safe-data-handling
Skill86 starsChanged 52 days agoMITView on GitHub
Use this when reading, writing, moving, copying, modifying, deleting, or generating data files — including any operation that touches data/raw, data/external, data/interim, data/processed, or outputs directories.
- Reads credentials
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- analysis-reportingSkill
- causal-inference-diagnosticsSkill
- dataframe-polarsSkill
- notebook-workflowSkill
- path-and-ioSkill
- plan-analysisSkill
- predictive-modeling-diagnosticsSkill
- prepare-prSkill
- python-project-opsSkill
- python-styleSkill
- review-sqlSkill
- run-edaSkill
- run-modelingSkill
- simulation-optimization-diagnosticsSkill
- sql-analysisSkill
- statistical-inference-diagnosticsSkill
- statistical-ml-reviewSkill
- summarize-analysisSkill
- sync-agent-docsSkill
- unsupervised-eda-diagnosticsSkill
- update-agent-docsSkill
- visualizationSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 5 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 8
Use this skill before reading, writing, moving, modifying, deleting, or generating data files.
- Distinctive: line 12
Never: commit raw data, credentials, API keys, tokens, or customer-level records.
- Very specific: line 14
Treat data/raw/ and data/external/ as immutable.
- Very specific: line 15
Write derived data to data/interim/, data/processed/, or outputs/.
- Very specific: line 16
Before writing output, confirm the target path is not under data/raw/ or data/external/.
- Distinctive: line 37
Do not include personally identifiable information (PII) or customer-level records in committed files.
- Very specific: line 38
If analysis requires customer-level data, keep it in data/raw/ (gitignored) and never commit.
- Distinctive: line 40
When in doubt, ask before writing customer-level data to any path.
- Distinctive: line 46
Do not hard-code API keys, tokens, or passwords in code or notebook outputs.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill: Safe Data Handling
Use this skill before reading, writing, moving, modifying, deleting, or generating data files.
Hard Rules
- Never commit raw data, credentials, API keys, tokens, or customer-level records.
- Never directly modify, overwrite, delete, or regenerate raw data.
- Treat
data/raw/anddata/external/as immutable. - Write derived data to
data/interim/,data/processed/, oroutputs/. - Before writing output, confirm the target path is not under
data/raw/ordata/external/.
Recommended Workflow
- Identify whether input data is raw, external, interim, processed, or output.
- Read raw/external data as immutable input — never modify the source.
- Write generated artifacts to a separate output path (
data/interim/,data/processed/, oroutputs/). - Summarize files read and written at the end of the operation.
Directory Roles
| Directory | Role | Mutable? |
data/raw/ | Original source data | No |
data/external/ | Third-party reference data | No |
data/interim/ | Intermediate transforms | Yes |
data/processed/ | Final cleaned/derived data | Yes |
outputs/ | Figures, tables, reports | Yes |
PII and Customer-Level Records
- Do not include personally identifiable information (PII) or customer-level records in committed files.
- If analysis requires customer-level data, keep it in
data/raw/(gitignored) and never commit. - Aggregated or anonymized outputs are acceptable for
data/processed/oroutputs/. - When in doubt, ask before writing customer-level data to any path.
- Analysis outputs must not allow individuals to be re-identified.
Credentials and Secrets
.envis gitignored..env.examplelists key names only — never real values.- Do not hard-code API keys, tokens, or passwords in code or notebook outputs.
- Load secrets from environment variables with
python-dotenv.
Verification
data/raw/ and data/external/ are gitignored, and CI enforces the rules above:
uv run python scripts/check_no_raw_data_commit.py # rawデータのコミットを検知
uv run python scripts/check_no_sensitive_patterns.py # 秘密情報のパターンを検知Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

