agentsclimarketplace
Sign in

Data minimization

Skill 26zl/universal-agent-skills/skills/data-minimization

Keep real personal and confidential data out of code, tests, fixtures, logs, error messages, examples, and prompts; use synthetic data, and mask identifiers when a real record is unavoidable. Use when writing tests, fixtures, seed data, logging, debugging output, or documentation, or when moving data between systems; do not use to remove lawful data processing that the product itself performs.From its SKILL.md

Install
npx -y skills add 26zl/universal-agent-skills --skill data-minimization

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 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.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.7 KB, 233 tokens by cl100k_base, as published. Nobody here has run it

Data Minimization

Personal data belongs in the systems built to protect it, not in development artifacts.

Rules

  • Never copy real names, e-mail addresses, national identifiers, or health, financial, or location records into tests, fixtures, seeds, examples, or documentation; generate synthetic data instead.
  • Never log personal or confidential data in plaintext; log stable opaque identifiers and mask everything else.
  • Keep production data out of scratch files, issue trackers, and shared prompts; when a real record is essential for a reproduction, reduce it to the minimal fields and mask direct identifiers.
  • Treat data supplied in a conversation as confidential input: use it for the task, never persist it into the repository.
  • When designing schemas or interfaces, collect only fields with a stated purpose, and flag fields that look like surplus collection.
  • Report any discovered dump, export, or backup of personal data inside the repository as a finding instead of working around it.

Boundaries

  • The product's lawful processing of personal data is out of scope; this skill governs development artifacts and diagnostics.
  • Regulatory retention and audit requirements win over minimization when they conflict.

What ships with it: 1 file

219 B alongside SKILL.md

agents/

Gives 0 of the 12 instructions most docs writing skills give in 233 tokens

Counted across 1,951 of the 3,904 authors here whose files we hold, read 2026-09-06

  • Use third-person for skill descriptionsin 54 of 1951, across 35 files
  • Start descriptions with Use whenin 43 of 1951, across 29 files
  • Run baseline scenarios before writing any skillin 40 of 1951, across 26 files
  • Use active voicein 40 of 1951, across 36 files
  • Map file responsibilities before defining tasksin 36 of 1951, across 29 files
  • Use checkbox syntax for tracking stepsin 35 of 1951, across 27 files
  • Ask one question at a timein 35 of 1951
  • Offer execution options after saving the planin 33 of 1951, across 24 files
  • Include complete code in every stepin 33 of 1951, across 27 files
  • Design units with clear boundaries and interfacesin 31 of 1951, across 23 files
  • Announce the skill usage at the startin 30 of 1951
  • Verify agent compliance after adding the skillin 29 of 1951, across 17 files

Said here and by no other author read

  • Generate synthetic data for tests and documentation
  • Mask identifiers in logs and error messages
  • Reduce real records to minimal fields for reproduction
  • Collect only fields with a stated purpose
  • Flag surplus data collection in schemas
  • Report discovered personal data dumps as findings

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.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.