azadehtavassoli/topics/document_intelligence
topics/document_intelligence/SKILL.md
# Document Intelligence Skill ## Purpose Convert unstructured documents into LLM-ready Markdown using MarkItDown, with deterministic defaults and governance-compliant wrappers. References: - `core/GLOBAL_RULES.md` - `core/LOGGING_STANDARD.md` - `core/TESTING_STANDARD.md` - `core/STRUCTURED_OUTPUT_STANDARD.md` ## When to use - You need a standard document-to-Markdown conversion path. - You need deterministic conversion that does not require an LLM by default. - You need optional visual/LLM int
development
Updated Apr 3, 2026
$ install --global
skillsauthnpx skillsauth add azadehtavassoli/agent-skills-toolkit topics/document_intelligenceInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 3, 2026, 10:26 PM20.7s15 files scanned
SKILL.md
Document Intelligence Skill
Purpose
Convert unstructured documents into LLM-ready Markdown using MarkItDown, with deterministic defaults and governance-compliant wrappers.
References:
core/GLOBAL_RULES.mdcore/LOGGING_STANDARD.mdcore/TESTING_STANDARD.mdcore/STRUCTURED_OUTPUT_STANDARD.md
When to use
- You need a standard document-to-Markdown conversion path.
- You need deterministic conversion that does not require an LLM by default.
- You need optional visual/LLM interpretation mode behind an explicit flag.
Hard MUST rules
- Use binary streams only (
io.BytesIO+convert_stream). - Default conversion mode MUST NOT require an LLM.
- Visual/LLM interpretation mode MUST be explicit and optional.
- All wrappers MUST write debug logs to file.
- All typed outputs MUST use
pydantic.BaseModel. - Tests MUST use stubs/fakes for LLM and framework integrations.
Workflow
- Validate request payload into a Pydantic request model.
- Build a binary stream from
content_bytes. - Instantiate MarkItDown in deterministic mode by default.
- Enable optional visual mode only when requested and explicitly wired with an
llm_client. - Convert with
convert_stream. - Return a Pydantic result model and emit debug log events.
Output checklist
- [ ] Binary-stream conversion implemented.
- [ ] Pydantic input/output models present.
- [ ] Debug file logging enabled.
- [ ] No-LLM default behavior documented and tested.
- [ ] Optional visual mode documented and stub-tested.
- [ ] Markdown structure contract test included.
Related Skills
azadehtavassoli/topics/demo_pipeline
development
VerifiedTrustedCommunity
# Demo Pipeline — SKILL ## What this skill is for Use this skill to implement a long-term, maintainable demo pipeline for product demos. The aim is to create a reusable machine for demos, not a one-off screen recording. ## Canonical design A good demo pipeline has these responsibilities: ### 1. Scenario definition A scenario defines: - objective - audience - core message - preconditions - interaction steps - hero moment - output profiles Use: - `brief.md` for human-readable story and intent
SKILL.mdUpdated Apr 22, 2026
azadehtavassoli/topics/ui
development
VerifiedTrustedCommunity
# UI TOPIC SKILL ## Purpose Define deterministic UI implementation patterns with accessibility, component decomposition, and reproducible behavior. ## Framework Adapters - `topics/ui/frameworks/streamlit/` - `topics/ui/frameworks/gradio/` ## Hard MUST Rules - Component contracts must be explicit. - Accessibility checks are mandatory. - UI state transitions must be predictable and testable. - Framework-specific UI logic MUST remain inside adapter folders.
SKILL.mdUpdated Apr 3, 2026
azadehtavassoli/topics/rag
testing
VerifiedTrustedCommunity
# RAG TOPIC SKILL ## Purpose Define deterministic retrieval-augmented generation pipelines with grounded outputs and measurable evaluation. ## Hard MUST Rules 1. Retrieval, ranking, and generation stages MUST be explicit and logged. 2. Groundedness and citation integrity MUST be validated in tests. 3. Evaluation outputs MUST be structured and reproducible. 4. No real LLM/provider calls in automated tests. 5. Structured output models are mandatory.
SKILL.mdUpdated Apr 3, 2026
azadehtavassoli/topics/mcp
tools
VerifiedTrustedCommunity
# MCP TOPIC SKILL ## Purpose Implement Model Context Protocol (MCP) servers and clients with the official MCP Python SDK (`mcp`) using deterministic, transport-explicit patterns. ## When to Use - Building MCP servers over `stdio` for local process integration - Building MCP servers over Streamable HTTP for remote/networked access - Building MCP clients that connect to local (`stdio`) or online (`streamable-http`) servers - Defining reusable MCP templates and transport-specific implementation p
SKILL.mdUpdated Apr 3, 2026