SKILLEMALL.ai
GitHub ↗ RU Sign in

AC spreadsheet-qa

Answers business questions about the user's own spreadsheet or data export (CSV, TSV, XLSX from a CRM, Shopify, Stripe, QuickBooks, ad platforms, HR or payroll systems) correctly and auditably. Profiles every file first (grain, duplicate keys, embedded Grand Total rows, text-stored numbers, mixed currencies, UTC timestamps, Excel serial dates, hidden rows), states the metric definition used, computes every number in SQL or pandas instead of mental math, checks joins for fan-out, reconciles to a known total, and returns the query, filters, row counts, and rows behind the answer. Use this whenever the user says "analyze this spreadsheet", "how many...", "what's the total in this export", "which customers...", "pivot this", "revenue by month", "top 10", "what's our churn/MRR/AOV", or asks any question about their data, CSV, or Excel file, even a quick one. Also use when they ask to change values in a data file.

OneWave-AI/claude-skills Agent Skills author: OneWave-AI 17 files · 5 scripts body ≈ 1 913 tokens Open the sourcegithub.com↗ analyzed 6 h ago

Answers business questions about the user's own spreadsheet or data export (CSV, TSV, XLSX from a CRM, Shopify, Stripe, QuickBooks, ad platforms, HR or…

As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

ProcedureExcelStripeShopifyData and analyticstype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
A
97/100
safety, quality, tests
Safety 60%
100
Quality 40%
93
Run on models
none yet
Process rating
C
52/100
Has gaps
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 · 0

    ✓ No critical or high findings

    Files scanned: 6. 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 52/100

    • 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
    • 0Progress reporting. Says nothing while it works
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 15 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1913 tokens
    • 100Running it twice. Mutating operations check current state

    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

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Description length 921: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 8 example trigger phrases
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 15 items
    • +4Has examples (4 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)
    • +3All 3 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.