privacy-review
Skill0 starsChanged 15 days agoMITView on GitHub
Minimize data, define purpose and retention, and redact before sharing.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- beworkall/agent-skills-securitytheir own version, first seen Nov 15, 2026
- Smaui94/ClaudeSkillCollectiontheir own version, first seen Nov 8, 2026
- kerimovxx1990-dot/business-ai-kittheir own version, first seen Oct 20, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- beworkall/agent-skills-security★ 0same name
- kerimovxx1990-dot/business-ai-kit★ 0same name
- Smaui94/ClaudeSkillCollection★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository99 other files it gives its agents.
- accessibilitySkill
- api-designSkill
- api-docsSkill
- authenticationSkill
- authorizationSkill
- backup-recoverySkill
- career-planSkill
- changelogSkill
- ci-pipelinesSkill
- citation-checkSkill
- cloud-costSkill
- code-reviewSkill
- content-strategySkill
- context-budgetSkill
- conversion-optimizationSkill
- copy-editingSkill
- copywritingSkill
- coverage-strategySkill
- cryptographySkill
- data-qualitySkill
- data-visualizationSkill
- debuggingSkill
- decision-logSkill
- design-systemSkill
- dockerSkill
- documentationSkill
- e2e-testingSkill
- email-marketingSkill
- etl-designSkill
- experiment-designSkill
- experiment-methodsSkill
- fact-checkingSkill
- feedback-loopSkill
- flaky-testsSkill
- forecastingSkill
- fuzz-testingSkill
- go-concurrencySkill
- grant-writingSkill
- incident-opsSkill
- incident-responseSkill
- injection-defenseSkill
- integration-testingSkill
- interview-prepSkill
- job-fitSkill
- kubernetesSkill
- legacy-codeSkill
- linux-troubleshootingSkill
- literature-reviewSkill
- llm-evaluationSkill
- marketing-analyticsSkill
- meeting-facilitationSkill
- ml-evaluationSkill
- networkingSkill
- observabilitySkill
- onboardingSkill
- paid-adsSkill
- pandas-analysisSkill
- patent-searchSkill
- peer-reviewSkill
- portfolioSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Verify with a reproducible exploit or test.
- Distinctive: line 25
No secret appears in logs or artifacts.
- Distinctive: line 31
No fabricated sources, data, or test results.
- Distinctive: line 32
If the task falls outside the method, say so and stop.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Privacy review
Use
Apply this when the task matches the description. Keep the output decision-useful and mark unknowns.
Method
- Map assets, trust boundaries, and attacker capability.
- Assume attacker control of every input.
- Apply least privilege and defense in depth.
- Verify with a reproducible exploit or test.
Focus: Privacy review.
Verification
- The attack path is blocked or explicitly accepted.
- No secret appears in logs or artifacts.
- State clearly what was not verified.
Boundaries
- This is a checklist, not proof of correctness.
- No fabricated sources, data, or test results.
- If the task falls outside the method, say so and stop.
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.