Privacy guard
Skill alainlebret/claude-agents/higher-ed-teaching-agents/skills/privacy-guard
Detects and redacts personally identifiable or sensitive data in submissions and generated reports before evaluation outputs are finalized.From its SKILL.md
npx -y skills add alainlebret/claude-agents --skill privacy-guardAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
0.9 KB, 145 tokens by cl100k_base, as published. Nobody here has run it
Privacy Guard
Goal
Enforce privacy-by-default for submission evaluation workflows.
Inputs
- Student submissions and logs
- Intermediate evidence files
- Mission and evaluation metadata
Produce
Write:
privacy-report.json- Redacted mirrors under
sanitized/ anonymization-map.json(restricted access)
Mandatory checks
- Detect direct identifiers (names, emails, student IDs).
- Detect accidental sensitive payloads in logs/datasets.
- Ensure final evidence and feedback reference anonymized IDs.
Rules
- Preserve grading-relevant content while redacting identities.
- Mark unresolved sensitivity as
failand block publication. - Keep redaction operations auditable in report entries.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most quality gates skills give in 145 tokens
Counted across 1,195 of the 2,094 authors here whose files we hold, read 2026-08-07
- Read the output and check the exit codein 54 of 1195, across 14 files
- Verify requirements using a line-by-line checklistin 53 of 1195, across 12 files
- Identify the verification command proving the claimin 51 of 1195, across 12 files
- Run the full verification commandin 50 of 1195, across 11 files
- Verify output confirms the claimin 49 of 1195, across 12 files
- Check version control diff after agent delegationin 46 of 1195, across 6 files
- State claim with evidencein 44 of 1195, across 4 files
- Run the test suitein 33 of 1195, across 26 files
- Keep state in memory by defaultin 27 of 1195, across 6 files
- Make prototype runnable with one commandin 26 of 1195, across 5 files
- Produce a verification reportin 25 of 1195, across 14 files
- Detect the package manager from lockfilesin 24 of 1195, across 5 files
Said here and by no other author read
- detect direct identifiers in submissions
- detect accidental sensitive payloads in logs and datasets
- ensure final evidence references anonymized IDs
- preserve grading-relevant content while redacting identities
- keep redaction operations auditable in report entries
- write privacy-report.json
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.