Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Analyze CSV · cowork-os | DecimalAI

databy cowork-os

Analyze CSV

cowork-os/analyze-csv

Source cowork-os/cowork-os ↗License MIT

Load a CSV and provide insights

NewMaintained

Automatic

Data Analyst pack

Last verified 8/20/2026

What it changes

Passed 2 of 8 test cases with the skill, and 3 of 8 without it.

Without skill41%

With skill27%

Checks it passed that the model alone missed

The response lists summary metrics for numeric fields.
The response lists datatype observations for the columns.
The response identifies missing value counts in the customer dataset.

and 3 more in the full report

2 fixed4 passed either way11 still failing5 broke

Pass-rate lift: -14 pp
Tokens: 0%
Agent turns: 0%
Response time: -12%

Model gemini-3.6-flashMeasured 8/20/2026v1 · latest is v26 of 22 cases passed with skill · 8 comparable

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/cowork-os-analyze-csv/SKILL.md https://app.decimal.ai/s/cowork-os-analyze-csv/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add cowork-os-analyze-csv, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/cowork-os-analyze-csv/ and pins it in .decimal/skills.lock

decimalai skills add cowork-os-analyze-csv

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/cowork-os-analyze-csv/SKILL.md https://app.decimal.ai/s/cowork-os-analyze-csv/SKILL.md

Raw file: /s/cowork-os-analyze-csv/SKILL.md ↗ · machine-readable summary at /s/cowork-os-analyze-csv.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

Please run a diagnostic on the CSV stored at `user_exports/inventory.csv`. I want a structured overview covering dataset dimensions, field properties, summary metrics, and noticeable outliers or missing values.

What was checked, without and with the skill
Checked	Without skill	With skill
The response delivers dataset profiling output directly rather than supplying code for local execution.	Missed	Passed
The response reports dataset dimensions including row and column totals.	Missed	Passed
The response lists summary metrics for numeric fields.	Missed	Passed

case-03 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md39 linessingle file

Analyze CSV

Purpose

Load a CSV and provide insights

Routing

Use when: Use when asked to analyze a CSV file for schema, data quality, statistical summaries, or anomalies.
Do not use when: Don't use this for non-tabular files or for purely visual charting without data inspection.
Outputs: Concise dataset summary with column stats, missing-value signals, and actionable insights.
Success criteria: Reports include row/column counts, datatype observations, numeric statistics, and high-confidence anomalies.

Trigger Examples

Positive

Use the analyze-csv skill for this request.
Help me with analyze csv.
Use when asked to analyze a CSV file for schema, data quality, statistical summaries, or anomalies.
Analyze CSV: provide an actionable result.

Negative

Don't use this for non-tabular files or for purely visual charting without data inspection.
Do not use analyze-csv for unrelated requests.
This request is outside analyze csv scope.
This is conceptual discussion only; no tool workflow is needed.

Parameters

Name	Type	Required	Description
path	string	Yes	Path to the CSV file

Runtime Prompt

Current runtime prompt length: 499 characters.
Runtime prompt is defined directly in ../analyze-csv.json.

Track record

Benchmark

2 / 8

test cases passed, vs 3 / 8 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/25/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

cowork-os / cowork-os

resources/skills/analyze-csv/SKILL.md

View on GitHub ↗

License MITImported 9/25/2026Version v2

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Analyze CSV

Purpose

Routing

Trigger Examples

Positive

Negative

Parameters

Runtime Prompt

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills