agentleFS
cobusgreylingcobusgreyling/grok-bot-templates/skills/sanitize-share/SKILL.md

sanitize-share

Skill14 starsChanged 3 months agoMITView on GitHub

Paste this into Grok Bot after a successful run: Save the process we just used as a skill called “Sanitize Share”. A useful skill states the six fields from Skills and routines. The owner wants to share a Bot as a public template and needs the description, skills, and routines stripped of secrets, customer data, and internal URLs before the link goes out. No key-shaped strings, no @customer domains, no .internal hosts. Approval boundaries are still present after redaction. A…

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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
  1. Distinctive:

    Read the description and any skill/routine text.

    line 21
  2. Distinctive:

    No key-shaped strings, no @customer domains, no .internal hosts.

    line 28
  3. Distinctive:

    Do not create the public share link yourself.

    line 38

≈ “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

Sanitize Share

Paste this into Grok Bot after a successful run:

Save the process we just used as a skill called “Sanitize Share”.

A useful skill states the six fields from Skills and routines.

1. When to use it

The owner wants to share a Bot as a public template and needs the description, skills, and routines stripped of secrets, customer data, and internal URLs before the link goes out.

2. Required inputs and access

  • The Bot's current description, skill list, and routine text
  • Optional extra files the owner is about to attach to the profile

3. Sequence of work

  1. Read the description and any skill/routine text.
  2. Flag API keys, tokens, emails, customer names, internal hostnames, and staging URLs.
  3. Propose a redacted description. Do not silently delete standing safety rules.
  4. Confirm share-safe so identity, job, boundary, and first task remain; secrets gone.

4. How to validate the result

No key-shaped strings, no @customer domains, no .internal hosts. Approval boundaries are still present after redaction.

5. What to return

A share-safe PROFILE and a diff of what was removed, plus a reminder that the link is public and does not copy the computer or logins.

6. What requires approval

Do not create the public share link yourself. The owner copies it from the Bot after they accept the redaction.

Type / in the composer to reference a saved skill. If it does not appear, open Settings → Plugins → Yours and enable it for this Bot.

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.