prompt <description>` | Create a prompt template from a natural language description |
| `validate <file>` | Check a chain/agent Python file for common configuration errors |

## Examples

```bash
python3 langchain_builder.py init my-rag-app
python3 langchain_builder.py chain llm --name summarizer
python3 langchain_builder.py agent search,calculator
python3 langchain_builder.py prompt "Summarize a document in 3 bullet points"
python3 langchain_builder.py validate my_chain.py
```

## Chain types

- **llm** — Single LLMChain with prompt + model
- **sequential** — SequentialChain connecting multiple LLMChains
- **router** — RouterChain that selects sub-chains based on input classification

## Generated files include

- Proper `langchain` imports (community packages where needed)
- Environment variable loading via `python-dotenv`
- Error handling and type hints
- Runnable patterns (LangChain Expression Language where applicable)

---

…

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> What it does → Commands → Examples → Chain types → Generated files include
terms    -> llm · sequential · router · Build LangChain chains, agents, and tool integrations with scaffolding, validation, and template generation. · --- > Source: [Danielhogben/hermes-skills](https://github.com/Danielhogben/hermes-skills) — distributed by [TomeVault](https://tomevault.io).
files/cmd -> init <project> · chain <type> --name <n> · llm · sequential · router · agent <tools> · prompt <description> · validate <file>
body sha256 -> c94fce76139b