sofer/anonymise
skills/anonymise/SKILL.md
Anonymise CSV files by removing personal identifying information and adding datetime stamps. Use when user wants to process a new CSV file or strip PII from data.
$ install --global
skillsauthnpx skillsauth add sofer/.agents anonymiseInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 29, 2026, 9:01 AM38.7s3 files scanned
SKILL.md
- name:
- anonymise
- description:
- Anonymise CSV files by removing personal identifying information and adding datetime stamps. Use when user wants to process a new CSV file or strip PII from data.
CSV Anonymiser
When the user wants to anonymise a CSV file or process new data:
1. Check .gitignore
First, verify that CSV files are excluded from git:
cat .gitignore
If *.csv is not present, add it:
echo "*.csv" >> .gitignore
2. Identify the CSV File
The script can auto-detect new CSV files:
- Auto-detection: Files without a timestamp pattern (YYYYMMDD_HHMMSS) in their name
- New files: Any CSV file that hasn't been processed yet
- If multiple new files exist, the script will list them and ask user to specify which one
3. Remove Personal Identifying Information
Columns to remove are configured in ~/.agents/skills/anonymise/config.txt:
- One column header per line
- Lines starting with
#are comments - Default includes
"Record - Airtable ID"(PII)
Process the file:
- Read the CSV file
- Remove all columns listed in
~/.agents/skills/anonymise/config.txt - Keep all other columns intact
- Preserve the header row (minus the removed columns)
4. Add Datetime Stamp
The script will:
- Create a new file with format:
YYYYMMDD_HHMMSS.csv(just the timestamp) - Delete the original file
Example: ILR data 25_26-Social value data for Dingley.csv becomes 20231216_143022.csv
5. Run the Anonymisation Script
Execute the Python script located in the same directory as this skill:
Auto-detect mode (finds CSV files without timestamps):
python3 ~/.agents/skills/anonymise/anonymise.py
Specific file mode:
python3 ~/.agents/skills/anonymise/anonymise.py "filename.csv"
If multiple new files are found in auto-detect mode, the script will list them and you'll need to specify which one to process.
6. Confirm Completion
After processing:
- Confirm the anonymised file was created with timestamp
- Confirm the original file was removed
- Confirm .gitignore includes
*.csv - Remind user that CSV files won't be committed to git
Notes
- Uses British English spelling throughout
- Handles UTF-8 BOM encoding (
utf-8-sig) for compatibility - Preserves all data except the first column
- Assumes consistent CSV structure across files
- Files are automatically excluded from version control
Related Skills
sofer/agent-config-audit
tools
VerifiedTrustedCommunity
Check whether Claude and Codex have equivalent access to shared agent resources, skills, hooks, plugins, MCP servers, permissions, startup behaviour, and provider-specific adapter config. Use when comparing agent environments, debugging missing capabilities after restart, or deciding whether to symlink a resource or configure a runtime.
4SKILL.mdUpdated May 10, 2026
sofer/skill-usage
testing
VerifiedTrustedCommunity
Record substantive skill use in an append-only local log. Use after choosing or invoking a non-system skill for real work, when a skill is inspected but not used, or when a skill fails to apply. Do not use for routine system skills or incidental file reads.
4SKILL.mdUpdated May 1, 2026
sofer/problem-statement
testing
VerifiedTrustedCommunity
Turn a vague or underspecified request into a self-contained problem statement. Use when the user has a rough idea, when a request would fail if handed directly to an agent, or before non-trivial work that needs shared understanding.
4SKILL.mdUpdated May 1, 2026
sofer/learning
data-ai
VerifiedTrustedCommunity
Append a one-line learning to ~/.agents/learning-log.md. Use when the user types /learning, or when something genuinely worth remembering surfaced during work and the user confirms it should be captured.
4SKILL.mdUpdated May 1, 2026