data-analysis is agent-read markdown (skill) from nahid-sparktales/agent-dispatcher: Get a defensible answer out of a dataset — grain and denominators pinned, missing data accounted for, aggregates checked against their segments, and every number reproducible from raw input by a script. Use when asked what a dataset shows, when a number needs explaining or two numbers disagree, or before any finding from data is reported to someone who will act on it. Not for defining product metrics or instrumentation, not for building the pipeline that produced the data, and not for designing .
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Data analysis
Wrong analyses rarely come from wrong arithmetic. They come from a denominator drawn from a
different population, rows that silently disappeared, an aggregate whose segments all point the
other way, or a correlation written up with a causal verb.
## When this fires
A dataset has to answer a question, a reported number needs explaining or reconciling, or a finding
from data is about to be shown to someone who will decide something. It does not fire when the
task is only to render an agreed number as a chart.
## What a result is allowed to claim
Pick the weakest rung that the evidence supports and write the sentence at that rung:
- **Described** — this is what the data contains, for this population and window.
- **Associated** — these move together; the confounders are named and unresolved.
- **Predictive** — this pattern held out of sample, on data the fitting never saw.
- **Causal** — an experiment or a design with an identified counterfactual supports it.
Most exploratory work stops at the first two. Writing a rung you did not earn is the failure this
procedure exists to prevent.
## Procedure
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_tus5sexrzylu6rjf
GET https://markdownregistry.com/api/v1/resolve?ref=nahid-sparktales/agent-dispatcher/data-analysis
GET https://markdownregistry.com/api/v1/blob/dc7b69c91df1688cbeaafef044a63de12a5626835480ec4716b5b66edb4d7673
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
nahid-sparktales/agent-dispatcher · skills/agent-dispatcher/SKILL.md · Route work to a specialist role and load its task-specific guidance. Use when the user invokes /agent-dispatcher, names…
nahid-sparktales/agent-dispatcher · skills/ai/agent-design/SKILL.md · Scope an agent or subagent before it is built — the one job it owns, the smallest tool set that closes that job, what…
nahid-sparktales/agent-dispatcher · skills/ai/agent-evals/SKILL.md · Build an eval suite that can actually detect a regression — cases pulled from real traffic, graders that check…
nahid-sparktales/agent-dispatcher · skills/ai/context-engineering/SKILL.md · Decide what actually occupies the model's window — progressive disclosure through an index, retrieval versus inlining…
nahid-sparktales/agent-dispatcher · skills/ai/llm-observability/SKILL.md · See what an agent actually did — one trace per run with nested model, tool and retrieval spans, token and latency…
nahid-sparktales/agent-dispatcher · skills/ai/mcp-design/SKILL.md · Build an MCP server, or bring an existing one into a project — choosing the transport, deciding which tools, resources…
nahid-sparktales/agent-dispatcher · skills/ai/memory-design/SKILL.md · Decide what an agent should remember, which layer holds it, who it is scoped to, and how a stale or contradicted memory…
nahid-sparktales/agent-dispatcher · skills/ai/model-routing/SKILL.md · Pick a model per job and degrade sensibly when one fails — a quality bar per call site, candidates compared on the same…
nahid-sparktales/agent-dispatcher · skills/ai/prompt-engineering/SKILL.md · Write or revise a prompt so it holds up — output contract, instruction placement, examples that earn their place, an…
nahid-sparktales/agent-dispatcher · skills/ai/prompt-injection-defense/SKILL.md · Treat everything an agent reads but did not author as data rather than instructions — an explicit trust boundary, a…
nahid-sparktales/agent-dispatcher · skills/ai/retrieval-rag/SKILL.md · Build and fix retrieval that actually returns the right passage — structure-aware chunking, one pinned embedding model…
nahid-sparktales/agent-dispatcher · skills/ai/structured-output/SKILL.md · Get parseable, trustworthy structured results out of a model — schema design, the enforcement mechanism the provider…
bytedance/deer-flow · skills/public/data-analysis/SKILL.md · Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate…
dougtrajano/pydantic-ai-skills · examples/skills/data-analysis/SKILL.md · Profile and aggregate a bundled sales dataset - group revenue by region, category, channel or month, apply filters, and…
evovexai/evoflow · skills/public/data-analysis/SKILL.md · Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate…
trpc-group/trpc-agent-python · examples/skills/skills/data_analysis/SKILL.md · Python-based data analysis tools using pandas and numpy for data processing and visualization.
