Process documents with Blockify API to create optimized IdeaBlocks for RAG.

Custom licenceAuto-check: notesAI & LLM Engineering

Install Blockify Integration

skills CLI
$ npx skills add iternal-technologies-partners/blockify-agentic-data-optimization --skill blockify-integration -a claude-code

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

GitHub CLI
$ gh skill install iternal-technologies-partners/blockify-agentic-data-optimization blockify-integration --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/iternal-technologies-partners/blockify-agentic-data-optimization.git skills-src && mkdir -p .claude/skills && cp -r skills-src/blockify-skill-for-claude-code/skills/blockify-integration .claude/skills/blockify-integration && 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/

Facts

Skill name
blockify-integration
GitHub stars
316
Token cost
~6.2k tokens
SKILL.md length
594 words
Files
47 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
Custom licence

At a glance

Process documents with Blockify API to create optimized IdeaBlocks for RAG.

  • Works in 6 steps: Create Environment File → Load Environment Variables → Install Dependencies → …
  • Processing documentation
  • SKILL.md covers Why This Exists, End-to-End Process Flow, Complete Setup (Step-by-Step) and Data Flow Diagram, plus 10 more sections
  • Runs Python scripts from its folder; calls python3 and docker-compose; needs BLOCKIFY_API_KEY and OPENAI_API_KEY

What it does

Blockify Integration is an agent skill from iternal-technologies-partners/blockify-agentic-data-optimization. Process documents with Blockify API to create optimized IdeaBlocks for RAG. Search external ChromaDB knowledge bases with 100k+ blocks. Use when processing documentation, creating knowledge bases, improving AI context retrieval, or when user mentions Blockify, IdeaBlocks, or knowledge distillation.

Its SKILL.md is about 6.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 52 other files, including scripts and reference files (for example `BENCHMARK-GUIDE.md`, `config/benchmark_config.yaml` and `references/API.md`).

It sits in AI & LLM Engineering, covering Knowledge bases and Retrieval-augmented generation. It works with Chroma. The repository describes itself as: Blockify: Agentic data optimization for enterprise RAG and agentic search. Blockify replaces naive chunking with deduplicated IdeaBlocks — ≈78X accuracy aggregate improvement…

When your agent uses it

  • Processing documentation
  • Creating knowledge bases
  • Improving AI context retrieval
  • User mentions Blockify

Example prompts

  • “/blockify-integration”

Requirements

  • Python 3
  • Docker
  • A credential in BLOCKIFY_API_KEY
  • A credential in OPENAI_API_KEY

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Create Environment File
  2. Load Environment Variables
  3. Install Dependencies
  4. Ingest Documents
  5. Distill (Deduplicate)
  6. Search

What it can do on your machine

Read from SKILL.md and the folder at commit 9e36c10. 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 8 files in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • docker-compose

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

  • Network

    Links to these hosts (documentation or services it may open):

    • platform.openai.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • BLOCKIFY_API_KEY
    • OPENAI_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Blockify Integration loads about 6.2k tokens when it runs, and up to ~8.1k if it reads all its reference files. Until then it costs about 80 tokens; SKILL.md has 594 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~6.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.1k

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:78
    # Create .env file
  • NoteMentions a .env fileSKILL.md:79
    cat > .env << 'EOF'
  • NoteMentions a .env fileSKILL.md:91
    export $(cat .env | grep -v '^#' | grep -v '^$' | xargs)
  • NoteMentions a .env fileSKILL.md:144
    cp .env.example .env
  • NoteMentions a .env fileSKILL.md:145
    # Add API keys to .env
  • NoteMentions a .env fileSKILL.md:349
    │ Missing env var    │ export $(cat .env    │
  • NoteMentions a .env fileSKILL.md:453
    export $(cat /path/to/.env | grep -v '^#' | grep -v '^$' | xargs)
  • NoteMentions a .env fileSKILL.md:594
    # 2. Create .env file with your API keys
  • NoteMentions a .env fileSKILL.md:595
    cat > ../../.env << 'EOF'
  • NoteMentions a .env fileSKILL.md:602
    export $(cat ../../.env | grep -v '^#' | grep -v '^$' | xargs)

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 594 words (~6,213 tokens).

“Problem: Traditional RAG systems chunk documents by character/token count, losing semantic coherence. A 500-token chunk may split a concept mid-sentence, contain unrelated paragraphs, or bury key facts in noise.”

— opening of SKILL.md by iternal-technologies-partners, Custom licence
name
blockify-integration

Read the full SKILL.md on GitHub

Files

SKILL.md and 46 other files (scripts, references) in blockify-skill-for-claude-code/skills/blockify-integration of iternal-technologies-partners/blockify-agentic-data-optimization.

  • SKILL.md
  • BENCHMARK-GUIDE.md
  • config/benchmark_config.yaml
  • references/API.md
  • references/DISTILLATION.md
  • references/SCHEMA.md
  • requirements.txt
  • scripts/benchmark/__init__.py
  • scripts/benchmark/charts.py
  • scripts/benchmark/config.py
  • scripts/benchmark/embeddings.py
  • scripts/benchmark/metrics.py
  • scripts/benchmark/report_generator.py
  • scripts/benchmark/templates/base.html
  • scripts/benchmark/templates/sections/accuracy_chart.html
  • … and 32 more

Open the folder on GitHubat commit 9e36c10

Compare with similar skills

Blockify Integration 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.

Blockify Integration compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Blockify Integration this skilliternal-technologies-partners/blockify-agentic-data-optimization316—~6.2kAutomated safety check: NotesCustom licence
Penguin SDKPrism-Shadow/penguin-harness2.5k—~11kAutomated safety check: PassApache-2.0
Sc QAopen-edge-platform/edge-ai-suites140—~2.3kAutomated safety check: PassApache-2.0
RAG AssistantAtmosphere/atmosphere3.8k—~504Automated safety check: PassApache-2.0
Langchain4j RAG Implementation Patternsgiuseppe-trisciuoglio/developer-kit3551 repos~3.3kAutomated safety check: NotesMIT
Orchata RAGLeoYeAI/openclaw-master-skills2.2k—~4.7kAutomated safety check: PassMIT

Similar skills

  • Penguin SDK

    Prism-Shadow/penguin-harness

    A skill your agent uses whenever the user wants to build an agent application — their own program with an embedded agent, such as an AI app, an agentic app or a RAG app.

    2.5k GitHub stars~11k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Sc QA

    open-edge-platform/edge-ai-suites

    Ask a natural-language question against indexed content via the Content Search RAG Q&A endpoint.

    140 GitHub stars~2.3k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • RAG Assistant

    Atmosphere/atmosphere

    Knowledge base assistant that retrieves and cites documents from a curated index.

    3.8k GitHub stars~504 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Langchain4j RAG Implementation Patterns

    giuseppe-trisciuoglio/developer-kit

    Provides Retrieval-Augmented Generation (RAG) implementation patterns with LangChain4j for Java.

    355 GitHub starsUsed in 1 repo~3.3k tokens
    AI & LLM EngineeringAuto-check: notes
  • Orchata RAG

    LeoYeAI/openclaw-master-skills

    Knowledge management and RAG platform with tree-based document indexing.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed
  • RAG

    automateyournetwork/netclaw

    Ingest user-selected documents and retrieve cited procedures, standards, and design evidence from the local RAG knowledge base.

    674 GitHub stars~2.8k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

Works with

Questions about Blockify Integration

What does Blockify Integration do?

Process documents with Blockify API to create optimized IdeaBlocks for RAG. Blockify Integration is an agent skill from iternal-technologies-partners/blockify-agentic-data-optimization. Process documents with Blockify API to create optimized IdeaBlocks for RAG.

When should I use Blockify Integration?

Blockify Integration fits situations like: processing documentation; creating knowledge bases; improving AI context retrieval; user mentions Blockify.

How do I install Blockify Integration in Claude Code?

Run `npx skills add iternal-technologies-partners/blockify-agentic-data-optimization --skill blockify-integration -a claude-code`. Or copy the skill folder (blockify-skill-for-claude-code/skills/blockify-integration in iternal-technologies-partners/blockify-agentic-data-optimization) into .claude/skills/blockify-integration in your project. Claude Code loads it when a task matches its description.

How do I install Blockify Integration in Codex?

Run `npx skills add iternal-technologies-partners/blockify-agentic-data-optimization --skill blockify-integration -a codex`. Or copy the skill folder (blockify-skill-for-claude-code/skills/blockify-integration in iternal-technologies-partners/blockify-agentic-data-optimization) into .agents/skills/blockify-integration in your project. Codex loads it when a task matches its description.

Can I use Blockify Integration 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 iternal-technologies-partners/blockify-agentic-data-optimization --skill blockify-integration -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/blockify-integration, .gemini/skills/blockify-integration, .github/skills/blockify-integration and .opencode/skills/blockify-integration in your project.

What does Blockify Integration need to run?

Going by SKILL.md and its folder, Blockify Integration needs Python for the scripts in its folder, the command-line tools its instructions call (python3 and docker-compose) and credentials named BLOCKIFY_API_KEY and OPENAI_API_KEY. Our summary lists: Python 3; Docker; A credential in BLOCKIFY_API_KEY; A credential in OPENAI_API_KEY.

Does Blockify Integration access the network?

SKILL.md names 1 domain. As links in the text: platform.openai.com. This is read from the text; nothing was executed.

Is Blockify Integration 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 Blockify Integration use?

Blockify Integration has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Blockify Integration use?

About 6.2k tokens (SKILL.md is roughly 25k 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 1.9k tokens, read only when the agent opens those files.

What are the alternatives to Blockify Integration?

Skills that share tags, products or a category with Blockify Integration: Penguin SDK (Prism-Shadow/penguin-harness, 2.5k stars), Sc QA (open-edge-platform/edge-ai-suites, 140 stars), RAG Assistant (Atmosphere/atmosphere, 3.8k stars) and Langchain4j RAG Implementation Patterns (giuseppe-trisciuoglio/developer-kit, 355 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Blockify Integration?

iternal-technologies-partners (a GitHub organization) maintains it in iternal-technologies-partners/blockify-agentic-data-optimization, which has 316 GitHub stars. The repository was last updated on April 22, 2026.

Source: iternal-technologies-partners/blockify-agentic-data-optimization on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.