SKILLEMALL.ai
GitHub ↗ RU Sign in

AD markitdown

Use when a NON-multimodal agent (a text-only LLM backend that cannot read attachments) receives a document — PDF, Word (docx), PowerPoint (pptx), Excel (xlsx/xls), EPUB, HTML, CSV, JSON, XML, or ZIP — and you need its CONTENT to read, summarize, quote, or store it. The model can't open the file itself, so convert it to Markdown first with the markitdown MCP server (local, free, no API key). An OPTIONAL OCR layer reads scanned PDFs and images via an OpenAI-compatible vision model, but ONLY when a key is configured. Skip for files the agent can already read as plain text, and for plain images when no OCR key is set.

ClawHub Agent Skills author: Tommy, Joon Shin v1.0.0 MIT-0 2 files body ≈ 1 683 tokens Open the sourceclawhub.ai↗ analyzed 35 h ago

Use when a NON-multimodal agent (a text-only LLM backend that cannot read attachments) receives a document — PDF, Word (docx), PowerPoint (pptx), Excel…

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationPowerPointWordExcelSlackAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
93/100
safety, quality, tests
Safety 60%
100
Quality 40%
83
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 0

    ✓ No critical or high findings

    Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 46/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 40Consistency. Frontmatter name (markitdown) differs from the folder (markitdown-skill-for-non-multimodal-agent)
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 85Steps. 17 steps, 1 vague phrases
    • 100Execution cost. Instruction body is 1683 tokens
    • 100Running it twice. No mutating operations
    • 100Progress reporting. Reports progress

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 621: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 17 items
    • +4Has examples (6 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

    External checks

    ClawHub: suspicious
    The skill bundle is mostly coherent for ClawHub maintenance, but one review helper defaults to launching nested Codex with full sandbox bypass, which is broader authority than a review helper needs.
    LLM: suspicious (medium) · VirusTotal: · 13 Jun 2026