SKILLoptionalHermes Optional Skills

Guidance

Name: Guidance
Author: Orchestra Research

Constrain LLM output with grammars; guarantee valid JSON

Prompt EngineeringGuidanceConstrained GenerationStructured OutputJSON ValidationGrammarMicrosoft ResearchFormat Enforcement

Last registry verification2026-08-18v1.0.1Orchestra Research

Open original source ↗اقرأ بالعربية

Plain meaning

What does it add to Hermes?

Constrain LLM output with grammars; guarantee valid JSON

Guidance is a skill related to research and sources. It gives the agent a way to find external information and sources instead of relying only on model memory.

This plain-language explanation is based on the publisher description. The original text remains visible for verification.

Use it when

Use it when your goal in research and sources is clear and you can limit it to the data and actions it actually needs.

Skip it when

Do not add it merely to experiment when Hermes already has a simpler path, or when you cannot review its source and permissions.

Who is it for?

Best for users who want a repeatable way of working inside Hermes.

Safe first test

Ask for one recent fact with two sources, then open both links and verify dates and evidence.

Original publisher description

Constrain LLM output with grammars; guarantee valid JSON

✓

Data source

This entry was indexed from Hermes Optional Skills. Our explanation interprets the type and domain without inventing a capability not present upstream.

Security review

The source is official or editorially reviewed, but you still need to review permissions and version compatibility.

Safe setup path

Inspect, install, then test.

01
Open the source
Match the publisher, license, and description to your need. Check the real update history.
02
Review permissions and secrets
Never paste a secret value into this site. Use environment-variable names and grant the smallest scope.
03
Copy setup only after review
The controls below copy text. They do not execute commands on your device.
04
Test with a non-sensitive task
Inspect the visible tools, then exclude write or delete tools you do not need.

Install command

Review the command, then copy it.

hermes skills install guidance

Hermes Belarabi does not execute this command. Installation happens on your device and remains subject to Hermes scanning and your review.

The full skill definition

Exactly what Hermes loads when this skill runs.

Reproduced from the official documentation. Read it before enabling the skill: this text becomes the agent's instructions.

Constrain LLM output with grammars; guarantee valid JSON.

Skill metadata

A lookup table. Do not read it all; find the row that applies to you.

Source	Optional — install with `hermes skills install official/mlops/guidance`
Path	`optional-skills/mlops/guidance`
Version	`1.0.1`
Author	Orchestra Research
License	MIT
Dependencies	`guidance`, `transformers`
Platforms	linux, macos, windows
Tags	`Prompt Engineering`, `Guidance`, `Constrained Generation`, `Structured Output`, `JSON Validation`, `Grammar`, `Microsoft Research`, `Format Enforcement`, `Multi-Step Workflows`

Reference: full SKILL.md

Explains the idea itself. Read it slowly; the later sections build on it.

When to Use This Skill

Explains the idea itself. Read it slowly; the later sections build on it.

Use Guidance when you need to:

Control LLM output syntax with regex or grammars
Guarantee valid JSON/XML/code generation
Reduce latency vs traditional prompting approaches
Enforce structured formats (dates, emails, IDs, etc.)
Build multi-step workflows with Pythonic control flow
Prevent invalid outputs through grammatical constraints

GitHub Stars: 18,000+ | From: Microsoft Research

Installation

Ordered, practical steps. Run one and confirm it worked before moving on.

Shell6 lines

# Base installation
pip install guidance

# With specific backends
pip install guidance[transformers]  # Hugging Face models
pip install guidance[llama_cpp]     # llama.cpp models

Quick Start

Ordered, practical steps. Run one and confirm it worked before moving on.

Basic Example: Structured Generation

Python9 lines

from guidance import models, gen

# Load model (supports OpenAI, Transformers, llama.cpp)
lm = models.OpenAI("gpt-4")

# Generate with constraints
result = lm + "The capital of France is " + gen("capital", max_tokens=5)

print(result["capital"])  # "Paris"

Chat format with a local model

Constraint support requires local logit access. Regex, select(), and grammar-based constrained generation only work with local backends (Transformers, LlamaCpp). Remote API backends (OpenAI, and Azure variants) support unconstrained gen() / chat only — they cannot enforce token-level constraints. guidance 0.3.x has no models.Anthropic class.

Python14 lines

from guidance import models, gen, system, user, assistant

# Local model (supports constrained generation)
lm = models.Transformers("microsoft/Phi-4-mini-instruct")

# Use context managers for chat format
with system():
    lm += "You are a helpful assistant."

with user():
    lm += "What is the capital of France?"

with assistant():
    lm += gen(max_tokens=20)

Core Concepts

Explains the idea itself. Read it slowly; the later sections build on it.

1. Context Managers

Guidance uses Pythonic context managers for chat-style interactions.

Python17 lines

from guidance import system, user, assistant, gen

lm = models.Transformers("microsoft/Phi-4-mini-instruct")

# System message
with system():
    lm += "You are a JSON generation expert."

# User message
with user():
    lm += "Generate a person object with name and age."

# Assistant response
with assistant():
    lm += gen("response", max_tokens=100)

print(lm["response"])

Benefits:

Natural chat flow
Clear role separation
Easy to read and maintain

2. Constrained Generation

Guidance ensures outputs match specified patterns using regex or grammars.

Regex Constraints

Python15 lines

from guidance import models, gen

lm = models.Transformers("microsoft/Phi-4-mini-instruct")

# Constrain to valid email format
lm += "Email: " + gen("email", regex=r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}")

# Constrain to date format (YYYY-MM-DD)
lm += "Date: " + gen("date", regex=r"\d{4}-\d{2}-\d{2}")

# Constrain to phone number
lm += "Phone: " + gen("phone", regex=r"\d{3}-\d{3}-\d{4}")

print(lm["email"])  # Guaranteed valid email
print(lm["date"])   # Guaranteed YYYY-MM-DD format

How it works:

Regex converted to grammar at token level
Invalid tokens filtered during generation
Model can only produce matching outputs

Selection Constraints

Python15 lines

from guidance import models, gen, select

lm = models.Transformers("microsoft/Phi-4-mini-instruct")

# Constrain to specific choices
lm += "Sentiment: " + select(["positive", "negative", "neutral"], name="sentiment")

# Multiple-choice selection
lm += "Best answer: " + select(
    ["A) Paris", "B) London", "C) Berlin", "D) Madrid"],
    name="answer"
)

print(lm["sentiment"])  # One of: positive, negative, neutral
print(lm["answer"])     # One of: A, B, C, or D

3. Token Healing

Guidance automatically "heals" token boundaries between prompt and generation.

Problem: Tokenization creates unnatural boundaries.

Python5 lines

# Without token healing
prompt = "The capital of France is "
# Last token: " is "
# First generated token might be " Par" (with leading space)
# Result: "The capital of France is  Paris" (double space!)

Solution: Guidance backs up one token and regenerates.

Python7 lines

from guidance import models, gen

lm = models.Transformers("microsoft/Phi-4-mini-instruct")

# Token healing enabled by default
lm += "The capital of France is " + gen("capital", max_tokens=5)
# Result: "The capital of France is Paris" (correct spacing)

Benefits:

Natural text boundaries
No awkward spacing issues
Better model performance (sees natural token sequences)

4. Grammar-Based Generation

Define complex structures by composing grammar functions. The template-string grammar= form is not part of current guidance — build grammars from composable functions, or use guidance.json() for JSON.

Python19 lines

from guidance import models, gen
from guidance import json as gen_json
from pydantic import BaseModel, Field

lm = models.Transformers("microsoft/Phi-4-mini-instruct")

# JSON via a Pydantic schema (guidance.json compiles the schema to a grammar)
class Person(BaseModel):
    name: str = Field(pattern=r"[A-Za-z ]+")
    age: int
    email: str = Field(pattern=r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}")

lm += gen_json(name="person", schema=Person)

print(lm["person"])  # Guaranteed valid JSON matching the schema

# Or compose grammar functions directly:
grammar = "name=" + gen("name", regex=r"[A-Za-z ]+") + " age=" + gen("age", regex=r"[0-9]+")
lm += grammar

Use cases:

Complex structured outputs
Nested data structures
Programming language syntax
Domain-specific languages

5. Guidance Functions

Create reusable generation patterns with the @guidance decorator.

Python15 lines

from guidance import guidance, gen, models

@guidance
def generate_person(lm):
    """Generate a person with name and age."""
    lm += "Name: " + gen("name", max_tokens=20, stop="\n")
    lm += "\nAge: " + gen("age", regex=r"[0-9]+", max_tokens=3)
    return lm

# Use the function
lm = models.Transformers("microsoft/Phi-4-mini-instruct")
lm = generate_person(lm)

print(lm["name"])
print(lm["age"])

Stateful Functions:

Python24 lines

@guidance(stateless=False)
def react_agent(lm, question, tools, max_rounds=5):
    """ReAct agent with tool use."""
    lm += f"Question: {question}\n\n"

    for i in range(max_rounds):
        # Thought
        lm += f"Thought {i+1}: " + gen("thought", stop="\n")

        # Action
        lm += "\nAction: " + select(list(tools.keys()), name="action")

        # Execute tool
        tool_result = tools[lm["action"]]()
        lm += f"\nObservation: {tool_result}\n\n"

        # Check if done
        lm += "Done? " + select(["Yes", "No"], name="done")
        if lm["done"] == "Yes":
            break

    # Final answer
    lm += "\nFinal Answer: " + gen("answer", max_tokens=100)
    return lm

Backend Configuration

Settings you configure once. Change one at a time so you can see what each does. Set OPENAI_API_KEY in your environment, not in the chat.

OpenAI (remote — unconstrained only)

Remote API backends cannot do constrained generation (regex/select/grammar); use them only for plain chat/gen(). For constraints, use a local backend.

Python6 lines

from guidance import models

lm = models.OpenAI(
    model="gpt-4o-mini",
    api_key="your-api-key"  # Or set OPENAI_API_KEY env var
)

Local Models (Transformers)

Python6 lines

from guidance.models import Transformers

lm = Transformers(
    "microsoft/Phi-4-mini-instruct",
    device="cuda"  # Or "cpu"
)

Local Models (llama.cpp)

Python7 lines

from guidance.models import LlamaCpp

lm = LlamaCpp(
    model_path="/path/to/model.gguf",
    n_ctx=4096,
    n_gpu_layers=35
)

Common Patterns

Explains the idea itself. Read it slowly; the later sections build on it.

Pattern 1: JSON Generation

Python18 lines

from guidance import models, gen, system, user, assistant

lm = models.Transformers("microsoft/Phi-4-mini-instruct")

with system():
    lm += "You generate valid JSON."

with user():
    lm += "Generate a user profile with name, age, and email."

with assistant():
    lm += """{
    "name": """ + gen("name", regex=r'"[A-Za-z ]+"', max_tokens=30) + """,
    "age": """ + gen("age", regex=r"[0-9]+", max_tokens=3) + """,
    "email": """ + gen("email", regex=r'"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}"', max_tokens=50) + """
}"""

print(lm)  # Valid JSON guaranteed

Pattern 2: Classification

Python12 lines

from guidance import models, gen, select

lm = models.Transformers("microsoft/Phi-4-mini-instruct")

text = "This product is amazing! I love it."

lm += f"Text: {text}\n"
lm += "Sentiment: " + select(["positive", "negative", "neutral"], name="sentiment")
lm += "\nConfidence: " + gen("confidence", regex=r"[0-9]+", max_tokens=3) + "%"

print(f"Sentiment: {lm['sentiment']}")
print(f"Confidence: {lm['confidence']}%")

Pattern 3: Multi-Step Reasoning

Python20 lines

from guidance import models, gen, guidance

@guidance
def chain_of_thought(lm, question):
    """Generate answer with step-by-step reasoning."""
    lm += f"Question: {question}\n\n"

    # Generate multiple reasoning steps
    for i in range(3):
        lm += f"Step {i+1}: " + gen(f"step_{i+1}", stop="\n", max_tokens=100) + "\n"

    # Final answer
    lm += "\nTherefore, the answer is: " + gen("answer", max_tokens=50)

    return lm

lm = models.Transformers("microsoft/Phi-4-mini-instruct")
lm = chain_of_thought(lm, "What is 15% of 200?")

print(lm["answer"])

Pattern 4: ReAct Agent

Python36 lines

from guidance import models, gen, select, guidance

@guidance(stateless=False)
def react_agent(lm, question):
    """ReAct agent with tool use."""
    tools = {
        "calculator": lambda expr: eval(expr),
        "search": lambda query: f"Search results for: {query}",
    }

    lm += f"Question: {question}\n\n"

    for round in range(5):
        # Thought
        lm += f"Thought: " + gen("thought", stop="\n") + "\n"

        # Action selection
        lm += "Action: " + select(["calculator", "search", "answer"], name="action")

        if lm["action"] == "answer":
            lm += "\nFinal Answer: " + gen("answer", max_tokens=100)
            break

        # Action input
        lm += "\nAction Input: " + gen("action_input", stop="\n") + "\n"

        # Execute tool
        if lm["action"] in tools:
            result = tools[lm["action"]](lm["action_input"])
            lm += f"Observation: {result}\n\n"

    return lm

lm = models.Transformers("microsoft/Phi-4-mini-instruct")
lm = react_agent(lm, "What is 25 * 4 + 10?")
print(lm["answer"])

Pattern 5: Data Extraction

Python30 lines

from guidance import models, gen, guidance

@guidance
def extract_entities(lm, text):
    """Extract structured entities from text."""
    lm += f"Text: {text}\n\n"

    # Extract person
    lm += "Person: " + gen("person", stop="\n", max_tokens=30) + "\n"

    # Extract organization
    lm += "Organization: " + gen("organization", stop="\n", max_tokens=30) + "\n"

    # Extract date
    lm += "Date: " + gen("date", regex=r"\d{4}-\d{2}-\d{2}", max_tokens=10) + "\n"

    # Extract location
    lm += "Location: " + gen("location", stop="\n", max_tokens=30) + "\n"

    return lm

text = "Tim Cook announced at Apple Park on 2024-09-15 in Cupertino."

lm = models.Transformers("microsoft/Phi-4-mini-instruct")
lm = extract_entities(lm, text)

print(f"Person: {lm['person']}")
print(f"Organization: {lm['organization']}")
print(f"Date: {lm['date']}")
print(f"Location: {lm['location']}")

Best Practices

Explains the idea itself. Read it slowly; the later sections build on it.

1. Use Regex for Format Validation

Python5 lines

# ✅ Good: Regex ensures valid format
lm += "Email: " + gen("email", regex=r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}")

# ❌ Bad: Free generation may produce invalid emails
lm += "Email: " + gen("email", max_tokens=50)

2. Use select() for Fixed Categories

Python5 lines

# ✅ Good: Guaranteed valid category
lm += "Status: " + select(["pending", "approved", "rejected"], name="status")

# ❌ Bad: May generate typos or invalid values
lm += "Status: " + gen("status", max_tokens=20)

3. Leverage Token Healing

Python3 lines

# Token healing is enabled by default
# No special action needed - just concatenate naturally
lm += "The capital is " + gen("capital")  # Automatic healing

4. Use stop Sequences

Python5 lines

# ✅ Good: Stop at newline for single-line outputs
lm += "Name: " + gen("name", stop="\n")

# ❌ Bad: May generate multiple lines
lm += "Name: " + gen("name", max_tokens=50)

5. Create Reusable Functions

Python11 lines

# ✅ Good: Reusable pattern
@guidance
def generate_person(lm):
    lm += "Name: " + gen("name", stop="\n")
    lm += "\nAge: " + gen("age", regex=r"[0-9]+")
    return lm

# Use multiple times
lm = generate_person(lm)
lm += "\n\n"
lm = generate_person(lm)

6. Balance Constraints

Python5 lines

# ✅ Good: Reasonable constraints
lm += gen("name", regex=r"[A-Za-z ]+", max_tokens=30)

# ❌ Too strict: May fail or be very slow
lm += gen("name", regex=r"^(John|Jane)$", max_tokens=10)

Comparison to Alternatives

A lookup table. Do not read it all; find the row that applies to you.

Feature	Guidance	Instructor	Outlines	LMQL
Regex Constraints	✅ Yes	❌ No	✅ Yes	✅ Yes
Grammar Support	✅ CFG	❌ No	✅ CFG	✅ CFG
Pydantic Validation	❌ No	✅ Yes	✅ Yes	❌ No
Token Healing	✅ Yes	❌ No	✅ Yes	❌ No
Local Models	✅ Yes	⚠️ Limited	✅ Yes	✅ Yes
API Models	✅ Yes	✅ Yes	⚠️ Limited	✅ Yes
Pythonic Syntax	✅ Yes	✅ Yes	✅ Yes	❌ SQL-like
Learning Curve	Low	Low	Medium	High

When to choose Guidance:

Need regex/grammar constraints
Want token healing
Building complex workflows with control flow
Using local models (Transformers, llama.cpp)
Prefer Pythonic syntax

When to choose alternatives:

Instructor: Need Pydantic validation with automatic retrying
Outlines: Need JSON schema validation
LMQL: Prefer declarative query syntax

Performance Characteristics

Explains the idea itself. Read it slowly; the later sections build on it.

Latency Reduction:

30-50% faster than traditional prompting for constrained outputs
Token healing reduces unnecessary regeneration
Grammar constraints prevent invalid token generation

Memory Usage:

Minimal overhead vs unconstrained generation
Grammar compilation cached after first use
Efficient token filtering at inference time

Token Efficiency:

Prevents wasted tokens on invalid outputs
No need for retry loops
Direct path to valid outputs

Resources

Explains the idea itself. Read it slowly; the later sections build on it.

Documentation: https://guidance.readthedocs.io
GitHub: https://github.com/guidance-ai/guidance (18k+ stars)
Notebooks: https://github.com/guidance-ai/guidance/tree/main/notebooks
Discord: Community support available