create-unstructured-data

create-unstructured-data is a skill for Claude Code, Codex from mstr-sharma/strategy-automate. It costs 129 tokens per session (1,472 once invoked), scanned A, original, MIT.

A tool for turning local documents into Strategy unstructured-data sources, called nuggets, so Strategy’s AI features can use them as reference material. PowerPoint files are converted to Markdown first.

In plain words
What is it for?
Uploading PDF, Word, Markdown, text, email, and PowerPoint files to Strategy, including converting .pptx or .potx presentations before upload.
Why use it?
It makes documents available for grounded answers and avoids unsupported uploads, such as legacy .ppt files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 skills/build-mosaic-model/scripts/build_mosaic.py api-call \.

Good fit Uploading PDF, Word, Markdown, text, email, and PowerPoint files to Strategy, including converting .pptx or .potx presentations before upload.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mstr-sharma/strategy-automate
agentmods
npx agentmods add skills/mstr-sharma/strategy-automate/create-unstructured-data

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for create-unstructured-data

README.md
[![agentmods](https://agentmods.dev/badge/skills/mstr-sharma/strategy-automate/create-unstructured-data.svg)](https://agentmods.dev/skills/mstr-sharma/strategy-automate/create-unstructured-data)
Your own site
<a href="https://agentmods.dev/skills/mstr-sharma/strategy-automate/create-unstructured-data"><img src="https://agentmods.dev/badge/skills/mstr-sharma/strategy-automate/create-unstructured-data.svg" alt="Measured on agentmods" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,472 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00129 $0.01472
Opus 5 $0.00064 $0.00736
Sonnet 5 $0.00026 $0.00294
Haiku 4.5 $0.00013 $0.00147

Measured 7d ago against content hash aeb28642b859, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

create-unstructured-data scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/create_unstructured.py, scripts/pptx_to_md.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/create-unstructured-data/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Unstructured Data (Nuggets)

Turn a local document into a Strategy unstructured-data nugget so AI surfaces (Auto Agent, chat, question answering) can ground on it. Doc reference: rest-api-docs → common-workflows → analytics → unstructured-data-api.

Accepted inputs

Input Handling API fileType
.pdf direct upload 0
.docx direct upload 1
.md / .markdown direct upload 3
.txt direct upload 4
.eml direct upload 5
.pptx / .potx auto-converted to Markdown (pptx_to_md.py, stdlib-only), then uploaded as fileType 3

PowerPoint is NOT accepted by the API — conversion is mandatory, not optional. .ppt (legacy binary) is not convertible by the stdlib extractor; ask the user to re-save as .pptx or export text another way.

Environment / prerequisites

  • Standard env vars: MSTR_BASE, MSTR_USER, MSTR_PASSWORD, MSTR_PROJECT_ID (or MSTR_PROJECT_NAME), MSTR_DEST_FOLDER_ID (destination folder for the nugget).
  • The nuggets API family ships in recent Strategy ONE releases (docs say April 2026+). Verify before promising: build_mosaic.py openapi-search "nugget" must show /api/nuggets. Most nugget endpoints are visibility: internal — fetch {Library}/api/openapi.yaml?visibility=all to see the full set (/{id}, /{id}/file, /{id}/categories, /status/query, /{id}/deleteRequest, /orphans).

One-shot workflow

cd "$REPO"
python3 skills/create-unstructured-data/scripts/create_unstructured.py DECK.pptx \
    [--notes] [--title "Doc Title"] [--name "display-name.md"] \
    [--folder-id <ID>] [--no-poll] [--poll-timeout 120]

What it does: (pptx only) convert to Markdown alongside the source → login → resolve project → multipart POST /api/nuggets?type=unstructuredData with file, fileName, fileType, fileSize, folderId → parse {"id": ...} → poll POST /api/nuggets/status/query with {"nuggets":[{"id","projectId"}]} until the status record is stable → print JSON (nuggetId, uploadedFile, raw status observations).

Read the full file on GitHub · 100 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 100 lines · 129 tokens per session scan A aeb28642b859

Subscribe to this mod's changes

create-unstructured-data is a skill published in the GitHub repository mstr-sharma/strategy-automate (2 stars, last pushed 3d ago), licensed MIT. It adds 129 tokens to every session and 1,472 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

markitdown

Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.

K-Dense-AI/scientific-agent-skills · 61 tokens

llamaindex

Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM…

davila7/claude-code-templates · 70 tokens

jupyter-notebooks

Create, edit, or validate reproducible SQL or Python notebooks. Use for notebooks, SQL/Python scratchpads, reproducible exploration, audit trails, or runnable companions where the analysis should be reviewable or rerunnable.

XiaomiMiMo/MiMo-Code · 49 tokens

extracting-keywords

Use when extracting keywords (YAKE/RAKE) from documents — and, secondarily, when detecting document language or generating embeddings for RAG and search. Covers the keyword config (and its feature gating), --detect-language, and the standalone embed command with real flags.

xberg-io/xberg · 63 tokens

azure-ai-document-intelligence-dotnet

Azure AI Document Intelligence SDK for .NET. Extract text, tables, and structured data from documents using prebuilt and custom models. Use for invoice processing, receipt extraction, ID document analysis, and custom document models. Triggers: "Document Intelligence", "DocumentIntelligenceClient", "form recognizer"…

microsoft/skills · 83 tokens

azure-ai-document-intelligence-ts

Extract text, tables, and structured data from documents using Azure Document Intelligence (@azure-rest/ai-document-intelligence). Use when processing invoices, receipts, IDs, forms, or building custom document models.

microsoft/skills · 47 tokens