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 skills add sAjAd-2006/bizinsight-agent --skill data-analysisgit clone --depth 1 https://github.com/sAjAd-2006/bizinsight-agentWrote 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/sajad-2006/bizinsight-agent/data-analysis)<a href="https://agentmods.dev/skills/sajad-2006/bizinsight-agent/data-analysis"><img src="https://agentmods.dev/badge/skills/sajad-2006/bizinsight-agent/data-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sajad-2006/bizinsight-agent/data-analysis"><img src="https://agentmods.dev/badge/skills/sajad-2006/bizinsight-agent/data-analysis.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00053 | $0.00471 |
| Opus 5.5 | $0.00021 | $0.00188 |
| Sonnet 5.5 | $0.00011 | $0.00094 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
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 2mo 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.
What it actually says
Data Analysis Skill
Methodology
Follow this 5-step analysis pipeline sequentially:
Step 1: Column Profiling
- Identify all columns and their data types (numeric, categorical, datetime)
- Count missing values per column
- Determine cardinality of categorical columns
- Report basic shape of the dataset (rows × columns)
Step 2: Descriptive Statistics
- For numeric columns: mean, median, std, min, max, quartiles (Q1, Q3)
- For categorical columns: mode, unique count, frequency distribution (top 5)
- For datetime columns: date range, frequency, gaps
Step 3: Trend Analysis
- Group data by meaningful time periods (daily, weekly, monthly, quarterly)
- Calculate period-over-period changes (absolute and percentage)
- Identify upward, downward, or stable trends
- Note any seasonal patterns
Step 4: Anomaly Detection
- Identify outliers using IQR method (values below Q1 - 1.5×IQR or above Q3 + 1.5×IQR)
- Flag statistical anomalies (values beyond 2 standard deviations from mean)
- Check for data quality issues: negative values where unexpected, impossible dates
Step 5: Correlation Analysis
- Compute pairwise correlations between numeric columns
- Identify strong correlations (|r| > 0.7)
- Note any counter-intuitive correlations
- Suggest causal hypotheses for strong correlations
Output Format
Present findings as a structured analysis with:
- Executive summary (3-5 bullet points)
- Detailed findings per step
- Key metrics table
- Flags and warnings
Tools Used
read_csv- Load datasetget_columns- Inspect column structurefilter_rows- Subset data for segmented analysiscompute_aggregate- Calculate statisticsdetect_anomalies- Find outliers
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.
- 2mo ago First seen · 57 lines · 53 tokens per session scan A f69f218c3b6f
data-analysis is a skill published in the GitHub repository sAjAd-2006/bizinsight-agent (2 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 471 once invoked, about $0.0002 per session on Opus 5.5. 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
majia-guanyuan
A practical extension layer for Guandata BI, a business-intelligence platform used to query data, build charts, and publish dashboards. It covers advanced data-pipeline work and custom HTML, CSS, and JavaScript dashboards beyond the standard tools.
datalens-editor
Use when authoring or diagnosing DataLens JavaScript Editor table, Gravity, Advanced, Markdown, selector charts, or HTML inside an Editor chart. Not for standalone HTML Pages, native Wizard charts, or independent SDK scripts.
datalens-dataset-wizard
Use when creating, updating, validating, or previewing DataLens datasets and native Wizard charts. Not for metadata-only reads, cloud identity lookup, standalone HTML, or independent SDK scripting.
datalens-dashboard
Use when composing, updating, or visually verifying DataLens dashboard tabs, widgets, selectors, parameters, relations, styles, or layout. Not for standalone HTML Pages, SDK scripts, or metadata-only inspection.
datalens-inspect
Use when reading DataLens metadata, authentication, workbook inventory, relations, current errors, or cloud RLS subject identities without changing objects or access. Not for authoring, backup, or independent SDK scripts.
datalens-maintenance
Use when exporting DataLens backups, inspecting administrative capabilities, previewing or applying dependency-safe cleanup, or working on standalone HTML Pages. Not for Editor HTML cells, ordinary chart authoring, or RLS identity lookup.