Chunking Strategy

What it does

When your agent uses it

• Building retrieval-augmented generation systems
• Vector databases
• Processing large documents

Example prompts

• “Use the chunking-strategy skill to provide chunking strategies for RAG systems. An agent skill from giuseppe-trisciuoglio/developer-kit”
• “/chunking-strategy”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): Read, Write, Bash

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Fixed-Size Chunking (Level 1)
2. 2Recursive Character Chunking (Level 2)
3. 3Structure-Aware Chunking (Level 3)
4. 4Semantic Chunking (Level 4)
5. 5Advanced Methods (Level 5)

What it can do on your machine

Read from SKILL.md and the folder at commit fe73fb3. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Bash

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  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

Chunking Strategy loads about 1.6k tokens when it runs, and up to ~64k if it reads all its reference files. Until then it costs about 94 tokens; SKILL.md has 438 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~94

When it runs · the whole SKILL.md, loaded when a task matches

~1.6k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~64k

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

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Write, Bash

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from giuseppe-trisciuoglio/developer-kit at commit fe73fb3, republished under its MIT licence (© giuseppe-trisciuoglio). 438 words, ~1,646 tokens.

name

chunking-strategy

description

Provides chunking strategies for RAG systems. Generates chunk size recommendations (256-1024 tokens), overlap percentages (10-20%), and semantic boundary detection methods. Validates semantic coherence and evaluates retrieval precision/recall metrics. Use when building retrieval-augmented generation systems, vector databases, or processing large documents.

allowed-tools

Read, Write, Bash

# Check semantic coherence (requires sentence-transformers)
python -c "
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('all-MiniLM-L6-v2')
chunks = [...]  # your chunks
embeddings = model.encode(chunks)
similarity = (embeddings @ embeddings.T).mean()
print(f'Cohesion: {similarity:.3f}')  # target: 0.3-0.7
"

# Measure retrieval precision
python -c "
relevant = sum(1 for c in retrieved if c in relevant_chunks)
precision = relevant / len(retrieved)
print(f'Precision: {precision:.2f}')  # target: >= 0.7
"

# Check chunk size distribution
python -c "
import numpy as np
sizes = [len(c.split()) for c in chunks]
print(f'Mean: {np.mean(sizes):.0f}, Std: {np.std(sizes):.0f}')
print(f'Min: {min(sizes)}, Max: {max(sizes)}')
"

from langchain.text_splitter import RecursiveCharacterTextSplitter

splitter = RecursiveCharacterTextSplitter(
    chunk_size=256,
    chunk_overlap=25,
    length_function=len
)
chunks = splitter.split_documents(documents)

import ast

def chunk_python_code(code):
    tree = ast.parse(code)
    chunks = []
    for node in ast.walk(tree):
        if isinstance(node, (ast.FunctionDef, ast.ClassDef)):
            chunks.append(ast.get_source_segment(code, node))
    return chunks

def semantic_chunk(text, similarity_threshold=0.8):
    sentences = split_into_sentences(text)
    embeddings = generate_embeddings(sentences)
    chunks, current = [], [sentences[0]]
    for i in range(1, len(sentences)):
        sim = cosine_similarity(embeddings[i-1], embeddings[i])
        if sim < similarity_threshold:
            chunks.append(" ".join(current))
            current = [sentences[i]]
        else:
            current.append(sentences[i])
    chunks.append(" ".join(current))
    return chunks

© giuseppe-trisciuoglio, 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 8 other files (references) in plugins/developer-kit-ai/skills/chunking-strategy of giuseppe-trisciuoglio/developer-kit.

• SKILL.md
• references/advanced-strategies.md
• references/evaluation.md
• references/implementation.md
• references/research.md
• references/semantic-methods.md
• references/strategies.md
• references/tools.md
• references/visualization-tools.md

Open the folder on GitHubat commit fe73fb3