Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/thuong-nc/perlytics-skill/exploratory-data-analysisnpx skills add thuong-nc/perlytics-skill --skill exploratory-data-analysisgit clone --depth 1 https://github.com/thuong-nc/perlytics-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thuong-nc/perlytics-skill/exploratory-data-analysis)<a href="https://agentmods.dev/skills/thuong-nc/perlytics-skill/exploratory-data-analysis"><img src="https://agentmods.dev/badge/skills/thuong-nc/perlytics-skill/exploratory-data-analysis.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00028 | $0.01265 |
| Opus 5 | $0.00014 | $0.00633 |
| Sonnet 5 | $0.00006 | $0.00253 |
| Haiku 4.5 | $0.00003 | $0.00127 |
Grade A, and why
exploratory-data-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exploratory Data Analysis
Purpose
Understand a dataset's structure, distributions, concentrations, and notable patterns before any hypothesis-driven analysis begins.
When to use
Use this skill when:
- a user shares a dataset with no specific analytical question ("analyze this CSV," "what's in here?")
- you need to understand what a dataset contains before choosing which analytical skill to apply
- the business context is unclear and the data itself needs to inform the direction
- a first look is needed to surface what questions the data is well-positioned to answer
When not to use
Do not use this skill when:
- the analytical question is already specific and well-framed - proceed directly to the relevant skill
- data quality has not yet been checked - run
data-quality-checkfirst if the dataset is new and untested
Required thinking discipline
- Describe first, conclude never. EDA surfaces patterns and candidate questions - it does not answer them.
- Do not force a narrative on the data. If nothing is surprising, say so.
- Surface concentrations and anomalies without explaining them - explanation requires hypothesis and evidence.
- End by recommending which analytical direction the data supports, not by stating what the data means.
- Evidence constraint: Every conclusion must cite specific data — a number, a rate, a segment, or a timeframe. Do not speculate without evidential basis. If data is insufficient, state what is missing rather than asserting an unsupported inference.
Workflow
-
Inventory: Record the dataset dimensions (row count, column count, time range if a time column exists, primary entity if identifiable). State what each column appears to represent.
-
Distribution summary:
- For numeric columns: range, approximate mean and median, skew direction, and whether extreme values exist.
- For categorical columns: cardinality (how many unique values), top 5 values and their share, and whether there is a long tail.
- Flag any column where one value dominates more than 80% of rows - this limits the column's usefulness for segmentation.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 109 lines · 28 tokens per session scan A 9105014b24ee
exploratory-data-analysis is a skill published in the GitHub repository thuong-nc/perlytics-skill (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 1,265 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
sn-image-imitate
Generates a new image that imitates the style of a reference image while updating content based on user intent. Uses a three-stage pipeline: image annotation (long caption), caption rewriting, and image generation. Use when user asks to "imitate style", "保持这个风格重画", "按这张图风格生成", or "style transfer with new content".
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
jobs-to-be-done
Discover what customers truly need by analyzing the "job" they hire your product to do. Use when the user mentions "customer discovery", "why customers churn", "what job does this solve", "competing against luck", "product-market fit", "switching behavior", "milkshake moment", or "functional vs emotional jobs". Also…
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…