agentleFS
Sign inStart free
prPMDevprPMDev/my-portfolio-kit/.claude/skills/anonymizer/SKILL.md

anonymizer

Skill2 starsChanged 35 days agoMITView on GitHub

Anonymize work content. Scans for sensitive elements (employer/client/project/metrics/people/internal details) and recommends keep/generalize/remove per item using story-adapter's sensitivity defaults; user applies all or adjusts.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. sliday/skills★ 3same 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 repository11 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Only flag items in real portfolio content.

    line 16
  2. Very specific:

    Log: every masked, removed, or generalized item to ANONYMIZATION-LEDGER.md exactly as in story-adapter step 4b (same header, private, …

    line 33

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Anonymizer

A standalone sensitivity pass for content you're unsure about. /story-adapter and /refresh already run this check on stories; use this for anything else (hero/about copy, testimonials, existing pages).

Not needed for: personal side projects you own, public open-source work, freelance work shared with client permission, or generic skills not tied to an employer.

Context Classification

Only flag items in real portfolio content. Classify each finding first:

ContextExampleAction
Example"Led the 12-person Pulse team" inside a before/after demoSkip
Path/Configdocs/reference/stories/, https://example.github.io/Skip
Skill DefinitionText inside a skill's .md fileSkip
Portfolio ContentCompany name in index.html hero, client in data/work.json, metric in case study copyEvaluate
Personal ProjectUser's own side project nameNote — usually OK to keep

Process

  1. Scan portfolio content and classify each finding (above).
  2. Recommend using the sensitivity table in story-adapter step 3 (.claude/skills/story-adapter/SKILL.md): keep public employer, generalize client, remove codename, ratios for metrics, remove colleague names, remove internal negatives. Every item gets a reason ("Anonymize — client name in user-facing copy, NDA risk").
  3. Ask — present the assessment below. The user accepts wholesale ("apply all") or adjusts any line. Never auto-apply; the user decides. When in doubt, recommend the safer option.
  4. Transform per the confirmed choices. Preserve the "so what": if removing context guts the point, find a safe generalization.
  5. Verify nothing identifiable remains.
  6. Log every masked, removed, or generalized item to ANONYMIZATION-LEDGER.md exactly as in story-adapter step 4b (same header, private, gitignored, never published).

Never publish: colleague names, NDA/unreleased info, proprietary methods, exact metrics tied to an identifiable company, client names without permission.

Note: Testimonial attribution (recommender names) is OK — those are public LinkedIn recommendations where the person chose to be identified.

Output

Assessment:

## Anonymization Assessment
**Content scanned:** [files]
### Verdict: CLEAN | NEEDS REVIEW

| Area | Found | Where | Recommendation (reason) |
|------|-------|-------|-------------------------|
| Employers / Clients / Projects / Metrics / People / Internal details | [item] | [file] | [Keep/Generalize/Ratio/Remove — why] |

**Skipped:** [count] items (examples, paths, config)
Say "apply all" or adjust any line, e.g. "Clients: keep, Metrics: remove".

CLEAN = nothing to flag; report and move on.

After confirmation:

## Anonymization Report
| Original | Anonymized | Reason |
|----------|------------|--------|
**Preserved:** [safe elements kept because they add value]
**Logged:** [n] rows to ANONYMIZATION-LEDGER.md
**Result:** Ready to publish / Needs user review on X

Then hand off to /voice-guardian for tone and /quality-check before publishing.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free