SKILLEMALL.ai
GitHub ↗ RU Sign in

AD receipt-snap

Process receipt photos and PDFs, extract vendor date amount currency, convert to EUR, upload to Google Drive with proper naming Vendor_Date_EURAmount.pdf, and log to a Google Sheet. Use when user sends a receipt with #recibo or processes expense receipts for tax reporting. Handles: PDF invoices, photo screenshots, USD to EUR conversion, Spanish expense categories, quarterly reporting for tax purposes.

ClawHub Agent Skills author: MarinhoBot v1.0.6 MIT-0 5 files body ≈ 953 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorGoogle SheetsGoogle DriveFinanceData and analyticstype 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
92/100
safety, quality, tests
Safety 60%
98
Quality 40%
84
Run on models
none yet
Process rating
D
43/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Exfiltration read-dotenv README.md:56
      Reads a .env file
      cp .env.example .env
    • low Exfiltration read-dotenv receipt_snap.py:14
      Reads a .env file (code comment; quoted — discussed, not commanded)
      # Set env vars (or copy .env.example to .env and fill in)
      commentquoted

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 43/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 20When it triggers. No condition that starts the skill
    • 40Consistency. Frontmatter name (receipt-snap) differs from the folder (receipt-snap-spain)
    • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
    • 100Steps. 26 steps
    • 100Execution cost. Instruction body is 953 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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 404: enough signal without eating the budget
    • +4Structure: 21 headings
    • +3Step-by-step instructions: 26 items
    • +4Has examples (7 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    External checks

    ClawHub: clean
    This skill handles sensitive receipts, but its Google Drive, Google Sheets, exchange-rate, and local CSV behavior is disclosed and fits its tax-tracking purpose.
    LLM: benign (high) · VirusTotal: · 29 May 2026